Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
e52989280a | ||
|
|
621f8e4d29 | ||
|
|
7a1c3149fd | ||
|
|
5467db4447 | ||
|
|
96bdcb3dea | ||
|
|
54278ea1f0 | ||
|
|
4e9aec6d2a | ||
|
|
db79350caa | ||
|
|
a6e0177cb9 | ||
|
|
d3968822a7 | ||
|
|
b06d979525 | ||
|
|
1ed782560d | ||
|
|
3c41c9721d | ||
|
|
e805212ae6 | ||
|
|
80567df1ea | ||
|
|
fab89d2374 | ||
|
|
a937fa5100 | ||
|
|
a298ceb18c | ||
|
|
c7c02bb4de | ||
|
|
a7debec87d | ||
|
|
b4b941fe1b | ||
|
|
3ddc4bd007 | ||
|
|
27c68f293d | ||
|
|
ee3d1768e3 | ||
|
|
f1124e04df | ||
|
|
55c8c07b90 | ||
|
|
6bb5929e09 | ||
|
|
6ac0f84e27 | ||
|
|
162f9ed6d2 | ||
|
|
7600bef8e7 | ||
|
|
9df96572ac | ||
|
|
8ff0d31e57 | ||
|
|
5160d20fbc | ||
|
|
9f730b9fb5 | ||
|
|
a7ecc57432 | ||
|
|
ec5790a90c | ||
|
|
57e5c108de | ||
|
|
84bb44d222 | ||
|
|
026a243f81 | ||
|
|
d1e5e031e3 | ||
|
|
a5bb93ddec | ||
|
|
fe27e44081 | ||
|
|
d21a6b1ee8 | ||
|
|
395d90b5a6 | ||
|
|
635272b892 | ||
|
|
0edb590bb5 | ||
|
|
5aa4216c86 | ||
|
|
1ae8fc798e | ||
|
|
e8ec271f0b | ||
|
|
9e3a150196 | ||
|
|
acd23bf662 | ||
|
|
5532731910 | ||
|
|
029abbd614 | ||
|
|
46ecb808f7 | ||
|
|
5befed7332 | ||
|
|
15a192c63a | ||
|
|
317485b122 | ||
|
|
0f23c6d425 | ||
|
|
44d531fdb8 | ||
|
|
a3262a8f9c | ||
|
|
7e9dca632b | ||
|
|
cc7de0edb7 | ||
|
|
808814bce7 | ||
|
|
89000c1c33 | ||
|
|
71cbd82ef4 | ||
|
|
dff15cb8d6 | ||
|
|
befa12bb23 | ||
|
|
f86a2d3a82 | ||
|
|
3d7c1ba1ec | ||
|
|
a64a2fc243 | ||
|
|
b65d2cc73f | ||
|
|
207260aca1 | ||
|
|
81b27340e5 | ||
|
|
a92665e85c | ||
|
|
e7bf00aa95 | ||
|
|
392c6930bb | ||
|
|
ed253fef99 | ||
|
|
cef25cc601 | ||
|
|
e1b13e369c | ||
|
|
ed09f05424 | ||
|
|
369831eb76 | ||
|
|
0d17a8e6b5 | ||
|
|
2e4f05e8ec | ||
|
|
1891b2edde | ||
|
|
477faee1c7 | ||
|
|
5957b250f0 | ||
|
|
7d27e67966 | ||
|
|
c31d96dabe | ||
|
|
4ab9ae5a71 | ||
|
|
888da4e208 | ||
|
|
8f480ead6a | ||
|
|
cdc3b4d6b1 | ||
|
|
bae1797e83 | ||
|
|
7319a026ab | ||
|
|
509b6da063 | ||
|
|
10ea37b732 | ||
|
|
6ce126d6d8 | ||
|
|
ab76a47eb8 | ||
|
|
5261efebc3 | ||
|
|
ca5486dc5a | ||
|
|
eecc0dea91 | ||
|
|
cf7c95e700 | ||
|
|
366bc21d1e | ||
|
|
526ddacd2f | ||
|
|
ab45b19e7e | ||
|
|
6289d9cab0 | ||
|
|
85e0a544fe | ||
|
|
6f47cd318a | ||
|
|
66758448cb | ||
|
|
c8673fe517 | ||
|
|
b5a958745b | ||
|
|
cfd079bbcb | ||
|
|
0e8365ff80 | ||
|
|
758b9d60bd | ||
|
|
b40cddd144 | ||
|
|
dabd18c0de | ||
|
|
e1ffd0e8a9 | ||
|
|
731d580a83 | ||
|
|
d4f95eca45 | ||
|
|
0477499b77 | ||
|
|
29de4d245e | ||
|
|
2012ec7bcb | ||
|
|
5b3ce80a34 | ||
|
|
c3641de724 | ||
|
|
822dd4d555 | ||
|
|
09e88da71a | ||
|
|
31a2b26144 | ||
|
|
f7713a32aa | ||
|
|
c97a885f9e | ||
|
|
b1cc5c3564 | ||
|
|
91d8691bc4 | ||
|
|
072072e9b2 | ||
|
|
148bb63aa8 | ||
|
|
d60443751a | ||
|
|
1421f2c743 | ||
|
|
751ea27263 | ||
|
|
78b6020ea4 | ||
|
|
d08d22dec6 | ||
|
|
ee1f15eebe | ||
|
|
d755bca7c8 | ||
|
|
5565241ef5 | ||
|
|
a4cf2604ee | ||
|
|
3e860a5449 | ||
|
|
0305ceed45 | ||
|
|
4add8c871e | ||
|
|
6f566b5518 | ||
|
|
d6d71a0366 | ||
|
|
4c903cf7f2 | ||
|
|
b061f4fd84 | ||
|
|
2b73aea438 | ||
|
|
db958d9df8 | ||
|
|
f699f087db | ||
|
|
7d7e5f17a5 | ||
|
|
d486dd1083 | ||
|
|
5123085037 | ||
|
|
43041c26c5 | ||
|
|
ca2902cc46 | ||
|
|
2365ed47e1 | ||
|
|
78689590e6 | ||
|
|
d73187f3dd | ||
|
|
d1df96a953 | ||
|
|
c1650d3770 | ||
|
|
a72c5044f4 | ||
|
|
4e7f69a502 | ||
|
|
6d719fcd60 | ||
|
|
ac09b58620 | ||
|
|
b9cc02ecb9 | ||
|
|
00b00d2f9a | ||
|
|
5a9e85a60f | ||
|
|
fea77d86a7 | ||
|
|
11466ff261 | ||
|
|
80549933fc | ||
|
|
a428fac98d | ||
|
|
a109b264ef | ||
|
|
389b8968c2 | ||
|
|
b000d162e7 | ||
|
|
66e1672f37 | ||
|
|
52e7fe1d30 | ||
|
|
b61c5f23c6 | ||
|
|
0285bfa50a | ||
|
|
0069d6b289 | ||
|
|
ebba78528e | ||
|
|
da2bc575e0 | ||
|
|
25ea63042d | ||
|
|
24debfe377 | ||
|
|
414ee9166d | ||
|
|
edc4dd33b0 | ||
|
|
22b970e4d4 | ||
|
|
e367e307fb | ||
|
|
69ffca50d5 | ||
|
|
01fd82c43b | ||
|
|
f04bdb2491 | ||
|
|
aa6c673316 | ||
|
|
b2752ac6c6 | ||
|
|
7c038f1d45 | ||
|
|
b6547ba58e | ||
|
|
fde9cd4735 | ||
|
|
1d3e423617 | ||
|
|
9fc66563dd | ||
|
|
8a82f4a516 | ||
|
|
17d1934ed5 | ||
|
|
21fcf1bd04 | ||
|
|
ebd606ff00 | ||
|
|
f1241e4fe8 | ||
|
|
9de14b5c67 | ||
|
|
706c2d19b9 | ||
|
|
7a81c13543 | ||
|
|
4648276cc6 | ||
|
|
2c235dfce9 | ||
|
|
dacd8f5455 | ||
|
|
da261ff8cf | ||
|
|
a5ae72d7ae | ||
|
|
fd568e2419 | ||
|
|
7c7c3d83ef | ||
|
|
03dba9c7a2 | ||
|
|
1d0616640e | ||
|
|
f6437ab778 | ||
|
|
7ad22c73a8 | ||
|
|
54903b1cc0 | ||
|
|
e566ac9eb3 | ||
|
|
f95f81eaf3 | ||
|
|
f2ede43d0e | ||
|
|
f2ef9f817c | ||
|
|
7bba367f98 | ||
|
|
977892ad1f | ||
|
|
2ca696e064 | ||
|
|
3bb384d789 | ||
|
|
ac1fa2edca | ||
|
|
4ce9d76b65 | ||
|
|
1a1a2d27ce | ||
|
|
c9598ef732 | ||
|
|
4c01eb4a3d | ||
|
|
f9471184d7 | ||
|
|
bb0e4ec059 | ||
|
|
7f8b6d3c5e | ||
|
|
c6a756352a | ||
|
|
66456a893c | ||
|
|
8704a46e96 | ||
|
|
3de8ca609f | ||
|
|
586387ab3a | ||
|
|
37a988fd9f | ||
|
|
cb6045b026 | ||
|
|
9956d5dd82 | ||
|
|
b103ce4eb7 | ||
|
|
22df9a5252 | ||
|
|
b030d1dc9f | ||
|
|
387a759614 | ||
|
|
5dd8910e02 | ||
|
|
b19c812f58 | ||
|
|
e58939235f | ||
|
|
b8e1612511 | ||
|
|
a0abf2dee7 | ||
|
|
f5bced4510 | ||
|
|
a8d91b0ae5 | ||
|
|
307821ca25 | ||
|
|
c5d052ed16 | ||
|
|
e2f33faa67 | ||
|
|
1f6694ba50 | ||
|
|
01922f849e | ||
|
|
3fb6a7ba6e | ||
|
|
16b8102900 | ||
|
|
acb5dd0dd4 | ||
|
|
b325eebe00 | ||
|
|
eb0041d275 | ||
|
|
3ccd74d93e | ||
|
|
e0d06f9a64 | ||
|
|
d63e7b4677 | ||
|
|
0210f51944 | ||
|
|
073500bf75 | ||
|
|
60d33ca140 | ||
|
|
e65892c80d | ||
|
|
24320405b4 | ||
|
|
b5ea2cd1cb | ||
|
|
c26814da87 | ||
|
|
da8761bd96 | ||
|
|
b8a2fb50d4 | ||
|
|
310b566c9b | ||
|
|
43c31f933c | ||
|
|
3a54afe506 | ||
|
|
891b8523f0 | ||
|
|
bc12bd38b4 | ||
|
|
0cb66e5551 | ||
|
|
b81e92ca94 | ||
|
|
7ca5b01a75 | ||
|
|
44753536f3 | ||
|
|
d774c91d7b | ||
|
|
2abb76e167 | ||
|
|
75d4b9f20a | ||
|
|
056401a858 | ||
|
|
b678ac929e | ||
|
|
b7b19b0357 | ||
|
|
46ac1812d8 | ||
|
|
b21a478528 | ||
|
|
65f2bbba57 | ||
|
|
d0111bf41d | ||
|
|
31db574e63 | ||
|
|
c930dd06ec | ||
|
|
83dd92726e | ||
|
|
59f3e19d2d | ||
|
|
73ba5f039b | ||
|
|
e76dec7e15 | ||
|
|
8a67ca073a | ||
|
|
2b7cd6ab23 | ||
|
|
9b0568c5e7 | ||
|
|
48f6c8d3c1 | ||
|
|
2544d7293d | ||
|
|
c71d9458c8 | ||
|
|
c28c9abd5b | ||
|
|
c69ee8046a | ||
|
|
65894c9e39 | ||
|
|
55fd9fca1f | ||
|
|
f24e846272 | ||
|
|
d91113c9e7 | ||
|
|
94a9b73117 | ||
|
|
4ef027462f | ||
|
|
a788623ea3 | ||
|
|
94d3f3829b | ||
|
|
321e01157a | ||
|
|
97b2ba2d6a | ||
|
|
5ee8fcfea2 | ||
|
|
c9d4f2b82e | ||
|
|
aa003d0161 | ||
|
|
7decfc7d1e | ||
|
|
93c1b947fc | ||
|
|
66d1f4c67d | ||
|
|
70a13fbf1e | ||
|
|
1db8e12e1b | ||
|
|
8853321058 | ||
|
|
0a5e830159 | ||
|
|
fb041f9b6c | ||
|
|
28f83b18f9 | ||
|
|
cea854edf5 | ||
|
|
9a61b3c41b | ||
|
|
113d4b697a | ||
|
|
feb779bae9 | ||
|
|
521dc57b76 | ||
|
|
a0775544df | ||
|
|
14a0e299a1 | ||
|
|
1e783b623b | ||
|
|
c7a8654390 | ||
|
|
a7f8aee2c7 | ||
|
|
5ed03491f9 | ||
|
|
2260cdd3de | ||
|
|
377ca27cc9 | ||
|
|
5d979df2f9 | ||
|
|
9d5a477064 | ||
|
|
5006f8c2f7 | ||
|
|
8570ce68e2 | ||
|
|
3d3bbb4095 | ||
|
|
a1e3543897 | ||
|
|
4b82679b00 | ||
|
|
7fa7907219 | ||
|
|
60d5660286 | ||
|
|
5d4abe6e0d | ||
|
|
0405c74cf3 | ||
|
|
13fe6e0942 | ||
|
|
03c92f7652 | ||
|
|
084926ded3 | ||
|
|
382ed8e609 | ||
|
|
2ed2a793cd | ||
|
|
e0fb73f18a | ||
|
|
de896189b8 | ||
|
|
fbfd078795 | ||
|
|
e31aad242a | ||
|
|
93c5c39f8f | ||
|
|
810148550b | ||
|
|
172877a3cf | ||
|
|
a91fc1e4f3 | ||
|
|
f4fd595783 | ||
|
|
e690b92688 | ||
|
|
c8f771ec69 | ||
|
|
6b09e1d67c | ||
|
|
12195705f5 | ||
|
|
9f7871b4be | ||
|
|
44890dc712 | ||
|
|
57ae7467b9 | ||
|
|
1e5e25c54a | ||
|
|
ba7c4f4404 | ||
|
|
f3b52c08a7 | ||
|
|
1a36842407 | ||
|
|
a8b12914c8 | ||
|
|
d3db15fcd0 | ||
|
|
c40734fb8d | ||
|
|
55a9cef270 | ||
|
|
4b9b70fbb2 | ||
|
|
e61a1074ac | ||
|
|
e6c7f970f0 | ||
|
|
a023259445 | ||
|
|
b164ef1111 | ||
|
|
74d19dd069 | ||
|
|
185ae462a4 | ||
|
|
3676f07168 | ||
|
|
099258baa6 | ||
|
|
0bb3839d29 | ||
|
|
94b4c22594 | ||
|
|
b85035c45e | ||
|
|
687f8d9621 | ||
|
|
668f2f063f | ||
|
|
f93c712dca | ||
|
|
88f995803f | ||
|
|
c5ac30c303 | ||
|
|
0d72846b40 | ||
|
|
5d8da9633c | ||
|
|
325bd46740 |
@@ -0,0 +1,64 @@
|
||||
name: Notebook Check Pull Request
|
||||
|
||||
on:
|
||||
pull_request_target:
|
||||
types: [opened, reopened]
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
comment-welcome:
|
||||
permissions:
|
||||
contents: read
|
||||
pull-requests: write
|
||||
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Fetch pull request branch
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
repository: ${{ github.event.pull_request.head.repo.full_name }}
|
||||
ref: ${{ github.event.pull_request.head.sha }}
|
||||
- name: Fetch base develop branch
|
||||
run: git fetch -u "$GITHUB_SERVER_URL/$GITHUB_REPOSITORY" develop:develop
|
||||
- name: Create message
|
||||
env:
|
||||
HEAD_REPOSITORY: ${{ github.event.pull_request.head.repo.full_name }}
|
||||
HEAD_REF: ${{ github.event.pull_request.head.ref }}
|
||||
PR_NUM: ${{ github.event.pull_request.number }}
|
||||
run: |
|
||||
# Preview links and tool usage only needed for notebook changes.
|
||||
readarray -t changed_notebooks < <(git diff --name-only develop | grep '\.ipynb$' || true)
|
||||
if [[ ${#changed_notebooks[@]} == 0 ]]; then
|
||||
echo "No notebooks modified in this pull request."
|
||||
else
|
||||
msg="<h4>Preview</h4>\n"
|
||||
msg+="Preview and run these notebook edits with Google Colab:\n<ul>\n"
|
||||
# Link to PR branch in user's fork that is always current.
|
||||
for fp in "${changed_notebooks[@]}"; do
|
||||
gh_path="${HEAD_REPOSITORY}/blob/${HEAD_REF}/${fp}"
|
||||
colab_url="https://colab.research.google.com/github/${gh_path}"
|
||||
msg+="<li><a href='${colab_url}'>${fp}</a></li>\n"
|
||||
done
|
||||
msg+="</ul>\n"
|
||||
|
||||
reviewnb_url="https://app.reviewnb.com/${GITHUB_REPOSITORY}/pull/${PR_NUM}/files/"
|
||||
msg+="Rendered <a href='${reviewnb_url}'>notebook diffs</a> available on ReviewNB.com.\n"
|
||||
|
||||
msg+="If commits are added to the pull request, synchronize your local branch: <code>git pull origin $HEAD_REF</code>\n"
|
||||
fi
|
||||
echo "MESSAGE=$msg" >> $GITHUB_ENV
|
||||
- name: Post comment
|
||||
env:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
ISSUE_URL: ${{ github.event.pull_request.issue_url }}
|
||||
run: |
|
||||
# Env var defined in previous step. Escape string for JSON.
|
||||
body="$(echo -n -e $MESSAGE | python3 -c 'import json,sys; print(json.dumps(sys.stdin.read()))')"
|
||||
# Add comment to pull request.
|
||||
curl -X POST \
|
||||
-H "Accept: application/vnd.github.v3+json" \
|
||||
-H "Authorization: token $GITHUB_TOKEN" \
|
||||
"${ISSUE_URL}/comments" \
|
||||
--data "{\"body\": $body}"
|
||||
@@ -14,21 +14,8 @@ jobs:
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: '3.10'
|
||||
- name: 📦 Install mkdocs-material
|
||||
run: pip install "mkdocs-material[all]"
|
||||
- name: 📦 Install mkdocstrings[python]
|
||||
run: pip install "mkdocstrings[python]"
|
||||
- name: 📦 Install mkdocs-material[imaging]
|
||||
run: pip install "mkdocs-material[imaging]"
|
||||
- name: 📦 Install mike
|
||||
run: pip install "mike"
|
||||
- name: 📦 Install mkdocs-git-revision-date-localized-plugin
|
||||
run: pip install "mkdocs-git-revision-date-localized-plugin"
|
||||
- name: 📦 Install JupyterLab
|
||||
run: pip install jupyterlab
|
||||
- name: 📦 Install mkdocs-jupyter
|
||||
run: pip install mkdocs-jupyter
|
||||
- name: 📦 Install mkdocs-git-committers-plugin-2
|
||||
run: pip install mkdocs-git-committers-plugin-2
|
||||
- name: 🧪 Test documentation build
|
||||
run: mkdocs build --verbose
|
||||
- name: 🏗️ Install dependencies and Test Docs Build
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install "mkdocs-material" "mkdocstrings[python]" "mkdocs-material[imaging]" mike "mkdocs-git-revision-date-localized-plugin" jupyterlab mkdocs-jupyter mkdocs-git-committers-plugin-2
|
||||
mkdocs build --verbose
|
||||
|
||||
+1
-14
@@ -9,7 +9,6 @@ repos:
|
||||
- repo: https://github.com/pre-commit/pre-commit-hooks
|
||||
rev: v4.6.0
|
||||
hooks:
|
||||
- id: end-of-file-fixer
|
||||
- id: trailing-whitespace
|
||||
exclude: test/.*\.py
|
||||
- id: check-yaml
|
||||
@@ -19,14 +18,12 @@ repos:
|
||||
- id: check-case-conflict
|
||||
- id: check-added-large-files
|
||||
- id: detect-private-key
|
||||
- id: forbid-new-submodules
|
||||
- id: pretty-format-json
|
||||
exclude: demo.ipynb
|
||||
args: ['--autofix', '--no-sort-keys', '--indent=4']
|
||||
- id: end-of-file-fixer
|
||||
- id: mixed-line-ending
|
||||
|
||||
|
||||
- repo: https://github.com/PyCQA/bandit
|
||||
rev: '1.7.9'
|
||||
hooks:
|
||||
@@ -34,18 +31,8 @@ repos:
|
||||
args: ["-c", "pyproject.toml"]
|
||||
additional_dependencies: ["bandit[toml]"]
|
||||
|
||||
- repo: https://github.com/pycqa/isort
|
||||
rev: 5.13.2
|
||||
hooks:
|
||||
- id: isort
|
||||
name: isort (python)
|
||||
- id: isort
|
||||
name: isort (pyi)
|
||||
types: [pyi]
|
||||
|
||||
|
||||
- repo: https://github.com/astral-sh/ruff-pre-commit
|
||||
rev: v0.5.0
|
||||
rev: v0.6.3
|
||||
hooks:
|
||||
- id: ruff
|
||||
args: [--fix, --exit-non-zero-on-fix]
|
||||
|
||||
+122
-35
@@ -4,6 +4,25 @@ Thank you for your interest in contributing to Supervision!
|
||||
|
||||
We are actively improving this library to reduce the amount of work you need to do to solve common computer vision problems.
|
||||
|
||||
## Code of Conduct
|
||||
|
||||
Please read and adhere to our [Code of Conduct](CODE_OF_CONDUCT.md). This document outlines the expected behavior for all participants in our project.
|
||||
|
||||
## Table of Contents
|
||||
|
||||
- [Contribution Guidelines](#contribution-guidelines)
|
||||
- [Contributing Features](#contributing-features-)
|
||||
- [How to Contribute Changes](#how-to-contribute-changes)
|
||||
- [Installation for Contributors](#installation-for-contributors)
|
||||
- [Code Style and Quality](#-code-style-and-quality)
|
||||
- [Pre-commit tool](#pre-commit-tool)
|
||||
- [Docstrings](#docstrings)
|
||||
- [Type checking](#type-checking)
|
||||
- [Documentation](#-documentation)
|
||||
- [Cookbooks](#-cookbooks)
|
||||
- [Tests](#-tests)
|
||||
- [License](#-license)
|
||||
|
||||
## Contribution Guidelines
|
||||
|
||||
We welcome contributions to:
|
||||
@@ -32,49 +51,49 @@ First, fork this repository to your own GitHub account. Click "fork" in the top
|
||||
|
||||
Then, run `git clone` to download the project code to your computer.
|
||||
|
||||
You should also set up `roboflow/supervision` as an "upstream" remote (that is, tell git that the reference Supervision repository was the source of your fork of it):
|
||||
|
||||
```bash
|
||||
git remote add upstream https://github.com/roboflow/supervision.git
|
||||
git fetch upstream
|
||||
```
|
||||
|
||||
Move to a new branch using the `git checkout` command:
|
||||
|
||||
```bash
|
||||
git checkout -b <your_branch_name>
|
||||
git checkout -b <scope>/<your_branch_name> upstream/develop
|
||||
```
|
||||
|
||||
The name you choose for your branch should describe the change you want to make (i.e. `line-counter-docs`).
|
||||
The name you choose for your branch should describe the change you want to make and start with an appropriate prefix:
|
||||
|
||||
- `feat/`: for new features (e.g., `feat/line-counter`)
|
||||
- `fix/`: for bug fixes (e.g., `fix/memory-leak`)
|
||||
- `docs/`: for documentation changes (e.g., `docs/update-readme`)
|
||||
- `chore/`: for routine tasks, maintenance, or tooling changes (e.g., `chore/update-dependencies`)
|
||||
- `test/`: for adding or modifying tests (e.g., `test/add-unit-tests`)
|
||||
- `refactor/`: for code refactoring (e.g., `refactor/simplify-algorithm`)
|
||||
|
||||
Make any changes you want to the project code, then run the following commands to commit your changes:
|
||||
|
||||
```bash
|
||||
git add .
|
||||
git commit -m "Your commit message"
|
||||
git push -u origin main
|
||||
git add -A
|
||||
git commit -m "feat: add line counter functionality"
|
||||
git push -u origin <your_branch_name>
|
||||
```
|
||||
|
||||
## 🎨 Code quality
|
||||
Use conventional commit messages to clearly describe your changes. The format is:
|
||||
|
||||
### Pre-commit tool
|
||||
<type>[optional scope]: <description>
|
||||
|
||||
This project uses the [pre-commit](https://pre-commit.com/) tool to maintain code quality and consistency. Before submitting a pull request or making any commits, it is important to run the pre-commit tool to ensure that your changes meet the project's guidelines.
|
||||
|
||||
Furthermore, we have integrated a pre-commit GitHub Action into our workflow. This means that with every pull request opened, the pre-commit checks will be automatically enforced, streamlining the code review process and ensuring that all contributions adhere to our quality standards.
|
||||
|
||||
To run the pre-commit tool, follow these steps:
|
||||
|
||||
1. Install pre-commit by running the following command: `poetry install`. It will not only install pre-commit but also install all the deps and dev-deps of project
|
||||
|
||||
2. Once pre-commit is installed, navigate to the project's root directory.
|
||||
|
||||
3. Run the command `pre-commit run --all-files`. This will execute the pre-commit hooks configured for this project against the modified files. If any issues are found, the pre-commit tool will provide feedback on how to resolve them. Make the necessary changes and re-run the pre-commit command until all issues are resolved.
|
||||
|
||||
4. You can also install pre-commit as a git hook by executing `pre-commit install`. Every time you do a `git commit` pre-commit run automatically for you.
|
||||
|
||||
### Docstrings
|
||||
|
||||
All new functions and classes in `supervision` should include docstrings. This is a prerequisite for any new functions and classes to be added to the library.
|
||||
|
||||
`supervision` adheres to the [Google Python docstring style](https://google.github.io/styleguide/pyguide.html#383-functions-and-methods). Please refer to the style guide while writing docstrings for your contribution.
|
||||
|
||||
### Type checking
|
||||
|
||||
So far, **there is no type checking with mypy**. See [issue](https://github.com/roboflow-ai/template-python/issues/4).
|
||||
Common types include:
|
||||
- feat: A new feature
|
||||
- fix: A bug fix
|
||||
- docs: Documentation only changes
|
||||
- style: Changes that do not affect the meaning of the code (white-space, formatting, etc)
|
||||
- refactor: A code change that neither fixes a bug nor adds a feature
|
||||
- perf: A code change that improves performance
|
||||
- test: Adding missing tests or correcting existing tests
|
||||
- chore: Changes to the build process or auxiliary tools and libraries
|
||||
|
||||
Then, go back to your fork of the `supervision` repository, click "Pull Requests", and click "New Pull Request".
|
||||
|
||||
@@ -104,7 +123,75 @@ All pull requests will be reviewed by the maintainers of the project. We will pr
|
||||
|
||||
PRs must pass all tests and linting requirements before they can be merged.
|
||||
|
||||
## 📝 documentation
|
||||
## Installation for Contributors
|
||||
|
||||
Before starting your work on the project, set up your development environment:
|
||||
|
||||
1. Clone your fork of the project:
|
||||
```bash
|
||||
git clone https://github.com/YOUR_USERNAME/supervision.git
|
||||
cd supervision
|
||||
```
|
||||
Replace `YOUR_USERNAME` with your GitHub username.
|
||||
|
||||
2. Create and activate a virtual environment:
|
||||
```bash
|
||||
python3 -m venv .venv
|
||||
source .venv/bin/activate
|
||||
```
|
||||
|
||||
3. Install Poetry:
|
||||
|
||||
Using pip:
|
||||
```bash
|
||||
pip install -U pip setuptools
|
||||
pip install poetry
|
||||
```
|
||||
|
||||
Or using pipx (recommended for global installation):
|
||||
```bash
|
||||
pipx install poetry
|
||||
```
|
||||
|
||||
4. Install project dependencies:
|
||||
```bash
|
||||
poetry install
|
||||
```
|
||||
|
||||
5. Run pytest to verify the setup:
|
||||
```bash
|
||||
poetry run pytest
|
||||
```
|
||||
|
||||
## 🎨 Code Style and Quality
|
||||
|
||||
### Pre-commit tool
|
||||
|
||||
This project uses the [pre-commit](https://pre-commit.com/) tool to maintain code quality and consistency. Before submitting a pull request or making any commits, it is important to run the pre-commit tool to ensure that your changes meet the project's guidelines.
|
||||
|
||||
Furthermore, we have integrated a pre-commit GitHub Action into our workflow. This means that with every pull request opened, the pre-commit checks will be automatically enforced, streamlining the code review process and ensuring that all contributions adhere to our quality standards.
|
||||
|
||||
To run the pre-commit tool, follow these steps:
|
||||
|
||||
1. Install pre-commit by running the following command: `poetry install --with dev`. It will not only install pre-commit but also install all the deps and dev-deps of project
|
||||
|
||||
2. Once pre-commit is installed, navigate to the project's root directory.
|
||||
|
||||
3. Run the command `pre-commit run --all-files`. This will execute the pre-commit hooks configured for this project against the modified files. If any issues are found, the pre-commit tool will provide feedback on how to resolve them. Make the necessary changes and re-run the pre-commit command until all issues are resolved.
|
||||
|
||||
4. You can also install pre-commit as a git hook by executing `pre-commit install`. Every time you do a `git commit` pre-commit run automatically for you.
|
||||
|
||||
### Docstrings
|
||||
|
||||
All new functions and classes in `supervision` should include docstrings. This is a prerequisite for any new functions and classes to be added to the library.
|
||||
|
||||
`supervision` adheres to the [Google Python docstring style](https://google.github.io/styleguide/pyguide.html#383-functions-and-methods). Please refer to the style guide while writing docstrings for your contribution.
|
||||
|
||||
### Type checking
|
||||
|
||||
So far, **there is no type checking with mypy**. See [issue](https://github.com/roboflow-ai/template-python/issues/4).
|
||||
|
||||
## 📝 Documentation
|
||||
|
||||
The `supervision` documentation is stored in a folder called `docs`. The project documentation is built using `mkdocs`.
|
||||
|
||||
@@ -112,13 +199,13 @@ To run the documentation, install the project requirements with `poetry install
|
||||
|
||||
You can learn more about mkdocs on the [mkdocs website](https://www.mkdocs.org/).
|
||||
|
||||
## 🧑🍳 cookbooks
|
||||
## 🧑🍳 Cookbooks
|
||||
|
||||
We are always looking for new examples and cookbooks to add to the `supervision`
|
||||
documentation. If you have a use case that you think would be helpful to others, please
|
||||
submit a PR with your example. Here are some guidelines for submitting a new example:
|
||||
|
||||
- Create a new notebook in the [`docs/nodebooks`](https://github.com/roboflow/supervision/tree/develop/docs/notebooks) folder.
|
||||
- Create a new notebook in the [`docs/notebooks`](https://github.com/roboflow/supervision/tree/develop/docs/notebooks) folder.
|
||||
- Add a link to the new notebook in [`docs/theme/cookbooks.html`](https://github.com/roboflow/supervision/blob/develop/docs/theme/cookbooks.html). Make sure to add the path to the new notebook, as well as a title, labels, author and supervision version.
|
||||
- Use the [Count Objects Crossing the Line](https://supervision.roboflow.com/develop/notebooks/count-objects-crossing-the-line/) example as a template for your new example.
|
||||
- Freeze the version of `supervision` you are using.
|
||||
@@ -126,10 +213,10 @@ submit a PR with your example. Here are some guidelines for submitting a new exa
|
||||
- Notebook should be self-contained. If you rely on external data ( videos, images, etc.) or libraries, include download and installation commands in the notebook.
|
||||
- Annotate the code with appropriate comments, including links to the documentation describing each of the tools you have used.
|
||||
|
||||
## 🧪 tests
|
||||
## 🧪 Tests
|
||||
|
||||
[`pytests`](https://docs.pytest.org/en/7.1.x/) is used to run our tests.
|
||||
|
||||
## 📄 license
|
||||
## 📄 License
|
||||
|
||||
By contributing, you agree that your contributions will be licensed under an [MIT license](https://github.com/roboflow/supervision/blob/develop/LICENSE.md).
|
||||
|
||||
@@ -16,6 +16,7 @@
|
||||
|
||||
[](https://badge.fury.io/py/supervision)
|
||||
[](https://pypistats.org/packages/supervision)
|
||||
[](https://snyk.io/advisor/python/supervision)
|
||||
[](https://github.com/roboflow/supervision/blob/main/LICENSE.md)
|
||||
[](https://badge.fury.io/py/supervision)
|
||||
[](https://colab.research.google.com/github/roboflow/supervision/blob/main/demo.ipynb)
|
||||
@@ -95,8 +96,8 @@ import supervision as sv
|
||||
image = cv2.imread(...)
|
||||
detections = sv.Detections(...)
|
||||
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator()
|
||||
annotated_frame = bounding_box_annotator.annotate(
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
annotated_frame = box_annotator.annotate(
|
||||
scene=image.copy(),
|
||||
detections=detections
|
||||
)
|
||||
@@ -110,18 +111,21 @@ Supervision provides a set of [utils](https://supervision.roboflow.com/latest/da
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
from roboflow import Roboflow
|
||||
|
||||
dataset = sv.DetectionDataset.from_yolo(
|
||||
images_directory_path=...,
|
||||
annotations_directory_path=...,
|
||||
data_yaml_path=...
|
||||
project = Roboflow().workspace(<WORKSPACE_ID>).project(<PROJECT_ID>)
|
||||
dataset = project.version(<PROJECT_VERSION>).download("coco")
|
||||
|
||||
ds = sv.DetectionDataset.from_coco(
|
||||
images_directory_path=f"{dataset.location}/train",
|
||||
annotations_path=f"{dataset.location}/train/_annotations.coco.json",
|
||||
)
|
||||
|
||||
dataset.classes
|
||||
['dog', 'person']
|
||||
path, image, annotation = ds[0]
|
||||
# loads image on demand
|
||||
|
||||
len(dataset)
|
||||
# 1000
|
||||
for path, image, annotation in ds:
|
||||
# loads image on demand
|
||||
```
|
||||
|
||||
<details close>
|
||||
@@ -216,7 +220,7 @@ len(dataset)
|
||||
|
||||
## 🎬 tutorials
|
||||
|
||||
Want to learn how to use Supervision? Explore our [how-to guides](https://supervision.roboflow.com/develop/how_to/detect_and_annotate/), [end-to-end examples](https://github.com/roboflow/supervision/tree/develop/examples), and [cookbooks](https://supervision.roboflow.com/develop/cookbooks/)!
|
||||
Want to learn how to use Supervision? Explore our [how-to guides](https://supervision.roboflow.com/develop/how_to/detect_and_annotate/), [end-to-end examples](https://github.com/roboflow/supervision/tree/develop/examples), [cheatsheet](https://roboflow.github.io/cheatsheet-supervision/), and [cookbooks](https://supervision.roboflow.com/develop/cookbooks/)!
|
||||
|
||||
<br/>
|
||||
|
||||
@@ -291,7 +295,7 @@ We love your input! Please see our [contributing guide](https://github.com/robof
|
||||
/>
|
||||
</a>
|
||||
<img src="https://raw.githubusercontent.com/ultralytics/assets/main/social/logo-transparent.png" width="3%"/>
|
||||
<a href="https://disuss.roboflow.com">
|
||||
<a href="https://discuss.roboflow.com">
|
||||
<img
|
||||
src="https://media.roboflow.com/notebooks/template/icons/purple/forum.png?ik-sdk-version=javascript-1.4.3&updatedAt=1672949633584"
|
||||
width="3%"
|
||||
|
||||
Vendored
+1478
-1342
File diff suppressed because one or more lines are too long
+287
-10
@@ -1,8 +1,290 @@
|
||||
### 0.23.0 <small>Aug 28, 2024</small>
|
||||
|
||||
- Added [#930](https://github.com/roboflow/supervision/pull/930): `IconAnnotator`, a [new annotator](https://supervision.roboflow.com/latest/detection/annotators/#supervision.annotators.core.IconAnnotator) that allows drawing icons on each detection. Useful if you want to draw a specific icon for each class.
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
from inference import get_model
|
||||
|
||||
image = <SOURCE_IMAGE_PATH>
|
||||
icon_dog = <DOG_PNG_PATH>
|
||||
icon_cat = <CAT_PNG_PATH>
|
||||
|
||||
model = get_model(model_id="yolov8n-640")
|
||||
results = model.infer(image)[0]
|
||||
detections = sv.Detections.from_inference(results)
|
||||
|
||||
icon_paths = []
|
||||
for class_name in detections.data["class_name"]:
|
||||
if class_name == "dog":
|
||||
icon_paths.append(icon_dog)
|
||||
elif class_name == "cat":
|
||||
icon_paths.append(icon_cat)
|
||||
else:
|
||||
icon_paths.append("")
|
||||
|
||||
icon_annotator = sv.IconAnnotator()
|
||||
annotated_frame = icon_annotator.annotate(
|
||||
scene=image.copy(),
|
||||
detections=detections,
|
||||
icon_path=icon_paths
|
||||
)
|
||||
```
|
||||
|
||||
- Added [#1385](https://github.com/roboflow/supervision/pull/1385): [`BackgroundColorAnnotator`](https://supervision.roboflow.com/latest/detection/annotators/#supervision.annotators.core.BackgroundColorAnnotator), that draws an overlay on the background images of the detections.
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
from inference import get_model
|
||||
|
||||
image = <SOURCE_IMAGE_PATH>
|
||||
|
||||
model = get_model(model_id="yolov8n-640")
|
||||
results = model.infer(image)[0]
|
||||
detections = sv.Detections.from_inference(results)
|
||||
|
||||
background_overlay_annotator = sv.BackgroundOverlayAnnotator()
|
||||
annotated_frame = background_overlay_annotator.annotate(
|
||||
scene=image.copy(),
|
||||
detections=detections
|
||||
)
|
||||
```
|
||||
|
||||
- Added [#1386](https://github.com/roboflow/supervision/pull/1386): Support for Transformers v5 functions in [`sv.Detections.from_transformers`](https://supervision.roboflow.com/latest/detection/core/#supervision.detection.core.Detections.from_transformers). This includes the `DetrImageProcessor` methods `post_process_object_detection`, `post_process_panoptic_segmentation`, `post_process_semantic_segmentation`, and `post_process_instance_segmentation`.
|
||||
|
||||
```python
|
||||
import torch
|
||||
import supervision as sv
|
||||
from PIL import Image
|
||||
from transformers import DetrImageProcessor, DetrForObjectDetection
|
||||
|
||||
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
|
||||
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
|
||||
|
||||
image = Image.open(<SOURCE_IMAGE_PATH>)
|
||||
inputs = processor(images=image, return_tensors="pt")
|
||||
|
||||
with torch.no_grad():
|
||||
outputs = model(**inputs)
|
||||
|
||||
width, height = image.size
|
||||
target_size = torch.tensor([[height, width]])
|
||||
results = processor.post_process_object_detection(
|
||||
outputs=outputs, target_sizes=target_size)[0]
|
||||
detections = sv.Detections.from_transformers(
|
||||
transformers_results=results,
|
||||
id2label=model.config.id2label)
|
||||
```
|
||||
|
||||
- Added [#1354](https://github.com/roboflow/supervision/pull/1354): Ultralytics SAM (Segment Anything Model) support in [`sv.Detections.from_ultralytics`](https://supervision.roboflow.com/latest/detection/core/#supervision.detection.core.Detections.from_ultralytics). [SAM2](https://sam2.metademolab.com/) was released during this update, and is already supported via [`sv.Detections.from_sam`](https://supervision.roboflow.com/latest/detection/core/#supervision.detection.core.Detections.from_sam).
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
from segment_anything import (
|
||||
sam_model_registry,
|
||||
SamAutomaticMaskGenerator
|
||||
)
|
||||
|
||||
sam_model_reg = sam_model_registry[MODEL_TYPE]
|
||||
sam = sam_model_reg(checkpoint=CHECKPOINT_PATH).to(device=DEVICE)
|
||||
mask_generator = SamAutomaticMaskGenerator(sam)
|
||||
sam_result = mask_generator.generate(IMAGE)
|
||||
detections = sv.Detections.from_sam(sam_result=sam_result)
|
||||
```
|
||||
|
||||
- Added [#1458](https://github.com/roboflow/supervision/pull/1458): `outline_color` options for [`TriangleAnnotator`](https://supervision.roboflow.com/latest/detection/annotators/#supervision.annotators.core.TriangleAnnotator) and [`DotAnnotator`](https://supervision.roboflow.com/latest/detection/annotators/#supervision.annotators.core.DotAnnotator).
|
||||
|
||||
- Added [#1409](https://github.com/roboflow/supervision/pull/1409): `text_color` option for [`VertexLabelAnnotator`](https://supervision.roboflow.com/latest/keypoint/annotators/#supervision.keypoint.annotators.VertexLabelAnnotator) keypoint annotator.
|
||||
|
||||
- Changed [#1434](https://github.com/roboflow/supervision/pull/1434): [`InferenceSlicer`](https://supervision.roboflow.com/latest/detection/tools/inference_slicer/) now features an `overlap_ratio_wh` parameter, making it easier to compute slice sizes when handling overlapping slices.
|
||||
|
||||
- Fix [#1448](https://github.com/roboflow/supervision/pull/1448): Various annotator type issues have been resolved, supporting expanded error handling.
|
||||
|
||||
- Fix [#1348](https://github.com/roboflow/supervision/pull/1348): Introduced a new method for [seeking to a specific video frame](https://supervision.roboflow.com/latest/utils/video/#supervision.utils.video.get_video_frames_generator), addressing cases where traditional seek methods were failing. It can be enabled with `iterative_seek=True`.
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
for frame in sv.get_video_frames_generator(
|
||||
source_path=<SOURCE_VIDEO_PATH>,
|
||||
start=60,
|
||||
iterative_seek=True
|
||||
):
|
||||
...
|
||||
```
|
||||
|
||||
- Fix [#1424](https://github.com/roboflow/supervision/pull/1424): `plot_image` function now clearly indicates that the size is in inches.
|
||||
|
||||
!!! failure "Removed"
|
||||
|
||||
The `track_buffer`, `track_thresh`, and `match_thresh` parameters in [`ByteTrack`](trackers.md/#supervision.tracker.byte_tracker.core.ByteTrack) are deprecated and were removed as of `supervision-0.23.0`. Use `lost_track_buffer,` `track_activation_threshold`, and `minimum_matching_threshold` instead.
|
||||
|
||||
!!! failure "Removed"
|
||||
|
||||
The `triggering_position ` parameter in [`sv.PolygonZone`](detection/tools/polygon_zone.md/#supervision.detection.tools.polygon_zone.PolygonZone) was removed as of `supervision-0.23.0`. Use `triggering_anchors ` instead.
|
||||
|
||||
!!! failure "Deprecated"
|
||||
|
||||
`overlap_filter_strategy` in `InferenceSlicer.__init__` is deprecated and will be removed in `supervision-0.27.0`. Use `overlap_strategy` instead.
|
||||
|
||||
!!! failure "Deprecated"
|
||||
|
||||
`overlap_ratio_wh` in `InferenceSlicer.__init__` is deprecated and will be removed in `supervision-0.27.0`. Use `overlap_wh` instead.
|
||||
|
||||
### 0.22.0 <small>Jul 12, 2024</small>
|
||||
|
||||
- Added [#1326](https://github.com/roboflow/supervision/pull/1326): [`sv.DetectionsDataset`](https://supervision.roboflow.com/latest/datasets/core/#supervision.dataset.core.DetectionDataset) and [`sv.ClassificationDataset`](https://supervision.roboflow.com/latest/datasets/core/#supervision.dataset.core.ClassificationDataset) allowing to load the images into memory only when necessary (lazy loading).
|
||||
|
||||
!!! failure "Deprecated"
|
||||
|
||||
Constructing `DetectionDataset` with parameter `images` as `Dict[str, np.ndarray]` is deprecated and will be removed in `supervision-0.26.0`. Please pass a list of paths `List[str]` instead.
|
||||
|
||||
!!! failure "Deprecated"
|
||||
|
||||
The `DetectionDataset.images` property is deprecated and will be removed in `supervision-0.26.0`. Please loop over images with `for path, image, annotation in dataset:`, as that does not require loading all images into memory.
|
||||
|
||||
```python
|
||||
import roboflow
|
||||
from roboflow import Roboflow
|
||||
import supervision as sv
|
||||
|
||||
roboflow.login()
|
||||
rf = Roboflow()
|
||||
|
||||
project = rf.workspace(<WORKSPACE_ID>).project(<PROJECT_ID>)
|
||||
dataset = project.version(<PROJECT_VERSION>).download("coco")
|
||||
|
||||
ds_train = sv.DetectionDataset.from_coco(
|
||||
images_directory_path=f"{dataset.location}/train",
|
||||
annotations_path=f"{dataset.location}/train/_annotations.coco.json",
|
||||
)
|
||||
|
||||
path, image, annotation = ds_train[0]
|
||||
# loads image on demand
|
||||
|
||||
for path, image, annotation in ds_train:
|
||||
# loads image on demand
|
||||
```
|
||||
|
||||
- Added [#1296](https://github.com/roboflow/supervision/pull/1296): [`sv.Detections.from_lmm`](https://supervision.roboflow.com/latest/detection/core/#supervision.detection.core.Detections.from_lmm) now supports parsing results from the [Florence 2](https://huggingface.co/microsoft/Florence-2-large) model, extending the capability to handle outputs from this Large Multimodal Model (LMM). This includes detailed object detection, OCR with region proposals, segmentation, and more. Find out more in our [Colab notebook](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-finetune-florence-2-on-detection-dataset.ipynb).
|
||||
|
||||
- Added [#1232](https://github.com/roboflow/supervision/pull/1232) to support keypoint detection with Mediapipe. Both [legacy](https://colab.research.google.com/github/googlesamples/mediapipe/blob/main/examples/pose_landmarker/python/%5BMediaPipe_Python_Tasks%5D_Pose_Landmarker.ipynb) and [modern](https://ai.google.dev/edge/mediapipe/solutions/vision/pose_landmarker/python) pipelines are supported. See [`sv.KeyPoints.from_mediapipe`](https://supervision.roboflow.com/latest/keypoint/core/#supervision.keypoint.core.KeyPoints.from_mediapipe) for more.
|
||||
|
||||
- Added [#1316](https://github.com/roboflow/supervision/pull/1316): [`sv.KeyPoints.from_mediapipe`](https://supervision.roboflow.com/latest/keypoint/core/#supervision.keypoint.core.KeyPoints.from_mediapipe) extended to support FaceMesh from Mediapipe. This enhancement allows for processing both face landmarks from `FaceLandmarker`, and legacy results from `FaceMesh`.
|
||||
|
||||
- Added [#1310](https://github.com/roboflow/supervision/pull/1310): [`sv.KeyPoints.from_detectron2`](https://supervision.roboflow.com/latest/keypoint/core/#supervision.keypoint.core.KeyPoints.from_detectron2) is a new `KeyPoints` method, adding support for extracting keypoints from the popular [Detectron 2](https://github.com/facebookresearch/detectron2) platform.
|
||||
|
||||
- Added [#1300](https://github.com/roboflow/supervision/pull/1300): [`sv.Detections.from_detectron2`](https://supervision.roboflow.com/latest/detection/core/#supervision.detection.core.Detections.from_detectron2) now supports segmentation models detectron2. The resulting masks can be used with [`sv.MaskAnnotator`](https://supervision.roboflow.com/latest/annotators/#supervision.annotators.core.MaskAnnotator) for displaying annotations.
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
from detectron2 import model_zoo
|
||||
from detectron2.engine import DefaultPredictor
|
||||
from detectron2.config import get_cfg
|
||||
import cv2
|
||||
|
||||
image = cv2.imread(<SOURCE_IMAGE_PATH>)
|
||||
cfg = get_cfg()
|
||||
cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"))
|
||||
cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")
|
||||
predictor = DefaultPredictor(cfg)
|
||||
|
||||
result = predictor(image)
|
||||
detections = sv.Detections.from_detectron2(result)
|
||||
|
||||
mask_annotator = sv.MaskAnnotator()
|
||||
annotated_frame = mask_annotator.annotate(scene=image.copy(), detections=detections)
|
||||
```
|
||||
|
||||
- Added [#1277](https://github.com/roboflow/supervision/pull/1277): if you provide a font that supports symbols of a language, [`sv.RichLabelAnnotator`](https://supervision.roboflow.com/latest/detection/annotators/#supervision.annotators.core.LabelAnnotator.annotate) will draw them on your images.
|
||||
- Various other annotators have been revised to ensure proper in-place functionality when used with `numpy` arrays. Additionally, we fixed a bug where `sv.ColorAnnotator` was filling boxes with solid color when used in-place.
|
||||
|
||||
```python
|
||||
import cv2
|
||||
import supervision as sv
|
||||
import
|
||||
|
||||
image = cv2.imread(<SOURCE_IMAGE_PATH>)
|
||||
|
||||
model = get_model(model_id="yolov8n-640")
|
||||
results = model.infer(image)[0]
|
||||
detections = sv.Detections.from_inference(results)
|
||||
|
||||
rich_label_annotator = sv.RichLabelAnnotator(font_path=<TTF_FONT_PATH>)
|
||||
annotated_image = rich_label_annotator.annotate(scene=image.copy(), detections=detections)
|
||||
```
|
||||
|
||||
- Added [#1227](https://github.com/roboflow/supervision/pull/1227): Added support for loading Oriented Bounding Boxes dataset in YOLO format.
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
train_ds = sv.DetectionDataset.from_yolo(
|
||||
images_directory_path="/content/dataset/train/images",
|
||||
annotations_directory_path="/content/dataset/train/labels",
|
||||
data_yaml_path="/content/dataset/data.yaml",
|
||||
is_obb=True
|
||||
)
|
||||
|
||||
_, image, detections in train_ds[0]
|
||||
|
||||
obb_annotator = OrientedBoxAnnotator()
|
||||
annotated_image = obb_annotator.annotate(scene=image.copy(), detections=detections)
|
||||
```
|
||||
|
||||
- Fixed [#1312](https://github.com/roboflow/supervision/pull/1312): Fixed [`CropAnnotator`](https://supervision.roboflow.com/latest/detection/annotators/#supervision.annotators.core.TraceAnnotator.annotate).
|
||||
|
||||
!!! failure "Removed"
|
||||
|
||||
`BoxAnnotator` was removed, however `BoundingBoxAnnotator` has been renamed to `BoxAnnotator`. Use a combination of [`BoxAnnotator`](https://supervision.roboflow.com/latest/detection/annotators/#supervision.annotators.core.BoxAnnotator) and [`LabelAnnotator`](https://supervision.roboflow.com/latest/detection/annotators/#supervision.annotators.core.LabelAnnotator) to simulate old `BoundingBox` behavior.
|
||||
|
||||
!!! failure "Deprecated"
|
||||
|
||||
The name `BoundingBoxAnnotator` has been deprecated and will be removed in `supervision-0.26.0`. It has been renamed to [`BoxAnnotator`](https://supervision.roboflow.com/latest/detection/annotators/#supervision.annotators.core.BoxAnnotator).
|
||||
|
||||
- Added [#975](https://github.com/roboflow/supervision/pull/975) 📝 New Cookbooks: serialize detections into [json](https://github.com/roboflow/supervision/blob/de896189b83a1f9434c0a37dd9192ee00d2a1283/docs/notebooks/serialise-detections-to-json.ipynb) and [csv](https://github.com/roboflow/supervision/blob/de896189b83a1f9434c0a37dd9192ee00d2a1283/docs/notebooks/serialise-detections-to-csv.ipynb).
|
||||
|
||||
- Added [#1290](https://github.com/roboflow/supervision/pull/1290): Mostly an internal change, our file utility function now support both `str` and `pathlib` paths.
|
||||
|
||||
- Added [#1340](https://github.com/roboflow/supervision/pull/1340): Two new methods for converting between bounding box formats - [`xywh_to_xyxy`](https://supervision.roboflow.com/latest/detection/utils/#supervision.detection.utils.xywh_to_xyxy) and [`xcycwh_to_xyxy`](https://supervision.roboflow.com/latest/detection/utils/#supervision.detection.utils.xcycwh_to_xyxy)
|
||||
|
||||
!!! failure "Removed"
|
||||
|
||||
`from_roboflow` method has been removed due to deprecation. Use [from_inference](https://supervision.roboflow.com/latest/detection/core/#supervision.detection.core.Detections.from_inference) instead.
|
||||
|
||||
!!! failure "Removed"
|
||||
|
||||
`Color.white()` has been removed due to deprecation. Use `color.WHITE` instead.
|
||||
|
||||
!!! failure "Removed"
|
||||
|
||||
`Color.black()` has been removed due to deprecation. Use `color.BLACK` instead.
|
||||
|
||||
!!! failure "Removed"
|
||||
|
||||
`Color.red()` has been removed due to deprecation. Use `color.RED` instead.
|
||||
|
||||
!!! failure "Removed"
|
||||
|
||||
`Color.green()` has been removed due to deprecation. Use `color.GREEN` instead.
|
||||
|
||||
!!! failure "Removed"
|
||||
|
||||
`Color.blue()` has been removed due to deprecation. Use `color.BLUE` instead.
|
||||
|
||||
!!! failure "Removed"
|
||||
|
||||
`ColorPalette.default()` has been removed due to deprecation. Use [ColorPalette.DEFAULT](https://supervision.roboflow.com/latest/utils/draw/#supervision.draw.color.ColorPalette.DEFAULT) instead.
|
||||
|
||||
!!! failure "Removed"
|
||||
|
||||
`FPSMonitor.__call__` has been removed due to deprecation. Use the attribute [FPSMonitor.fps](https://supervision.roboflow.com/latest/utils/video/#supervision.utils.video.FPSMonitor.fps) instead.
|
||||
|
||||
### 0.21.0 <small>Jun 5, 2024</small>
|
||||
|
||||
- Added [#500](https://github.com/roboflow/supervision/pull/500): [`sv.Detections.with_nmm`](https://supervision.roboflow.com/develop/detection/core/#supervision.detection.core.Detections.with_nmm) to perform non-maximum merging on the current set of object detections.
|
||||
- Added [#500](https://github.com/roboflow/supervision/pull/500): [`sv.Detections.with_nmm`](https://supervision.roboflow.com/latest/detection/core/#supervision.detection.core.Detections.with_nmm) to perform non-maximum merging on the current set of object detections.
|
||||
|
||||
- Added [#1221](https://github.com/roboflow/supervision/pull/1221): [`sv.Detections.from_lmm`](https://supervision.roboflow.com/develop/detection/core/#supervision.detection.core.Detections.from_lmm) allowing to parse Large Multimodal Model (LMM) text result into [`sv.Detections`](https://supervision.roboflow.com/develop/detection/core/) object. For now `from_lmm` supports only [PaliGemma](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-finetune-paligemma-on-detection-dataset.ipynb) result parsing.
|
||||
- Added [#1221](https://github.com/roboflow/supervision/pull/1221): [`sv.Detections.from_lmm`](https://supervision.roboflow.com/latest/detection/core/#supervision.detection.core.Detections.from_lmm) allowing to parse Large Multimodal Model (LMM) text result into [`sv.Detections`](https://supervision.roboflow.com/latest/detection/core/) object. For now `from_lmm` supports only [PaliGemma](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-finetune-paligemma-on-detection-dataset.ipynb) result parsing.
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
@@ -21,7 +303,7 @@ detections.class_id
|
||||
# array([0])
|
||||
```
|
||||
|
||||
- Added [#1236](https://github.com/roboflow/supervision/pull/1236): [`sv.VertexLabelAnnotator`](https://supervision.roboflow.com/develop/keypoint/annotators/#supervision.keypoint.annotators.EdgeAnnotator.annotate) allowing to annotate every vertex of a keypoint skeleton with custom text and color.
|
||||
- Added [#1236](https://github.com/roboflow/supervision/pull/1236): [`sv.VertexLabelAnnotator`](https://supervision.roboflow.com/latest/keypoint/annotators/#supervision.keypoint.annotators.EdgeAnnotator.annotate) allowing to annotate every vertex of a keypoint skeleton with custom text and color.
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
@@ -164,8 +446,6 @@ with csv_sink:
|
||||
|
||||
- Added [#819](https://github.com/roboflow/supervision/pull/819): [`sv.JSONSink`](/0.19.0/detection/tools/save_detections/#supervision.detection.tools.csv_sink.JSONSink) allowing for the straightforward saving of image, video, or stream inference results in a `.json` file.
|
||||
|
||||
```python
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
from ultralytics import YOLO
|
||||
@@ -213,7 +493,7 @@ annotated_frame = crop_annotator.annotate(
|
||||
|
||||
!!! failure "Deprecated"
|
||||
|
||||
The `track_buffer`, `track_thresh`, and `match_thresh` parameters in `sv.ByterTrack` are deprecated and will be removed in `supervision-0.23.0`. Use `lost_track_buffer,` `track_activation_threshold`, and `minimum_matching_threshold` instead.
|
||||
The `track_buffer`, `track_thresh`, and `match_thresh` parameters in `sv.ByteTrack` are deprecated and will be removed in `supervision-0.23.0`. Use `lost_track_buffer,` `track_activation_threshold`, and `minimum_matching_threshold` instead.
|
||||
|
||||
- Changed [#910](https://github.com/roboflow/supervision/pull/910): [`sv.PolygonZone`](/0.19.0/detection/tools/polygon_zone/#supervision.detection.tools.polygon_zone.PolygonZone) to now accept a list of specific box anchors that must be in zone for a detection to be counted.
|
||||
|
||||
@@ -285,7 +565,6 @@ ColorPalette(colors=[Color(r=68, g=1, b=84), Color(r=59, g=82, b=139), ...])
|
||||
|
||||
`sv.ColorPalette.default()` is deprecated and will be removed in `supervision-0.22.0`. Use `sv.ColorPalette.DEFAULT` instead.
|
||||
|
||||
|
||||
- Changed [#769](https://github.com/roboflow/supervision/pull/769): [`sv.ColorPalette.DEFAULT`](/0.18.0/draw/color/#colorpalette) value, giving users a more extensive set of annotation colors.
|
||||
|
||||
- Changed [#677](https://github.com/roboflow/supervision/pull/677): `sv.Detections.from_roboflow` to [`sv.Detections.from_inference`](/0.18.0/detection/core/#supervision.detection.core.Detections.from_inference) streamlining its functionality to be compatible with both the both [inference](https://github.com/roboflow/inference) pip package and the Robloflow [hosted API](https://docs.roboflow.com/deploy/hosted-api).
|
||||
@@ -294,7 +573,6 @@ ColorPalette(colors=[Color(r=68, g=1, b=84), Color(r=59, g=82, b=139), ...])
|
||||
|
||||
`Detections.from_roboflow()` is deprecated and will be removed in `supervision-0.22.0`. Use `Detections.from_inference` instead.
|
||||
|
||||
|
||||
- Fixed [#735](https://github.com/roboflow/supervision/pull/735): [`sv.LineZone`](/0.18.0/detection/tools/line_zone/#linezone) functionality to accurately update the counter when an object crosses a line from any direction, including from the side. This enhancement enables more precise tracking and analytics, such as calculating individual in/out counts for each lane on the road.
|
||||
|
||||
### 0.17.0 <small>December 06, 2023</small>
|
||||
@@ -387,13 +665,12 @@ ColorPalette(colors=[Color(r=68, g=1, b=84), Color(r=59, g=82, b=139), ...])
|
||||
|
||||
- Fixed [#477](https://github.com/roboflow/supervision/pull/477): Poetry env definition allowing proper local installation.
|
||||
|
||||
- Fixed [#430](https://github.com/roboflow/supervision/pull/430): [`sv.ByteTrack`](/0.16.0/trackers/#supervision.tracker.byte_tracker.core.ByteTrack) to return `np.array([], dtype=int)` when `svDetections` is empty.
|
||||
- Fixed [#430](https://github.com/roboflow/supervision/pull/430): [`sv.ByteTrack`](/0.16.0/trackers/#supervision.tracker.byte_tracker.core.ByteTrack) to return `np.array([], dtype=int)` when `svDetections` is empty.
|
||||
|
||||
!!! failure "Deprecated"
|
||||
|
||||
`sv.Detections.from_yolov8` and `sv.Classifications.from_yolov8` as those are now replaced by [`sv.Detections.from_ultralytics`](/0.16.0/detection/core/#supervision.detection.core.Detections.from_ultralytics) and [`sv.Classifications.from_ultralytics`](/0.16.0/classification/core/#supervision.classification.core.Classifications.from_ultralytics).
|
||||
|
||||
|
||||
### 0.15.0 <small>October 5, 2023</small>
|
||||
|
||||
- Added [#170](https://github.com/roboflow/supervision/pull/170): [`sv.BoundingBoxAnnotator`](/0.15.0/annotators/#supervision.annotators.core.BoundingBoxAnnotator) allowing to annotate images and videos with bounding boxes.
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
---
|
||||
comments: true
|
||||
status: new
|
||||
---
|
||||
|
||||
# Datasets
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
---
|
||||
comments: true
|
||||
status: new
|
||||
---
|
||||
|
||||
# Datasets Utils
|
||||
|
||||
+30
-13
@@ -3,17 +3,34 @@ comments: true
|
||||
status: deprecated
|
||||
---
|
||||
|
||||
These features are phased out due to better alternatives or potential issues in future versions. Deprecated functionalities are supported for **three subsequent releases**, providing time for users to transition to updated methods.
|
||||
# Deprecated
|
||||
|
||||
- [`Detections.from_froboflow`](detection/core.md/#supervision.detection.core.Detections.from_roboflow) is deprecated and will be removed in `supervision-0.22.0`. Use [`Detections.from_inference`](detection/core.md/#supervision.detection.core.Detections.from_inference) instead.
|
||||
- The method `Color.white()` is deprecated and will be removed in `supervision-0.22.0`. Use the constant `Color.WHITE` instead.
|
||||
- The method `Color.black()` is deprecated and will be removed in `supervision-0.22.0`. Use the constant `Color.BLACK` instead.
|
||||
- The method `Color.red()` is deprecated and will be removed in `supervision-0.22.0`. Use the constant `Color.RED` instead.
|
||||
- The method `Color.green()` is deprecated and will be removed in `supervision-0.22.0`. Use the constant `Color.GREEN` instead.
|
||||
- The method `Color.blue()` is deprecated and will be removed in `supervision-0.22.0`. Use the constant `Color.BLUE` instead.
|
||||
- The method [`ColorPalette.default()`](draw/color.md/#supervision.draw.color.ColorPalette.default) is deprecated and will be removed in `supervision-0.22.0`. Use the constant [`ColorPalette.DEFAULT`](draw/color.md/#supervision.draw.color.ColorPalette.DEFAULT) instead.
|
||||
- `BoxAnnotator` is deprecated and will be removed in `supervision-0.22.0`. Use [`BoundingBoxAnnotator`](detection/annotators.md/#supervision.annotators.core.BoundingBoxAnnotator) and [`LabelAnnotator`](detection/annotators.md/#supervision.annotators.core.LabelAnnotator) instead.
|
||||
- The method [`FPSMonitor.__call__`](utils/video.md/#supervision.utils.video.FPSMonitor.__call__) is deprecated and will be removed in `supervision-0.22.0`. Use the attribute [`FPSMonitor.fps`](utils/video.md/#supervision.utils.video.FPSMonitor.fps) instead.
|
||||
- The `track_buffer`, `track_thresh`, and `match_thresh` parameters in [`ByterTrack`](trackers.md/#supervision.tracker.byte_tracker.core.ByteTrack) are deprecated and will be removed in `supervision-0.23.0`. Use `lost_track_buffer,` `track_activation_threshold`, and `minimum_matching_threshold` instead.
|
||||
- The `triggering_position ` parameter in [`sv.PolygonZone`](detection/tools/polygon_zone.md/#supervision.detection.tools.polygon_zone.PolygonZone) is deprecated and will be removed in `supervision-0.23.0`. Use `triggering_anchors ` instead.
|
||||
- The `frame_resolution_wh ` parameter in [`sv.PolygonZone`](detection/tools/polygon_zone.md/#supervision.detection.tools.polygon_zone.PolygonZone) is deprecated and will be removed in `supervision-0.24.0`.
|
||||
These features are phased out due to better alternatives or potential issues in future versions. Deprecated functionalities are supported for **five subsequent releases**, providing time for users to transition to updated methods.
|
||||
|
||||
- The `frame_resolution_wh ` parameter in [`sv.PolygonZone`](detection/tools/polygon_zone.md/#supervision.detection.tools.polygon_zone.PolygonZone) will be removed in `supervision-0.24.0`.
|
||||
|
||||
- Constructing [`DetectionDataset`](https://supervision.roboflow.com/latest/datasets/core/#supervision.dataset.core.DetectionDataset) and [`ClassificationDataset`](https://supervision.roboflow.com/latest/datasets/core/#supervision.dataset.core.ClassificationDataset) with parameter `images` as `Dict[str, np.ndarray]` will be removed in `supervision-0.26.0`. Please pass a list of paths `List[str]` instead.
|
||||
- The `DetectionDataset.images` property will be removed in `supervision-0.26.0`. Please loop over images with `for path, image, annotation in dataset:`, as that does not require loading all images into memory.
|
||||
- `BoundingBoxAnnotator` has been renamed to `BoxAnnotator` after the old implementation of [`BoxAnnotator`](https://supervision.roboflow.com/latest/detection/annotators/#supervision.annotators.core.BoxAnnotator) has been removed. `BoundingBoxAnnotator` will be removed in `supervision-0.26.0`.
|
||||
|
||||
- `overlap_filter_strategy` in [`InferenceSlicer.__init__`](https://supervision.roboflow.com/latest/detection/tools/inference_slicer/) is deprecated and will be removed in `supervision-0.27.0`. Use `overlap_strategy` instead.
|
||||
- `overlap_ratio_wh` in [`InferenceSlicer.__init__`](https://supervision.roboflow.com/latest/detection/tools/inference_slicer/) is deprecated and will be removed in `supervision-0.27.0`. Use `overlap_wh` instead.
|
||||
|
||||
# Removed
|
||||
|
||||
### 0.23.0
|
||||
|
||||
- The `track_buffer`, `track_thresh`, and `match_thresh` parameters in [`ByteTrack`](trackers.md/#supervision.tracker.byte_tracker.core.ByteTrack) are deprecated and were removed as of `supervision-0.23.0`. Use `lost_track_buffer,` `track_activation_threshold`, and `minimum_matching_threshold` instead.
|
||||
- The `triggering_position ` parameter in [`sv.PolygonZone`](detection/tools/polygon_zone.md/#supervision.detection.tools.polygon_zone.PolygonZone) was removed as of `supervision-0.23.0`. Use `triggering_anchors ` instead.
|
||||
|
||||
### 0.22.0
|
||||
|
||||
- [`Detections.from_froboflow`](detection/core.md/#supervision.detection.core.Detections.from_roboflow) is removed as of `supervision-0.22.0`. Use [`Detections.from_inference`](detection/core.md/#supervision.detection.core.Detections.from_inference) instead.
|
||||
- The method `Color.white()` was removed as of `supervision-0.22.0`. Use the constant `Color.WHITE` instead.
|
||||
- The method `Color.black()` was removed as of `supervision-0.22.0`. Use the constant `Color.BLACK` instead.
|
||||
- The method `Color.red()` was removed as of `supervision-0.22.0`. Use the constant `Color.RED` instead.
|
||||
- The method `Color.green()` was removed as of `supervision-0.22.0`. Use the constant `Color.GREEN` instead.
|
||||
- The method `Color.blue()` was removed as of `supervision-0.22.0`. Use the constant `Color.BLUE` instead.
|
||||
- The method [`ColorPalette.default()`](draw/color.md/#supervision.draw.color.ColorPalette.default) was removed as of `supervision-0.22.0`. Use the constant [`ColorPalette.DEFAULT`](draw/color.md/#supervision.draw.color.ColorPalette.DEFAULT) instead.
|
||||
- `BoxAnnotator` was removed as of `supervision-0.22.0`, however `BoundingBoxAnnotator` was immediately renamed to `BoxAnnotator`. Use [`BoxAnnotator`](detection/annotators.md/#supervision.annotators.core.BoxAnnotator) and [`LabelAnnotator`](detection/annotators.md/#supervision.annotators.core.LabelAnnotator) instead of the old `BoxAnnotator`.
|
||||
- The method [`FPSMonitor.__call__`](utils/video.md/#supervision.utils.video.FPSMonitor.__call__) was removed as of `supervision-0.22.0`. Use the attribute [`FPSMonitor.fps`](utils/video.md/#supervision.utils.video.FPSMonitor.fps) instead.
|
||||
|
||||
@@ -1,10 +1,11 @@
|
||||
---
|
||||
comments: true
|
||||
status: new
|
||||
---
|
||||
|
||||
# Annotators
|
||||
|
||||
=== "BoundingBox"
|
||||
=== "Box"
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
@@ -12,8 +13,8 @@ comments: true
|
||||
image = ...
|
||||
detections = sv.Detections(...)
|
||||
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator()
|
||||
annotated_frame = bounding_box_annotator.annotate(
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
annotated_frame = box_annotator.annotate(
|
||||
scene=image.copy(),
|
||||
detections=detections
|
||||
)
|
||||
@@ -299,10 +300,10 @@ comments: true
|
||||
]
|
||||
|
||||
rich_label_annotator = sv.RichLabelAnnotator(
|
||||
font_path=".../font.ttf",
|
||||
font_path="<TTF_FONT_PATH>",
|
||||
text_position=sv.Position.CENTER
|
||||
)
|
||||
annotated_frame = label_annotator.annotate(
|
||||
annotated_frame = rich_label_annotator.annotate(
|
||||
scene=image.copy(),
|
||||
detections=detections,
|
||||
labels=labels
|
||||
@@ -315,6 +316,33 @@ comments: true
|
||||
|
||||
</div>
|
||||
|
||||
=== "Icon"
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
image = ...
|
||||
detections = sv.Detections(...)
|
||||
|
||||
icon_paths = [
|
||||
"<ICON_PATH>"
|
||||
for _ in detections
|
||||
]
|
||||
|
||||
icon_annotator = sv.IconAnnotator()
|
||||
annotated_frame = icon_annotator.annotate(
|
||||
scene=image.copy(),
|
||||
detections=detections,
|
||||
icon_path=icon_paths
|
||||
)
|
||||
```
|
||||
|
||||
<div class="result" markdown>
|
||||
|
||||
{ align=center width="800" }
|
||||
|
||||
</div>
|
||||
|
||||
=== "Crop"
|
||||
|
||||
```python
|
||||
@@ -383,7 +411,7 @@ comments: true
|
||||
trace_annotator = sv.TraceAnnotator()
|
||||
|
||||
video_info = sv.VideoInfo.from_video_path(video_path='...')
|
||||
frames_generator = get_video_frames_generator(source_path='...')
|
||||
frames_generator = sv.get_video_frames_generator(source_path='...')
|
||||
tracker = sv.ByteTrack()
|
||||
|
||||
with sv.VideoSink(target_path='...', video_info=video_info) as sink:
|
||||
@@ -414,7 +442,7 @@ comments: true
|
||||
heat_map_annotator = sv.HeatMapAnnotator()
|
||||
|
||||
video_info = sv.VideoInfo.from_video_path(video_path='...')
|
||||
frames_generator = get_video_frames_generator(source_path='...')
|
||||
frames_generator = sv.get_video_frames_generator(source_path='...')
|
||||
|
||||
with sv.VideoSink(target_path='...', video_info=video_info) as sink:
|
||||
for frame in frames_generator:
|
||||
@@ -432,11 +460,32 @@ comments: true
|
||||
|
||||
</div>
|
||||
|
||||
=== "Background Color"
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
image = ...
|
||||
detections = sv.Detections(...)
|
||||
|
||||
background_overlay_annotator = sv.BackgroundOverlayAnnotator()
|
||||
annotated_frame = background_overlay_annotator.annotate(
|
||||
scene=image.copy(),
|
||||
detections=detections
|
||||
)
|
||||
```
|
||||
|
||||
<div class="result" markdown>
|
||||
|
||||

|
||||
|
||||
</div>
|
||||
|
||||
<div class="md-typeset">
|
||||
<h2><a href="#supervision.annotators.core.BoundingBoxAnnotator">BoundingBoxAnnotator</a></h2>
|
||||
<h2><a href="#supervision.annotators.core.BoxAnnotator">BoxAnnotator</a></h2>
|
||||
</div>
|
||||
|
||||
:::supervision.annotators.core.BoundingBoxAnnotator
|
||||
:::supervision.annotators.core.BoxAnnotator
|
||||
|
||||
<div class="md-typeset">
|
||||
<h2><a href="#supervision.annotators.core.RoundBoxAnnotator">RoundBoxAnnotator</a></h2>
|
||||
@@ -528,6 +577,12 @@ comments: true
|
||||
|
||||
:::supervision.annotators.core.RichLabelAnnotator
|
||||
|
||||
<div class="md-typeset">
|
||||
<h2><a href="#supervision.annotators.core.IconAnnotator">IconAnnotator</a></h2>
|
||||
</div>
|
||||
|
||||
:::supervision.annotators.core.IconAnnotator
|
||||
|
||||
<div class="md-typeset">
|
||||
<h2><a href="#supervision.annotators.core.BlurAnnotator">BlurAnnotator</a></h2>
|
||||
</div>
|
||||
@@ -552,6 +607,12 @@ comments: true
|
||||
|
||||
:::supervision.annotators.core.CropAnnotator
|
||||
|
||||
<div class="md-typeset">
|
||||
<h2><a href="#supervision.annotators.core.BackgroundOverlayAnnotator">BackgroundOverlayAnnotator</a></h2>
|
||||
</div>
|
||||
|
||||
:::supervision.annotators.core.BackgroundOverlayAnnotator
|
||||
|
||||
<div class="md-typeset">
|
||||
<h2><a href="#supervision.annotators.core.ColorLookup">ColorLookup</a></h2>
|
||||
</div>
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
---
|
||||
comments: true
|
||||
status: new
|
||||
---
|
||||
|
||||
# Double Detection Filter
|
||||
|
||||
@@ -2,7 +2,10 @@
|
||||
comments: true
|
||||
---
|
||||
|
||||
# Metrics
|
||||
# Legacy Metrics
|
||||
|
||||
Starting with `0.23.0`, a new metrics module is being introduced to supervision.
|
||||
Metrics here are part of the legacy evaluation API and will be deprecated in the future.
|
||||
|
||||
<div class="md-typeset">
|
||||
<h2><a href="#supervision.metrics.detection.ConfusionMatrix">ConfusionMatrix</a></h2>
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
---
|
||||
comments: true
|
||||
status: new
|
||||
---
|
||||
|
||||
<div class="md-typeset">
|
||||
|
||||
@@ -76,6 +76,18 @@ comments: true
|
||||
|
||||
:::supervision.detection.utils.pad_boxes
|
||||
|
||||
<div class="md-typeset">
|
||||
<h2><a href="#supervision.detection.utils.xywh_to_xyxy">xywh_to_xyxy</a></h2>
|
||||
</div>
|
||||
|
||||
:::supervision.detection.utils.xywh_to_xyxy
|
||||
|
||||
<div class="md-typeset">
|
||||
<h2><a href="#supervision.detection.utils.xcycwh_to_xyxy">xcycwh_to_xyxy</a></h2>
|
||||
</div>
|
||||
|
||||
:::supervision.detection.utils.xcycwh_to_xyxy
|
||||
|
||||
<div class="md-typeset">
|
||||
<h2><a href="#supervision.detection.utils.contains_holes">contains_holes</a></h2>
|
||||
</div>
|
||||
|
||||
@@ -135,7 +135,7 @@ You can load predictions from other computer vision frameworks and libraries usi
|
||||
|
||||
## Annotate Image with Detections
|
||||
|
||||
Finally, we can annotate the image with the predictions. Since we are working with an object detection model, we will use the [`sv.BoundingBoxAnnotator`](/latest/annotators/#supervision.annotators.core.BoundingBoxAnnotator) and [`sv.LabelAnnotator`](/latest/annotators/#supervision.annotators.core.LabelAnnotator) classes.
|
||||
Finally, we can annotate the image with the predictions. Since we are working with an object detection model, we will use the [`sv.BoxAnnotator`](/latest/annotators/#supervision.annotators.core.BoxAnnotator) and [`sv.LabelAnnotator`](/latest/annotators/#supervision.annotators.core.LabelAnnotator) classes.
|
||||
|
||||
=== "Inference"
|
||||
|
||||
@@ -149,10 +149,10 @@ Finally, we can annotate the image with the predictions. Since we are working wi
|
||||
results = model.infer(image)[0]
|
||||
detections = sv.Detections.from_inference(results)
|
||||
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator()
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
label_annotator = sv.LabelAnnotator()
|
||||
|
||||
annotated_image = bounding_box_annotator.annotate(
|
||||
annotated_image = box_annotator.annotate(
|
||||
scene=image, detections=detections)
|
||||
annotated_image = label_annotator.annotate(
|
||||
scene=annotated_image, detections=detections)
|
||||
@@ -170,10 +170,10 @@ Finally, we can annotate the image with the predictions. Since we are working wi
|
||||
results = model(image)[0]
|
||||
detections = sv.Detections.from_ultralytics(results)
|
||||
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator()
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
label_annotator = sv.LabelAnnotator()
|
||||
|
||||
annotated_image = bounding_box_annotator.annotate(
|
||||
annotated_image = box_annotator.annotate(
|
||||
scene=image, detections=detections)
|
||||
annotated_image = label_annotator.annotate(
|
||||
scene=annotated_image, detections=detections)
|
||||
@@ -204,10 +204,10 @@ Finally, we can annotate the image with the predictions. Since we are working wi
|
||||
transformers_results=results,
|
||||
id2label=model.config.id2label)
|
||||
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator()
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
label_annotator = sv.LabelAnnotator()
|
||||
|
||||
annotated_image = bounding_box_annotator.annotate(
|
||||
annotated_image = box_annotator.annotate(
|
||||
scene=image, detections=detections)
|
||||
annotated_image = label_annotator.annotate(
|
||||
scene=annotated_image, detections=detections)
|
||||
@@ -233,7 +233,7 @@ override this behavior by passing a list of custom `labels` to the `annotate` me
|
||||
results = model.infer(image)[0]
|
||||
detections = sv.Detections.from_inference(results)
|
||||
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator()
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
label_annotator = sv.LabelAnnotator()
|
||||
|
||||
labels = [
|
||||
@@ -242,7 +242,7 @@ override this behavior by passing a list of custom `labels` to the `annotate` me
|
||||
in zip(detections['class_name'], detections.confidence)
|
||||
]
|
||||
|
||||
annotated_image = bounding_box_annotator.annotate(
|
||||
annotated_image = box_annotator.annotate(
|
||||
scene=image, detections=detections)
|
||||
annotated_image = label_annotator.annotate(
|
||||
scene=annotated_image, detections=detections, labels=labels)
|
||||
@@ -260,7 +260,7 @@ override this behavior by passing a list of custom `labels` to the `annotate` me
|
||||
results = model(image)[0]
|
||||
detections = sv.Detections.from_ultralytics(results)
|
||||
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator()
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
label_annotator = sv.LabelAnnotator()
|
||||
|
||||
labels = [
|
||||
@@ -269,7 +269,7 @@ override this behavior by passing a list of custom `labels` to the `annotate` me
|
||||
in zip(detections['class_name'], detections.confidence)
|
||||
]
|
||||
|
||||
annotated_image = bounding_box_annotator.annotate(
|
||||
annotated_image = box_annotator.annotate(
|
||||
scene=image, detections=detections)
|
||||
annotated_image = label_annotator.annotate(
|
||||
scene=annotated_image, detections=detections, labels=labels)
|
||||
@@ -300,7 +300,7 @@ override this behavior by passing a list of custom `labels` to the `annotate` me
|
||||
transformers_results=results,
|
||||
id2label=model.config.id2label)
|
||||
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator()
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
label_annotator = sv.LabelAnnotator()
|
||||
|
||||
labels = [
|
||||
@@ -309,7 +309,7 @@ override this behavior by passing a list of custom `labels` to the `annotate` me
|
||||
in zip(detections['class_name'], detections.confidence)
|
||||
]
|
||||
|
||||
annotated_image = bounding_box_annotator.annotate(
|
||||
annotated_image = box_annotator.annotate(
|
||||
scene=image, detections=detections)
|
||||
annotated_image = label_annotator.annotate(
|
||||
scene=annotated_image, detections=detections, labels=labels)
|
||||
@@ -322,7 +322,7 @@ override this behavior by passing a list of custom `labels` to the `annotate` me
|
||||
If you are running the segmentation model
|
||||
[`sv.MaskAnnotator`](/latest/annotators/#supervision.annotators.core.MaskAnnotator)
|
||||
is a drop-in replacement for
|
||||
[`sv.BoundingBoxAnnotator`](/latest/annotators/#supervision.annotators.core.BoundingBoxAnnotator)
|
||||
[`sv.BoxAnnotator`](/latest/annotators/#supervision.annotators.core.BoxAnnotator)
|
||||
that will allow you to draw masks instead of boxes.
|
||||
|
||||
=== "Inference"
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
---
|
||||
comments: true
|
||||
status: new
|
||||
---
|
||||
|
||||
# Detect Small Objects
|
||||
@@ -32,10 +31,10 @@ size relative to the image resolution.
|
||||
results = model.infer(image)[0]
|
||||
detections = sv.Detections.from_inference(results)
|
||||
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator()
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
label_annotator = sv.LabelAnnotator()
|
||||
|
||||
annotated_image = bounding_box_annotator.annotate(
|
||||
annotated_image = box_annotator.annotate(
|
||||
scene=image, detections=detections)
|
||||
annotated_image = label_annotator.annotate(
|
||||
scene=annotated_image, detections=detections)
|
||||
@@ -53,10 +52,10 @@ size relative to the image resolution.
|
||||
results = model(image)[0]
|
||||
detections = sv.Detections.from_ultralytics(results)
|
||||
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator()
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
label_annotator = sv.LabelAnnotator()
|
||||
|
||||
annotated_image = bounding_box_annotator.annotate(
|
||||
annotated_image = box_annotator.annotate(
|
||||
scene=image, detections=detections)
|
||||
annotated_image = label_annotator.annotate(
|
||||
scene=annotated_image, detections=detections)
|
||||
@@ -85,7 +84,7 @@ size relative to the image resolution.
|
||||
outputs=outputs, target_sizes=target_size)[0]
|
||||
detections = sv.Detections.from_transformers(results)
|
||||
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator()
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
label_annotator = sv.LabelAnnotator()
|
||||
|
||||
labels = [
|
||||
@@ -94,7 +93,7 @@ size relative to the image resolution.
|
||||
in detections.class_id
|
||||
]
|
||||
|
||||
annotated_image = bounding_box_annotator.annotate(
|
||||
annotated_image = box_annotator.annotate(
|
||||
scene=image, detections=detections)
|
||||
annotated_image = label_annotator.annotate(
|
||||
scene=annotated_image, detections=detections, labels=labels)
|
||||
@@ -120,10 +119,10 @@ is less effective for ultra-high-resolution images (4K and above).
|
||||
results = model.infer(image)[0]
|
||||
detections = sv.Detections.from_inference(results)
|
||||
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator()
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
label_annotator = sv.LabelAnnotator()
|
||||
|
||||
annotated_image = bounding_box_annotator.annotate(
|
||||
annotated_image = box_annotator.annotate(
|
||||
scene=image, detections=detections)
|
||||
annotated_image = label_annotator.annotate(
|
||||
scene=annotated_image, detections=detections)
|
||||
@@ -141,10 +140,10 @@ is less effective for ultra-high-resolution images (4K and above).
|
||||
results = model(image, imgsz=1280)[0]
|
||||
detections = sv.Detections.from_ultralytics(results)
|
||||
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator()
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
label_annotator = sv.LabelAnnotator()
|
||||
|
||||
annotated_image = bounding_box_annotator.annotate(
|
||||
annotated_image = box_annotator.annotate(
|
||||
scene=image, detections=detections)
|
||||
annotated_image = label_annotator.annotate(
|
||||
scene=annotated_image, detections=detections)
|
||||
@@ -180,10 +179,10 @@ objects within each, and aggregating the results.
|
||||
slicer = sv.InferenceSlicer(callback = callback)
|
||||
detections = slicer(image)
|
||||
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator()
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
label_annotator = sv.LabelAnnotator()
|
||||
|
||||
annotated_image = bounding_box_annotator.annotate(
|
||||
annotated_image = box_annotator.annotate(
|
||||
scene=image, detections=detections)
|
||||
annotated_image = label_annotator.annotate(
|
||||
scene=annotated_image, detections=detections)
|
||||
@@ -207,10 +206,10 @@ objects within each, and aggregating the results.
|
||||
slicer = sv.InferenceSlicer(callback = callback)
|
||||
detections = slicer(image)
|
||||
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator()
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
label_annotator = sv.LabelAnnotator()
|
||||
|
||||
annotated_image = bounding_box_annotator.annotate(
|
||||
annotated_image = box_annotator.annotate(
|
||||
scene=image, detections=detections)
|
||||
annotated_image = label_annotator.annotate(
|
||||
scene=annotated_image, detections=detections)
|
||||
@@ -248,7 +247,7 @@ objects within each, and aggregating the results.
|
||||
slicer = sv.InferenceSlicer(callback = callback)
|
||||
detections = slicer(image)
|
||||
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator()
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
label_annotator = sv.LabelAnnotator()
|
||||
|
||||
labels = [
|
||||
@@ -257,7 +256,7 @@ objects within each, and aggregating the results.
|
||||
in detections.class_id
|
||||
]
|
||||
|
||||
annotated_image = bounding_box_annotator.annotate(
|
||||
annotated_image = box_annotator.annotate(
|
||||
scene=image, detections=detections)
|
||||
annotated_image = label_annotator.annotate(
|
||||
scene=annotated_image, detections=detections, labels=labels)
|
||||
|
||||
@@ -0,0 +1,454 @@
|
||||
---
|
||||
comments: true
|
||||
---
|
||||
|
||||
With Supervision, you can load and manipulate classification, object detection, and
|
||||
segmentation datasets. This tutorial will walk you through how to load, split, merge,
|
||||
visualize, and augment datasets in Supervision.
|
||||
|
||||
## Download Dataset
|
||||
|
||||
In this tutorial, we will use a dataset from
|
||||
[Roboflow Universe](https://universe.roboflow.com/), a public repository of
|
||||
thousands of computer vision datasets. If you already have your dataset in
|
||||
[COCO](https://roboflow.com/formats/coco-json),
|
||||
[YOLO](https://roboflow.com/formats/yolov8-pytorch-txt),
|
||||
or [Pascal VOC](https://roboflow.com/formats/pascal-voc-xml) format, you can skip this
|
||||
section.
|
||||
|
||||
```bash
|
||||
pip install roboflow
|
||||
```
|
||||
|
||||
Next, log into your Roboflow account and download the dataset of your choice in the
|
||||
COCO, YOLO, or Pascal VOC format. You can customize the following code snippet with
|
||||
your workspace ID, project ID, and version number.
|
||||
|
||||
=== "COCO"
|
||||
|
||||
```python
|
||||
import roboflow
|
||||
|
||||
roboflow.login()
|
||||
|
||||
rf = roboflow.Roboflow()
|
||||
project = rf.workspace('<WORKSPACE_ID>').project('<PROJECT_ID>')
|
||||
dataset = project.version('<PROJECT_VERSION>').download("coco")
|
||||
```
|
||||
|
||||
=== "YOLO"
|
||||
|
||||
```python
|
||||
import roboflow
|
||||
|
||||
roboflow.login()
|
||||
|
||||
rf = roboflow.Roboflow()
|
||||
project = rf.workspace('<WORKSPACE_ID>').project('<PROJECT_ID>')
|
||||
dataset = project.version('<PROJECT_VERSION>').download("yolov8")
|
||||
```
|
||||
|
||||
=== "Pascal VOC"
|
||||
|
||||
```python
|
||||
import roboflow
|
||||
|
||||
roboflow.login()
|
||||
|
||||
rf = roboflow.Roboflow()
|
||||
project = rf.workspace('<WORKSPACE_ID>').project('<PROJECT_ID>')
|
||||
dataset = project.version('<PROJECT_VERSION>').download("voc")
|
||||
```
|
||||
|
||||
## Load Dataset
|
||||
|
||||
The Supervision library provides convenient functions to load datasets in various
|
||||
formats. If your dataset is already split into train, test, and valid subsets, you can
|
||||
load each of those as separate [`sv.DetectionDataset`](https://supervision.roboflow.com/latest/datasets/core/#supervision.dataset.core.DetectionDataset)
|
||||
instances.
|
||||
|
||||
=== "COCO"
|
||||
|
||||
We can do so using the [`sv.DetectionDataset.from_coco`](https://supervision.roboflow.com/latest/datasets/core/#supervision.dataset.core.DetectionDataset.from_coco) to load annotations in [COCO](https://roboflow.com/formats/coco-json) format.
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
ds_train = sv.DetectionDataset.from_coco(
|
||||
images_directory_path=f'{dataset.location}/train',
|
||||
annotations_path=f'{dataset.location}/train/_annotations.coco.json',
|
||||
)
|
||||
ds_valid = sv.DetectionDataset.from_coco(
|
||||
images_directory_path=f'{dataset.location}/valid',
|
||||
annotations_path=f'{dataset.location}/valid/_annotations.coco.json',
|
||||
)
|
||||
ds_test = sv.DetectionDataset.from_coco(
|
||||
images_directory_path=f'{dataset.location}/test',
|
||||
annotations_path=f'{dataset.location}/test/_annotations.coco.json',
|
||||
)
|
||||
|
||||
ds_train.classes
|
||||
# ['person', 'bicycle', 'car', ...]
|
||||
|
||||
len(ds_train), len(ds_valid), len(ds_test)
|
||||
# 800, 100, 100
|
||||
```
|
||||
|
||||
=== "YOLO"
|
||||
|
||||
We can do so using the [`sv.DetectionDataset.from_yolo`](https://supervision.roboflow.com/latest/datasets/core/#supervision.dataset.core.DetectionDataset.from_yolo) to load annotations in [YOLO](https://roboflow.com/formats/yolov8-pytorch-txt) format.
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
ds_train = sv.DetectionDataset.from_yolo(
|
||||
images_directory_path=f'{dataset.location}/train/images',
|
||||
annotations_directory_path=f'{dataset.location}/train/labels',
|
||||
data_yaml_path=f'{dataset.location}/data.yaml'
|
||||
)
|
||||
ds_valid = sv.DetectionDataset.from_yolo(
|
||||
images_directory_path=f'{dataset.location}/valid/images',
|
||||
annotations_directory_path=f'{dataset.location}/valid/labels',
|
||||
data_yaml_path=f'{dataset.location}/data.yaml'
|
||||
)
|
||||
ds_test = sv.DetectionDataset.from_yolo(
|
||||
images_directory_path=f'{dataset.location}/test/images',
|
||||
annotations_directory_path=f'{dataset.location}/test/labels',
|
||||
data_yaml_path=f'{dataset.location}/data.yaml'
|
||||
)
|
||||
|
||||
ds_train.classes
|
||||
# ['person', 'bicycle', 'car', ...]
|
||||
|
||||
len(ds_train), len(ds_valid), len(ds_test)
|
||||
# 800, 100, 100
|
||||
```
|
||||
|
||||
=== "Pascal VOC"
|
||||
|
||||
We can do so using the [`sv.DetectionDataset.from_pascal_voc`](https://supervision.roboflow.com/latest/datasets/core/#supervision.dataset.core.DetectionDataset.from_pascal_voc) to load annotations in [Pascal VOC](https://roboflow.com/formats/pascal-voc-xml) format.
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
ds_train = sv.DetectionDataset.from_pascal_voc(
|
||||
images_directory_path=f'{dataset.location}/train/images',
|
||||
annotations_directory_path=f'{dataset.location}/train/labels'
|
||||
)
|
||||
ds_valid = sv.DetectionDataset.from_pascal_voc(
|
||||
images_directory_path=f'{dataset.location}/valid/images',
|
||||
annotations_directory_path=f'{dataset.location}/valid/labels'
|
||||
)
|
||||
ds_test = sv.DetectionDataset.from_pascal_voc(
|
||||
images_directory_path=f'{dataset.location}/test/images',
|
||||
annotations_directory_path=f'{dataset.location}/test/labels'
|
||||
)
|
||||
|
||||
ds_train.classes
|
||||
# ['person', 'bicycle', 'car', ...]
|
||||
|
||||
len(ds_train), len(ds_valid), len(ds_test)
|
||||
# 800, 100, 100
|
||||
```
|
||||
|
||||
## Split Dataset
|
||||
|
||||
If your dataset is not already split into train, test, and valid subsets, you can
|
||||
easily do so using the [`sv.DetectionDataset.split`](https://supervision.roboflow.com/latest/datasets/core/#supervision.dataset.core.DetectionDataset.split)
|
||||
method. We can split it as follows, ensuring a random shuffle of the data.
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
ds = sv.DetectionDataset(...)
|
||||
|
||||
len(ds)
|
||||
# 1000
|
||||
|
||||
ds_train, ds = ds.split(split_ratio=0.8, shuffle=True)
|
||||
ds_valid, ds_test = ds.split(split_ratio=0.5, shuffle=True)
|
||||
|
||||
len(ds_train), len(ds_valid), len(ds_test)
|
||||
# 800, 100, 100
|
||||
```
|
||||
|
||||
## Merge Dataset
|
||||
|
||||
If you have multiple datasets that you would like to merge, you can do so using the
|
||||
[`sv.DetectionDataset.merge`](https://supervision.roboflow.com/latest/datasets/core/#supervision.dataset.core.DetectionDataset.merge)
|
||||
method.
|
||||
|
||||
=== "COCO"
|
||||
|
||||
```{ .py hl_lines="22-28" }
|
||||
import supervision as sv
|
||||
|
||||
ds_train = sv.DetectionDataset.from_coco(
|
||||
images_directory_path=f'{dataset.location}/train',
|
||||
annotations_path=f'{dataset.location}/train/_annotations.coco.json',
|
||||
)
|
||||
ds_valid = sv.DetectionDataset.from_coco(
|
||||
images_directory_path=f'{dataset.location}/valid',
|
||||
annotations_path=f'{dataset.location}/valid/_annotations.coco.json',
|
||||
)
|
||||
ds_test = sv.DetectionDataset.from_coco(
|
||||
images_directory_path=f'{dataset.location}/test',
|
||||
annotations_path=f'{dataset.location}/test/_annotations.coco.json',
|
||||
)
|
||||
|
||||
ds_train.classes
|
||||
# ['person', 'bicycle', 'car', ...]
|
||||
|
||||
len(ds_train), len(ds_valid), len(ds_test)
|
||||
# 800, 100, 100
|
||||
|
||||
ds = sv.DetectionDataset.merge([ds_train, ds_valid, ds_test])
|
||||
|
||||
ds.classes
|
||||
# ['person', 'bicycle', 'car', ...]
|
||||
|
||||
len(ds)
|
||||
# 1000
|
||||
```
|
||||
|
||||
=== "YOLO"
|
||||
|
||||
```{ .py hl_lines="25-31" }
|
||||
import supervision as sv
|
||||
|
||||
ds_train = sv.DetectionDataset.from_yolo(
|
||||
images_directory_path=f'{dataset.location}/train/images',
|
||||
annotations_directory_path=f'{dataset.location}/train/labels',
|
||||
data_yaml_path=f'{dataset.location}/data.yaml'
|
||||
)
|
||||
ds_valid = sv.DetectionDataset.from_yolo(
|
||||
images_directory_path=f'{dataset.location}/valid/images',
|
||||
annotations_directory_path=f'{dataset.location}/valid/labels',
|
||||
data_yaml_path=f'{dataset.location}/data.yaml'
|
||||
)
|
||||
ds_test = sv.DetectionDataset.from_yolo(
|
||||
images_directory_path=f'{dataset.location}/test/images',
|
||||
annotations_directory_path=f'{dataset.location}/test/labels',
|
||||
data_yaml_path=f'{dataset.location}/data.yaml'
|
||||
)
|
||||
|
||||
ds_train.classes
|
||||
# ['person', 'bicycle', 'car', ...]
|
||||
|
||||
len(ds_train), len(ds_valid), len(ds_test)
|
||||
# 800, 100, 100
|
||||
|
||||
ds = sv.DetectionDataset.merge([ds_train, ds_valid, ds_test])
|
||||
|
||||
ds.classes
|
||||
# ['person', 'bicycle', 'car', ...]
|
||||
|
||||
len(ds)
|
||||
# 1000
|
||||
```
|
||||
|
||||
=== "Pascal VOC"
|
||||
|
||||
```{ .py hl_lines="22-28" }
|
||||
import supervision as sv
|
||||
|
||||
ds_train = sv.DetectionDataset.from_pascal_voc(
|
||||
images_directory_path=f'{dataset.location}/train/images',
|
||||
annotations_directory_path=f'{dataset.location}/train/labels'
|
||||
)
|
||||
ds_valid = sv.DetectionDataset.from_pascal_voc(
|
||||
images_directory_path=f'{dataset.location}/valid/images',
|
||||
annotations_directory_path=f'{dataset.location}/valid/labels'
|
||||
)
|
||||
ds_test = sv.DetectionDataset.from_pascal_voc(
|
||||
images_directory_path=f'{dataset.location}/test/images',
|
||||
annotations_directory_path=f'{dataset.location}/test/labels'
|
||||
)
|
||||
|
||||
ds_train.classes
|
||||
# ['person', 'bicycle', 'car', ...]
|
||||
|
||||
len(ds_train), len(ds_valid), len(ds_test)
|
||||
# 800, 100, 100
|
||||
|
||||
ds = sv.DetectionDataset.merge([ds_train, ds_valid, ds_test])
|
||||
|
||||
ds.classes
|
||||
# ['person', 'bicycle', 'car', ...]
|
||||
|
||||
len(ds)
|
||||
# 1000
|
||||
```
|
||||
|
||||
## Iterate over Dataset
|
||||
|
||||
There are two ways to loop over a `sv.DetectionDataset`: using a direct
|
||||
[for loop](https://supervision.roboflow.com/latest/datasets/core/#supervision.dataset.core.DetectionDataset.__iter__)
|
||||
called on the `sv.DetectionDataset` instance or loading `sv.DetectionDataset` entries
|
||||
[by index](https://supervision.roboflow.com/latest/datasets/core/#supervision.dataset.core.DetectionDataset.__getitem__).
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
ds = sv.DetectionDataset(...)
|
||||
|
||||
# Option 1
|
||||
for image_path, image, annotations in ds:
|
||||
... # Process each image and its annotations
|
||||
|
||||
# Option 2
|
||||
for idx in range(len(ds)):
|
||||
image_path, image, annotations = ds[idx]
|
||||
... # Process the image and annotations at index `idx`
|
||||
```
|
||||
|
||||
## Visualize Dataset
|
||||
|
||||
The Supervision library provides tools for easily visualizing your detection dataset.
|
||||
You can create a grid of annotated images to quickly inspect your data and labels.
|
||||
First, initialize the [`sv.BoxAnnotator`](https://supervision.roboflow.com/latest/detection/annotators/#supervision.annotators.core.BoxAnnotator)
|
||||
and [`sv.LabelAnnotator`](https://supervision.roboflow.com/latest/detection/annotators/#supervision.annotators.core.LabelAnnotator).
|
||||
Then, iterate through a subset of the dataset (e.g., the first 25 images), drawing
|
||||
bounding boxes and class labels on each image. Finally, combine the annotated images
|
||||
into a grid for display.
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
ds = sv.DetectionDataset(...)
|
||||
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
label_annotator = sv.LabelAnnotator()
|
||||
|
||||
annotated_images = []
|
||||
for i in range(16):
|
||||
_, image, annotations = ds[i]
|
||||
|
||||
labels = [ds.classes[class_id] for class_id in annotations.class_id]
|
||||
|
||||
annotated_image = image.copy()
|
||||
annotated_image = box_annotator.annotate(annotated_image, annotations)
|
||||
annotated_image = label_annotator.annotate(annotated_image, annotations, labels)
|
||||
annotated_images.append(annotated_image)
|
||||
|
||||
grid = sv.create_tiles(
|
||||
annotated_images,
|
||||
grid_size=(4, 4),
|
||||
single_tile_size=(400, 400),
|
||||
tile_padding_color=sv.Color.WHITE,
|
||||
tile_margin_color=sv.Color.WHITE
|
||||
)
|
||||
```
|
||||
|
||||

|
||||
|
||||
## Save Dataset
|
||||
|
||||
=== "COCO"
|
||||
|
||||
We can do so using the [`sv.DetectionDataset.as_coco`](https://supervision.roboflow.com/datasets/#supervision.dataset.core.DetectionDataset.as_coco) method to save annotations in [COCO](https://roboflow.com/formats/coco-json) format.
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
ds = sv.DetectionDataset(...)
|
||||
|
||||
ds.as_coco(
|
||||
images_directory_path='<IMAGE_DIRECTORY_PATH>',
|
||||
annotations_path='<ANNOTATIONS_PATH>'
|
||||
)
|
||||
```
|
||||
|
||||
=== "YOLO"
|
||||
|
||||
We can do so using the [`sv.DetectionDataset.as_yolo`](https://supervision.roboflow.com/datasets/#supervision.dataset.core.DetectionDataset.as_yolo) method to save annotations in [YOLO](https://roboflow.com/formats/yolov8-pytorch-txt) format.
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
ds = sv.DetectionDataset(...)
|
||||
|
||||
ds.as_yolo(
|
||||
images_directory_path='<IMAGE_DIRECTORY_PATH>',
|
||||
annotations_directory_path='<ANNOTATIONS_DIRECTORY_PATH>',
|
||||
data_yaml_path='<DATA_YAML_PATH>'
|
||||
)
|
||||
```
|
||||
|
||||
=== "Pascal VOC"
|
||||
|
||||
We can do so using the [`sv.DetectionDataset.as_pascal_voc`](https://supervision.roboflow.com/datasets/#supervision.dataset.core.DetectionDataset.as_pascal_voc) method to save annotations in [Pascal VOC](https://roboflow.com/formats/pascal-voc-xml) format.
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
ds = sv.DetectionDataset(...)
|
||||
|
||||
ds.as_pascal_voc(
|
||||
images_directory_path='<IMAGE_DIRECTORY_PATH>',
|
||||
annotations_directory_path='<ANNOTATIONS_DIRECTORY_PATH>'
|
||||
)
|
||||
```
|
||||
|
||||
## Augment Dataset
|
||||
|
||||
In this section, we'll explore using Supervision in combination with Albumentations to
|
||||
augment our dataset. Data augmentation is a common technique in computer vision to
|
||||
increase the size and diversity of training datasets, leading to improved model
|
||||
performance and generalization.
|
||||
|
||||
```bash
|
||||
pip install augmentation
|
||||
```
|
||||
|
||||
Albumentations provides a flexible and powerful API for image augmentation. The core of
|
||||
the library is the [`Compose`](https://albumentations.ai/docs/api_reference/full_reference/?h=compose#albumentations.core.composition.Compose)
|
||||
class, which allows you to chain multiple image transformations together. Each
|
||||
transformation is defined using a dedicated class, such as
|
||||
[`HorizontalFlip`](https://albumentations.ai/docs/api_reference/full_reference/?h=horizontalflip#albumentations.augmentations.geometric.transforms.HorizontalFlip),
|
||||
[`RandomBrightnessContrast`](https://albumentations.ai/docs/api_reference/full_reference/?h=horizontalflip#albumentations.augmentations.transforms.RandomBrightnessContrast),
|
||||
or [`Perspective`](https://albumentations.ai/docs/api_reference/full_reference/?h=horizontalflip#albumentations.augmentations.geometric.transforms.Perspective).
|
||||
|
||||
```python
|
||||
import albumentations as A
|
||||
|
||||
augmentation = A.Compose(
|
||||
transforms=[
|
||||
A.Perspective(p=0.1),
|
||||
A.HorizontalFlip(p=0.5),
|
||||
A.RandomBrightnessContrast(p=0.5)
|
||||
],
|
||||
bbox_params=A.BboxParams(
|
||||
format='pascal_voc',
|
||||
label_fields=['category']
|
||||
),
|
||||
)
|
||||
```
|
||||
|
||||
The key is to set `format='pascal_voc'`, which corresponds to the
|
||||
`[x_min, y_min, x_max, y_max]` bounding box format used in Supervision.
|
||||
|
||||
```python
|
||||
import numpy as np
|
||||
import supervision as sv
|
||||
from dataclasses import replace
|
||||
|
||||
ds = sv.DetectionDataset(...)
|
||||
|
||||
_, original_image, original_annotations = ds[0]
|
||||
|
||||
output = augmentation(
|
||||
image=original_image,
|
||||
bboxes=original_annotations.xyxy,
|
||||
category=original_annotations.class_id
|
||||
)
|
||||
|
||||
augmented_image = output['image']
|
||||
augmented_annotations = replace(
|
||||
original_annotations,
|
||||
xyxy=np.array(output['bboxes']),
|
||||
class_id=np.array(output['category'])
|
||||
)
|
||||
```
|
||||
|
||||

|
||||
@@ -32,7 +32,7 @@ download_assets(VideoAssets.PEOPLE_WALKING)
|
||||
First, you'll need to obtain predictions from your object detection or segmentation
|
||||
model. In this tutorial, we are using the YOLOv8 model as an example. However,
|
||||
Supervision is versatile and compatible with various models. Check this
|
||||
[link](latest/how_to/detect_and_annotate/#load-predictions-into-supervision)
|
||||
[link](/latest/how_to/detect_and_annotate/#load-predictions-into-supervision)
|
||||
for guidance on how to plug in other models.
|
||||
|
||||
We will define a `callback` function, which will process each frame of the video
|
||||
|
||||
@@ -146,4 +146,13 @@ You can install `supervision` in a
|
||||
|
||||
Master the techniques to selectively filter and focus on objects within a specific zone
|
||||
|
||||
- **Cheatsheet**
|
||||
|
||||
***
|
||||
|
||||
Access a quick reference guide to the most common `supervision` functions
|
||||
|
||||
[:octicons-arrow-right-24: Cheatsheet](https://roboflow.github.io/cheatsheet-supervision/)
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
@@ -28,16 +28,15 @@ document.addEventListener("DOMContentLoaded", function () {
|
||||
}, {});
|
||||
|
||||
|
||||
async function renderCard(element, elementIndex) {
|
||||
const url = element.getAttribute('data-url');
|
||||
const name = element.getAttribute('data-name');
|
||||
const labels = element.getAttribute('data-labels');
|
||||
const version = element.getAttribute('data-version');
|
||||
const authors = element.getAttribute('data-author');
|
||||
async function renderCard(element, elementIndex) {
|
||||
const name = element.getAttribute('data-name');
|
||||
const labels = element.getAttribute('data-labels');
|
||||
const version = element.getAttribute('data-version');
|
||||
const authors = element.getAttribute('data-author');
|
||||
|
||||
const labelHTML = labels ? labels.split(',').filter(label => label !== '').map((label, index) => {
|
||||
const color = labelToColor[label.trim()];
|
||||
return `
|
||||
const labelHTML = labels ? labels.split(',').filter(label => label !== '').map((label, index) => {
|
||||
const color = labelToColor[label.trim()];
|
||||
return `
|
||||
<span
|
||||
class="label non-selectable-text"
|
||||
style="background-color: ${color}"
|
||||
@@ -45,18 +44,18 @@ document.addEventListener("DOMContentLoaded", function () {
|
||||
${label.trim()}
|
||||
</span>
|
||||
`;
|
||||
}).join(' ') : '';
|
||||
}).join(' ') : '';
|
||||
|
||||
const authorArray = authors.split(',');
|
||||
const authorDataArray = await Promise.all(authorArray.map(async (author) => {
|
||||
const response = await fetch(`https://api.github.com/users/${author.trim()}`);
|
||||
return await response.json();
|
||||
}));
|
||||
const authorArray = authors.split(',');
|
||||
const authorDataArray = await Promise.all(authorArray.map(async (author) => {
|
||||
const response = await fetch(`https://api.github.com/users/${author.trim()}`);
|
||||
return await response.json();
|
||||
}));
|
||||
|
||||
let authorAvatarsHTML = authorDataArray.map((authorData, index) => {
|
||||
const marginLeft = index === 0 ? '0' : '-10px';
|
||||
const zIndex = 4 - index;
|
||||
return `
|
||||
let authorAvatarsHTML = authorDataArray.map((authorData, index) => {
|
||||
const marginLeft = index === 0 ? '0' : '-10px';
|
||||
const zIndex = 4 - index;
|
||||
return `
|
||||
<div
|
||||
class="author-container"
|
||||
data-login="${authorData.login}-${elementIndex}"
|
||||
@@ -75,10 +74,10 @@ document.addEventListener("DOMContentLoaded", function () {
|
||||
</a>
|
||||
</div>
|
||||
`;
|
||||
}).join('');
|
||||
}).join('');
|
||||
|
||||
let authorNamesHTML = authorDataArray.map(
|
||||
authorData => `
|
||||
let authorNamesHTML = authorDataArray.map(
|
||||
authorData => `
|
||||
<span
|
||||
class="author-name"
|
||||
data-login="${authorData.login}-${elementIndex}"
|
||||
@@ -88,54 +87,52 @@ document.addEventListener("DOMContentLoaded", function () {
|
||||
${authorData.login}
|
||||
</a>
|
||||
</span>`
|
||||
).join(', ');
|
||||
).join(', ');
|
||||
|
||||
let authorsHTML = `
|
||||
let authorsHTML = `
|
||||
<div class="authors">
|
||||
${authorAvatarsHTML}
|
||||
<div class="author-names">${authorNamesHTML}</div>
|
||||
</div>
|
||||
`;
|
||||
`;
|
||||
|
||||
element.innerText = `
|
||||
<a style="text-decoration: none; color: inherit;" href="${url}">
|
||||
<div style="flex-direction: column; height: 100%; display: flex;
|
||||
font-family: -apple-system,BlinkMacSystemFont,Segoe UI,Helvetica,Arial,sans-serif,Apple Color Emoji,Segoe UI Emoji; background: ${theme.background}; font-size: 14px; line-height: 1.5; color: ${theme.color}">
|
||||
<div style="display: flex; align-items: center;">
|
||||
<span style="font-weight: 700; font-size: 1rem; color: ${theme.linkColor};">
|
||||
${name}
|
||||
</span>
|
||||
</div>
|
||||
${authorsHTML}
|
||||
<div style="font-size: 12px; color: ${theme.color}; display: flex; flex: 0; justify-content: space-between">
|
||||
element.innerText = `
|
||||
<div style="flex-direction: column; height: 100%; display: flex;
|
||||
font-family: -apple-system,BlinkMacSystemFont,Segoe UI,Helvetica,Arial,sans-serif,Apple Color Emoji,Segoe UI Emoji; background: ${theme.background}; font-size: 14px; line-height: 1.5; color: ${theme.color}">
|
||||
<div style="display: flex; align-items: center;">
|
||||
<img src="/assets/supervision-lenny.png" aria-label="stars" width="20" height="20" role="img" />
|
||||
|
||||
<span style="margin-left: 4px">${version}</span>
|
||||
<span style="font-weight: 700; font-size: 1rem; color: ${theme.linkColor};">
|
||||
${name}
|
||||
</span>
|
||||
</div>
|
||||
<div style="display: flex; align-items: center; flex-wrap: wrap">
|
||||
${labelHTML}
|
||||
${authorsHTML}
|
||||
<div style="font-size: 12px; color: ${theme.color}; display: flex; flex: 0; justify-content: space-between">
|
||||
<div style="display: flex; align-items: center;">
|
||||
<img src="/assets/supervision-lenny.png" aria-label="stars" width="20" height="20" role="img" />
|
||||
|
||||
<span style="margin-left: 4px">${version}</span>
|
||||
</div>
|
||||
<div style="display: flex; align-items: center; flex-wrap: wrap">
|
||||
${labelHTML}
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</a>
|
||||
`
|
||||
`;
|
||||
|
||||
let sanitizedHTML = DOMPurify.sanitize(element.innerText);
|
||||
element.innerHTML = sanitizedHTML;
|
||||
let sanitizedHTML = DOMPurify.sanitize(element.innerText);
|
||||
element.innerHTML = sanitizedHTML;
|
||||
|
||||
document.querySelectorAll('.author-name').forEach(element => {
|
||||
element.addEventListener('mouseenter', function() {
|
||||
const login = this.getAttribute('data-login');
|
||||
document.querySelector(`.author-container[data-login="${login}"]`).classList.add('hover');
|
||||
document.querySelectorAll('.author-name').forEach(element => {
|
||||
element.addEventListener('mouseenter', function () {
|
||||
const login = this.getAttribute('data-login');
|
||||
document.querySelector(`.author-container[data-login="${login}"]`).classList.add('hover');
|
||||
});
|
||||
|
||||
element.addEventListener('mouseleave', function () {
|
||||
const login = this.getAttribute('data-login');
|
||||
document.querySelector(`.author-container[data-login="${login}"]`).classList.remove('hover');
|
||||
});
|
||||
});
|
||||
|
||||
element.addEventListener('mouseleave', function() {
|
||||
const login = this.getAttribute('data-login');
|
||||
document.querySelector(`.author-container[data-login="${login}"]`).classList.remove('hover');
|
||||
});
|
||||
});
|
||||
}
|
||||
}
|
||||
repoCards.forEach((element, index) => {
|
||||
renderCard(element, index);
|
||||
});
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
---
|
||||
comments: true
|
||||
status: new
|
||||
---
|
||||
|
||||
# Keypoint Detection
|
||||
|
||||
@@ -0,0 +1,18 @@
|
||||
---
|
||||
comments: true
|
||||
status: new
|
||||
---
|
||||
|
||||
# Mean Average Precision
|
||||
|
||||
<div class="md-typeset">
|
||||
<h2><a href="#supervision.metrics.mean_average_precision.MeanAveragePrecision">MeanAveragePrecision</a></h2>
|
||||
</div>
|
||||
|
||||
:::supervision.metrics.mean_average_precision.MeanAveragePrecision
|
||||
|
||||
<div class="md-typeset">
|
||||
<h2><a href="#supervision.metrics.mean_average_precision.MeanAveragePrecisionResult">MeanAveragePrecisionResult</a></h2>
|
||||
</div>
|
||||
|
||||
:::supervision.metrics.mean_average_precision.MeanAveragePrecisionResult
|
||||
+1
-1
@@ -368,7 +368,7 @@
|
||||
"<br>\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"In the code above we've created a`video_info` variable to pass information about the video to our `VideoSink`. The `VideoSink` is a cool little context manager that allows us to `write_frames()` to a video ouput file. We're also optionally using `tqdm` to display a progress bar with a % complete. We only scratched the surface of all of the customizable Annotators and additional features that Supervision and Inference have to offer. Stay tuned for more cookbooks on how to take advantge of them in your computer vision applications. Happy building! \ud83d\ude80"
|
||||
"In the code above we've created a`video_info` variable to pass information about the video to our `VideoSink`. The `VideoSink` is a cool little context manager that allows us to `write_frames()` to a video output file. We're also optionally using `tqdm` to display a progress bar with a % complete. We only scratched the surface of all of the customizable Annotators and additional features that Supervision and Inference have to offer. Stay tuned for more cookbooks on how to take advantage of them in your computer vision applications. Happy building! \ud83d\ude80"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
||||
+1
-1
@@ -402,7 +402,7 @@
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"## Improve Vizualizations"
|
||||
"## Improve Visualizations"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "HsPNfuM_3ENR"
|
||||
|
||||
Vendored
+1
-1
@@ -103,7 +103,7 @@
|
||||
"source": [
|
||||
"## Download a Video Asset\n",
|
||||
"\n",
|
||||
"Now that we have our enviornment setup, lets download a video that we can detect objects in. Supervision comes with a great utility to help us hit the ground running. We can use the below snippet to he video is save a video asset in our local directory. It can also be accessed with the variable `path_to_video` for additional application logic."
|
||||
"Now that we have our environment setup, lets download a video that we can detect objects in. Supervision comes with a great utility to help us hit the ground running. We can use the below snippet to he video is save a video asset in our local directory. It can also be accessed with the variable `path_to_video` for additional application logic."
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
+1
-1
@@ -951,7 +951,7 @@
|
||||
},
|
||||
"source": [
|
||||
"#### Import your data\n",
|
||||
"To load your data back in, upload the saved file to the Colab enviorment and run the code cell."
|
||||
"To load your data back in, upload the saved file to the Colab environment and run the code cell."
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
Vendored
+357
-224
File diff suppressed because one or more lines are too long
+1
-1
@@ -10,7 +10,7 @@
|
||||
"\n",
|
||||
"---\n",
|
||||
"\n",
|
||||
"[](https://colab.research.google.com/github/roboflow/supervision/blob/develop/docs/notebooks/detections-to-jsonsink.ipynb)\n",
|
||||
"[](https://colab.research.google.com/github/roboflow/supervision/blob/develop/docs/notebooks/serialise-detections-to-csv.ipynb)\n",
|
||||
"\n",
|
||||
"This cookbook introduce [sv.CSVSink](https://supervision.roboflow.com/latest/detection/tools/save_detections/#supervision.detection.tools.csv_sink.CSVSink) tool designed to write captured object detection data to file from video streams/file"
|
||||
]
|
||||
|
||||
+1
-1
@@ -10,7 +10,7 @@
|
||||
"\n",
|
||||
"---\n",
|
||||
"\n",
|
||||
"[](https://colab.research.google.com/github/roboflow/supervision/blob/develop/docs/notebooks/detections-to-jsonsink.ipynb)\n",
|
||||
"[](https://colab.research.google.com/github/roboflow/supervision/blob/develop/docs/notebooks/serialise-detections-to-json.ipynb)\n",
|
||||
"\n",
|
||||
"This cookbook introduce [sv.JSONSink](https://supervision.roboflow.com/develop/detection/tools/save_detections/#supervision.detection.tools.json_sink.JSONSink) tool designed to write captured object detection data to file from video streams/file"
|
||||
]
|
||||
|
||||
@@ -19,6 +19,16 @@
|
||||
}
|
||||
}
|
||||
|
||||
.custom-grid a {
|
||||
color: inherit;
|
||||
text-decoration: none;
|
||||
display: block;
|
||||
}
|
||||
|
||||
.custom-grid a:hover {
|
||||
color: inherit; /* Ensure color does not change on hover */
|
||||
}
|
||||
|
||||
.repo-card {
|
||||
background: radial-gradient(at right top, #A351FB25, #A5F9EA25);
|
||||
border-radius: 0.5rem;
|
||||
|
||||
Vendored
+39
-11
@@ -11,17 +11,45 @@
|
||||
<h1>Supervision Cookbooks</h1>
|
||||
</div>
|
||||
<div class="custom-grid">
|
||||
<p class="card repo-card" data-url="/develop/notebooks/quickstart" data-name="Supervision Quickstart" data-labels="ANNOTATOR,DETECTION,SAM" data-version="v0.18.0" data-author="SkalskiP,onuralpszr"></p>
|
||||
<p class="card repo-card" data-url="/develop/notebooks/count-objects-crossing-the-line" data-name="Count Objects Crossing the Line" data-labels="ANNOTATORS,LINE ZONE,TRACKING" data-version="v0.18.0" data-author="SkalskiP"></p>
|
||||
<p class="card repo-card" data-url="/develop/notebooks/zero-shot-object-detection-with-yolo-world" data-name="Zero-Shot Object Detection with YOLO-World" data-labels="ANNOTATORS,DETECTION,INFERENCE" data-version="v0.19.0" data-author="SkalskiP"></p>
|
||||
<p class="card repo-card" data-url="/develop/notebooks/download-supervision-assets" data-name="Downloading Supervision Assets" data-labels="ASSETS" data-version="v0.18.0" data-author="nickherrig"></p>
|
||||
<p class="card repo-card" data-url="/develop/notebooks/annotate-video-with-detections" data-name="Annotate Video with Detections" data-labels="INFERENCE,YOLOV8" data-version="v0.18.0" data-author="nickherrig"></p>
|
||||
<p class="card repo-card" data-url="/develop/notebooks/object-tracking" data-name="Object Tracking" data-labels="TRACKING, ANNOTATOR" data-version="v0.18.0" data-author="nickherrig"></p>
|
||||
<p class="card repo-card" data-url="/develop/notebooks/occupancy_analytics" data-name="Analyzing Zone Occupancy" data-labels="ANNOTATOR,DETECTION,ZONES" data-version="v0.19.0" data-author="stellasphere"></p>
|
||||
<p class="card repo-card" data-url="/develop/notebooks/evaluating-alignment-of-text-to-image-diffusion-models" data-name="Evaluating Alignment of Text-to-image Diffusion Models" data-labels="ANNOTATORS,YOLO WORLD" data-version="v0.19.0rc5" data-author="iamhatesz"></p>
|
||||
<p class="card repo-card" data-url="/develop/notebooks/serialise-detections-to-csv" data-name="Serialise Detections to a CSV File" data-labels="DETECTIONS,CSV SINK,INFERENCE" data-version="v0.21.0" data-author="onuralpszr"></p>
|
||||
<p class="card repo-card" data-url="/develop/notebooks/serialise-detections-to-json" data-name="Serialise Detections to a JSON File" data-labels="DETECTIONS,JSON SINK,INFERENCE" data-version="v0.21.0" data-author="onuralpszr"></p>
|
||||
|
||||
<a href="/develop/notebooks/quickstart"> <p class="card repo-card" data-name="Supervision Quickstart" data-labels="ANNOTATOR,DETECTION,SAM"
|
||||
data-version="v0.18.0" data-author="SkalskiP,onuralpszr"></p>
|
||||
</a>
|
||||
<a href="/develop/notebooks/count-objects-crossing-the-line">
|
||||
<p class="card repo-card" data-name="Count Objects Crossing the Line"
|
||||
data-labels="ANNOTATORS,LINE ZONE,TRACKING" data-version="v0.18.0" data-author="SkalskiP"></p>
|
||||
</a>
|
||||
<a href="/develop/notebooks/zero-shot-object-detection-with-yolo-world">
|
||||
<p class="card repo-card" data-name="Zero-Shot Object Detection with YOLO-World"
|
||||
data-labels="ANNOTATORS,DETECTION,INFERENCE" data-version="v0.19.0" data-author="SkalskiP"></p>
|
||||
</a>
|
||||
<a href="/develop/notebooks/download-supervision-assets">
|
||||
<p class="card repo-card" data-name="Downloading Supervision Assets" data-labels="ASSETS" data-version="v0.18.0"
|
||||
data-author="nickherrig"></p>
|
||||
</a>
|
||||
<a href="/develop/notebooks/annotate-video-with-detections">
|
||||
<p class="card repo-card" data-name="Annotate Video with Detections" data-labels="INFERENCE,YOLOV8"
|
||||
data-version="v0.18.0" data-author="nickherrig"></p>
|
||||
</a>
|
||||
<a href="/develop/notebooks/object-tracking">
|
||||
<p class="card repo-card" data-name="Object Tracking" data-labels="TRACKING, ANNOTATOR" data-version="v0.18.0"
|
||||
data-author="nickherrig"></p>
|
||||
</a>
|
||||
<a href="/develop/notebooks/occupancy_analytics">
|
||||
<p class="card repo-card" data-name="Analyzing Zone Occupancy" data-labels="ANNOTATOR,DETECTION,ZONES"
|
||||
data-version="v0.19.0" data-author="stellasphere"></p>
|
||||
</a>
|
||||
<a href="/develop/notebooks/evaluating-alignment-of-text-to-image-diffusion-models">
|
||||
<p class="card repo-card" data-name="Evaluating Alignment of Text-to-image Diffusion Models"
|
||||
data-labels="ANNOTATORS,YOLO WORLD" data-version="v0.19.0rc5" data-author="iamhatesz"></p>
|
||||
</a>
|
||||
<a href="/develop/notebooks/serialise-detections-to-csv">
|
||||
<p class="card repo-card" data-name="Serialise Detections to a CSV File"
|
||||
data-labels="DETECTIONS,CSV SINK,INFERENCE" data-version="v0.21.0" data-author="onuralpszr"></p>
|
||||
</a>
|
||||
<a href="/develop/notebooks/serialise-detections-to-json">
|
||||
<p class="card repo-card" data-name="Serialise Detections to a JSON File"
|
||||
data-labels="DETECTIONS,JSON SINK,INFERENCE" data-version="v0.21.0" data-author="onuralpszr"></p>
|
||||
</a>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
comments: true
|
||||
status: new
|
||||
---
|
||||
|
||||
# Image Utils
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
comments: true
|
||||
status: new
|
||||
---
|
||||
|
||||
# Video Utils
|
||||
|
||||
@@ -11,7 +11,7 @@ from tqdm import tqdm
|
||||
|
||||
import supervision as sv
|
||||
|
||||
COLORS = sv.ColorPalette.default()
|
||||
COLORS = sv.ColorPalette.DEFAULT
|
||||
|
||||
|
||||
def load_zones_config(file_path: str) -> List[np.ndarray]:
|
||||
@@ -75,7 +75,7 @@ def detect(
|
||||
frame (np.ndarray): The frame to process, expected to be a NumPy array.
|
||||
model (RoboflowInferenceModel): The Inference model used for processing the
|
||||
frame.
|
||||
confidence_threshold (float, optional): The confidence threshold for filtering
|
||||
confidence_threshold (float): The confidence threshold for filtering
|
||||
detections. Default is 0.5.
|
||||
|
||||
Returns:
|
||||
|
||||
@@ -9,7 +9,7 @@ from ultralytics import YOLO
|
||||
|
||||
import supervision as sv
|
||||
|
||||
COLORS = sv.ColorPalette.default()
|
||||
COLORS = sv.ColorPalette.DEFAULT
|
||||
|
||||
|
||||
def load_zones_config(file_path: str) -> List[np.ndarray]:
|
||||
@@ -72,7 +72,7 @@ def detect(
|
||||
Args:
|
||||
frame (np.ndarray): The frame to process, expected to be a NumPy array.
|
||||
model (YOLO): The YOLO model used for processing the frame.
|
||||
confidence_threshold (float, optional): The confidence threshold for filtering
|
||||
confidence_threshold (float): The confidence threshold for filtering
|
||||
detections. Default is 0.5.
|
||||
|
||||
Returns:
|
||||
|
||||
@@ -20,9 +20,9 @@ def heatmap_and_track(
|
||||
iou_threshold: float = 0.5,
|
||||
heatmap_alpha: float = 0.5,
|
||||
radius: int = 25,
|
||||
track_threshold: float = 0.35,
|
||||
track_activation_threshold: float = 0.35,
|
||||
track_seconds: int = 5,
|
||||
match_threshold: float = 0.99,
|
||||
minimum_matching_threshold: float = 0.99,
|
||||
) -> None:
|
||||
### instantiate model
|
||||
model = YOLO(source_weights_path)
|
||||
@@ -47,9 +47,9 @@ def heatmap_and_track(
|
||||
|
||||
### tracker config
|
||||
byte_tracker = sv.ByteTrack(
|
||||
track_thresh=track_threshold,
|
||||
track_buffer=track_seconds * fps,
|
||||
match_thresh=match_threshold,
|
||||
track_activation_threshold=track_activation_threshold,
|
||||
lost_track_buffer=track_seconds * fps,
|
||||
minimum_matching_threshold=minimum_matching_threshold,
|
||||
frame_rate=fps,
|
||||
)
|
||||
|
||||
@@ -175,7 +175,7 @@ if __name__ == "__main__":
|
||||
iou_threshold=args.iou_threshold,
|
||||
heatmap_alpha=args.heatmap_alpha,
|
||||
radius=args.radius,
|
||||
track_threshold=args.track_threshold,
|
||||
track_activation_threshold=args.track_threshold,
|
||||
track_seconds=args.track_seconds,
|
||||
match_threshold=args.match_threshold,
|
||||
minimum_matching_threshold=args.match_threshold,
|
||||
)
|
||||
|
||||
@@ -95,14 +95,14 @@ if __name__ == "__main__":
|
||||
model = get_roboflow_model(model_id=args.model_id, api_key=args.roboflow_api_key)
|
||||
|
||||
byte_track = sv.ByteTrack(
|
||||
frame_rate=video_info.fps, track_thresh=args.confidence_threshold
|
||||
frame_rate=video_info.fps, track_activation_threshold=args.confidence_threshold
|
||||
)
|
||||
|
||||
thickness = sv.calculate_optimal_line_thickness(
|
||||
resolution_wh=video_info.resolution_wh
|
||||
)
|
||||
text_scale = sv.calculate_optimal_text_scale(resolution_wh=video_info.resolution_wh)
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator(thickness=thickness)
|
||||
box_annotator = sv.BoxAnnotator(thickness=thickness)
|
||||
label_annotator = sv.LabelAnnotator(
|
||||
text_scale=text_scale,
|
||||
text_thickness=thickness,
|
||||
@@ -154,7 +154,7 @@ if __name__ == "__main__":
|
||||
annotated_frame = trace_annotator.annotate(
|
||||
scene=annotated_frame, detections=detections
|
||||
)
|
||||
annotated_frame = bounding_box_annotator.annotate(
|
||||
annotated_frame = box_annotator.annotate(
|
||||
scene=annotated_frame, detections=detections
|
||||
)
|
||||
annotated_frame = label_annotator.annotate(
|
||||
|
||||
@@ -73,14 +73,14 @@ if __name__ == "__main__":
|
||||
model = YOLO("yolov8x.pt")
|
||||
|
||||
byte_track = sv.ByteTrack(
|
||||
frame_rate=video_info.fps, track_thresh=args.confidence_threshold
|
||||
frame_rate=video_info.fps, track_activation_threshold=args.confidence_threshold
|
||||
)
|
||||
|
||||
thickness = sv.calculate_optimal_line_thickness(
|
||||
resolution_wh=video_info.resolution_wh
|
||||
)
|
||||
text_scale = sv.calculate_optimal_text_scale(resolution_wh=video_info.resolution_wh)
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator(thickness=thickness)
|
||||
box_annotator = sv.BoxAnnotator(thickness=thickness)
|
||||
label_annotator = sv.LabelAnnotator(
|
||||
text_scale=text_scale,
|
||||
text_thickness=thickness,
|
||||
@@ -132,7 +132,7 @@ if __name__ == "__main__":
|
||||
annotated_frame = trace_annotator.annotate(
|
||||
scene=annotated_frame, detections=detections
|
||||
)
|
||||
annotated_frame = bounding_box_annotator.annotate(
|
||||
annotated_frame = box_annotator.annotate(
|
||||
scene=annotated_frame, detections=detections
|
||||
)
|
||||
annotated_frame = label_annotator.annotate(
|
||||
|
||||
@@ -74,14 +74,14 @@ if __name__ == "__main__":
|
||||
model = models.get(Models.YOLO_NAS_L, pretrained_weights="coco")
|
||||
|
||||
byte_track = sv.ByteTrack(
|
||||
frame_rate=video_info.fps, track_thresh=args.confidence_threshold
|
||||
frame_rate=video_info.fps, track_activation_threshold=args.confidence_threshold
|
||||
)
|
||||
|
||||
thickness = sv.calculate_optimal_line_thickness(
|
||||
resolution_wh=video_info.resolution_wh
|
||||
)
|
||||
text_scale = sv.calculate_optimal_text_scale(resolution_wh=video_info.resolution_wh)
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator(thickness=thickness)
|
||||
box_annotator = sv.BoxAnnotator(thickness=thickness)
|
||||
label_annotator = sv.LabelAnnotator(
|
||||
text_scale=text_scale,
|
||||
text_thickness=thickness,
|
||||
@@ -132,7 +132,7 @@ if __name__ == "__main__":
|
||||
annotated_frame = trace_annotator.annotate(
|
||||
scene=annotated_frame, detections=detections
|
||||
)
|
||||
annotated_frame = bounding_box_annotator.annotate(
|
||||
annotated_frame = box_annotator.annotate(
|
||||
scene=annotated_frame, detections=detections
|
||||
)
|
||||
annotated_frame = label_annotator.annotate(
|
||||
|
||||
@@ -22,7 +22,7 @@ class FPSBasedTimer:
|
||||
"""Initializes the FPSBasedTimer with the specified frames per second rate.
|
||||
|
||||
Args:
|
||||
fps (int, optional): The frame rate of the video stream. Defaults to 30.
|
||||
fps (int): The frame rate of the video stream. Defaults to 30.
|
||||
"""
|
||||
self.fps = fps
|
||||
self.frame_id = 0
|
||||
|
||||
@@ -93,7 +93,7 @@ class VideoProcessor:
|
||||
self.zones_in = initiate_polygon_zones(ZONE_IN_POLYGONS, [sv.Position.CENTER])
|
||||
self.zones_out = initiate_polygon_zones(ZONE_OUT_POLYGONS, [sv.Position.CENTER])
|
||||
|
||||
self.bounding_box_annotator = sv.BoundingBoxAnnotator(color=COLORS)
|
||||
self.box_annotator = sv.BoxAnnotator(color=COLORS)
|
||||
self.label_annotator = sv.LabelAnnotator(
|
||||
color=COLORS, text_color=sv.Color.BLACK
|
||||
)
|
||||
@@ -134,9 +134,7 @@ class VideoProcessor:
|
||||
|
||||
labels = [f"#{tracker_id}" for tracker_id in detections.tracker_id]
|
||||
annotated_frame = self.trace_annotator.annotate(annotated_frame, detections)
|
||||
annotated_frame = self.bounding_box_annotator.annotate(
|
||||
annotated_frame, detections
|
||||
)
|
||||
annotated_frame = self.box_annotator.annotate(annotated_frame, detections)
|
||||
annotated_frame = self.label_annotator.annotate(
|
||||
annotated_frame, detections, labels
|
||||
)
|
||||
|
||||
@@ -90,7 +90,7 @@ class VideoProcessor:
|
||||
self.zones_in = initiate_polygon_zones(ZONE_IN_POLYGONS, [sv.Position.CENTER])
|
||||
self.zones_out = initiate_polygon_zones(ZONE_OUT_POLYGONS, [sv.Position.CENTER])
|
||||
|
||||
self.bounding_box_annotator = sv.BoundingBoxAnnotator(color=COLORS)
|
||||
self.box_annotator = sv.BoxAnnotator(color=COLORS)
|
||||
self.label_annotator = sv.LabelAnnotator(
|
||||
color=COLORS, text_color=sv.Color.BLACK
|
||||
)
|
||||
@@ -131,9 +131,7 @@ class VideoProcessor:
|
||||
|
||||
labels = [f"#{tracker_id}" for tracker_id in detections.tracker_id]
|
||||
annotated_frame = self.trace_annotator.annotate(annotated_frame, detections)
|
||||
annotated_frame = self.bounding_box_annotator.annotate(
|
||||
annotated_frame, detections
|
||||
)
|
||||
annotated_frame = self.box_annotator.annotate(annotated_frame, detections)
|
||||
annotated_frame = self.label_annotator.annotate(
|
||||
annotated_frame, detections, labels
|
||||
)
|
||||
|
||||
+46
-48
@@ -33,7 +33,6 @@ extra_css:
|
||||
- stylesheets/extra.css
|
||||
- stylesheets/cookbooks-card.css
|
||||
|
||||
|
||||
nav:
|
||||
- Supervision: index.md
|
||||
- Learn:
|
||||
@@ -42,51 +41,53 @@ nav:
|
||||
- Filter Detections: how_to/filter_detections.md
|
||||
- Detect Small Objects: how_to/detect_small_objects.md
|
||||
- Track Objects on Video: how_to/track_objects.md
|
||||
- Process Datasets: how_to/process_datasets.md
|
||||
|
||||
- Reference - Code API:
|
||||
- Detection and Segmentation:
|
||||
- Core: detection/core.md
|
||||
- Annotators: detection/annotators.md
|
||||
- Metrics: detection/metrics.md
|
||||
- Double Detection Filter: detection/double_detection_filter.md
|
||||
- Utils: detection/utils.md
|
||||
- Keypoint Detection:
|
||||
- Core: keypoint/core.md
|
||||
- Annotators: keypoint/annotators.md
|
||||
- Classification:
|
||||
- Core: classification/core.md
|
||||
- Tools:
|
||||
- Line Zone: detection/tools/line_zone.md
|
||||
- Polygon Zone: detection/tools/polygon_zone.md
|
||||
- Inference Slicer: detection/tools/inference_slicer.md
|
||||
- Detection Smoother: detection/tools/smoother.md
|
||||
- Save Detections: detection/tools/save_detections.md
|
||||
- Trackers: trackers.md
|
||||
- Datasets:
|
||||
- Core: datasets/core.md
|
||||
- Utils: datasets/utils.md
|
||||
- Utils:
|
||||
- Video: utils/video.md
|
||||
- Image: utils/image.md
|
||||
- Iterables: utils/iterables.md
|
||||
- Notebook: utils/notebook.md
|
||||
- File: utils/file.md
|
||||
- Draw: utils/draw.md
|
||||
- Geometry: utils/geometry.md
|
||||
- Assets: assets.md
|
||||
- Detection and Segmentation:
|
||||
- Core: detection/core.md
|
||||
- Annotators: detection/annotators.md
|
||||
- Double Detection Filter: detection/double_detection_filter.md
|
||||
- Utils: detection/utils.md
|
||||
- Keypoint Detection:
|
||||
- Core: keypoint/core.md
|
||||
- Annotators: keypoint/annotators.md
|
||||
- Classification:
|
||||
- Core: classification/core.md
|
||||
- Tools:
|
||||
- Line Zone: detection/tools/line_zone.md
|
||||
- Polygon Zone: detection/tools/polygon_zone.md
|
||||
- Inference Slicer: detection/tools/inference_slicer.md
|
||||
- Detection Smoother: detection/tools/smoother.md
|
||||
- Save Detections: detection/tools/save_detections.md
|
||||
- Trackers: trackers.md
|
||||
- Datasets:
|
||||
- Core: datasets/core.md
|
||||
- Utils: datasets/utils.md
|
||||
- Metrics:
|
||||
- mAP: metrics/mean_average_precision.md
|
||||
- Legacy Metrics: detection/metrics.md
|
||||
- Utils:
|
||||
- Video: utils/video.md
|
||||
- Image: utils/image.md
|
||||
- Iterables: utils/iterables.md
|
||||
- Notebook: utils/notebook.md
|
||||
- File: utils/file.md
|
||||
- Draw: utils/draw.md
|
||||
- Geometry: utils/geometry.md
|
||||
- Assets: assets.md
|
||||
- Cookbooks: cookbooks.md
|
||||
- Cheatsheet: https://roboflow.github.io/cheatsheet-supervision/
|
||||
- Contribute:
|
||||
- Contributing: contributing.md
|
||||
- Code of Conduct: code_of_conduct.md
|
||||
- License: license.md
|
||||
- Contributing: contributing.md
|
||||
- Code of Conduct: code_of_conduct.md
|
||||
- License: license.md
|
||||
- Release Notes:
|
||||
- Changelog: changelog.md
|
||||
- Deprecated: deprecated.md
|
||||
|
||||
|
||||
- Changelog: changelog.md
|
||||
- Deprecated: deprecated.md
|
||||
|
||||
theme:
|
||||
name: 'material'
|
||||
name: "material"
|
||||
icon:
|
||||
edit: material/pencil
|
||||
logo: assets/supervision-lenny.png
|
||||
@@ -103,19 +104,18 @@ theme:
|
||||
palette:
|
||||
# Palette for light mode
|
||||
- scheme: default
|
||||
primary: 'custom'
|
||||
primary: "custom"
|
||||
toggle:
|
||||
icon: material/brightness-7
|
||||
name: Switch to dark mode
|
||||
|
||||
# Palette toggle for dark mode
|
||||
- scheme: slate
|
||||
primary: 'custom'
|
||||
primary: "custom"
|
||||
toggle:
|
||||
icon: material/brightness-4
|
||||
name: Switch to light mode
|
||||
|
||||
|
||||
font:
|
||||
text: Roboto
|
||||
code: Roboto Mono
|
||||
@@ -126,10 +126,10 @@ theme:
|
||||
plugins:
|
||||
- search
|
||||
- mkdocs-jupyter:
|
||||
kernel_name: python3
|
||||
execute: false
|
||||
include_source: True
|
||||
include_requirejs: true
|
||||
kernel_name: python3
|
||||
execute: false
|
||||
include_source: True
|
||||
include_requirejs: true
|
||||
- mkdocstrings:
|
||||
default_handler: python
|
||||
handlers:
|
||||
@@ -153,8 +153,6 @@ plugins:
|
||||
- git-revision-date-localized:
|
||||
enable_creation_date: true
|
||||
|
||||
|
||||
|
||||
markdown_extensions:
|
||||
- admonition
|
||||
- pymdownx.details
|
||||
|
||||
Generated
+1035
-841
File diff suppressed because it is too large
Load Diff
+89
-23
@@ -1,18 +1,26 @@
|
||||
[tool.poetry]
|
||||
name = "supervision"
|
||||
version = "0.22.0rc1"
|
||||
version = "0.24.0rc1"
|
||||
description = "A set of easy-to-use utils that will come in handy in any Computer Vision project"
|
||||
authors = ["Piotr Skalski <piotr.skalski92@gmail.com>"]
|
||||
maintainers = ["Piotr Skalski <piotr.skalski92@gmail.com>"]
|
||||
readme = "README.md"
|
||||
license = "MIT"
|
||||
packages = [{include = "supervision"}]
|
||||
packages = [{ include = "supervision" }]
|
||||
homepage = "https://github.com/roboflow/supervision"
|
||||
repository = "https://github.com/roboflow/supervision"
|
||||
documentation = "https://github.com/roboflow/supervision/blob/main/README.md"
|
||||
keywords = ["machine-learning", "deep-learning", "vision", "ML", "DL", "AI", "Roboflow"]
|
||||
keywords = [
|
||||
"machine-learning",
|
||||
"deep-learning",
|
||||
"vision",
|
||||
"ML",
|
||||
"DL",
|
||||
"AI",
|
||||
"Roboflow",
|
||||
]
|
||||
|
||||
classifiers=[
|
||||
classifiers = [
|
||||
'Development Status :: 4 - Beta',
|
||||
'Intended Audience :: Developers',
|
||||
'Intended Audience :: Education',
|
||||
@@ -27,33 +35,40 @@ classifiers=[
|
||||
'Typing :: Typed',
|
||||
'Operating System :: Microsoft :: Windows',
|
||||
'Operating System :: POSIX :: Linux',
|
||||
'Operating System :: MacOS'
|
||||
'Operating System :: MacOS',
|
||||
]
|
||||
|
||||
[tool.poetry.dependencies]
|
||||
python = "^3.8"
|
||||
numpy = ">=1.21.2"
|
||||
numpy = [
|
||||
{ version = ">=1.21.2,<1.23.3", python = "<=3.10" },
|
||||
{ version = ">=1.23.3", python = ">3.10" },
|
||||
]
|
||||
scipy = [
|
||||
{ version = "1.10.0", python = "<3.9" },
|
||||
{ version = "^1.10.0", python = ">=3.9" }
|
||||
{ version = "^1.10.0", python = ">=3.9" },
|
||||
]
|
||||
matplotlib = ">=3.6.0"
|
||||
pyyaml = ">=5.3"
|
||||
defusedxml = "^0.7.1"
|
||||
pillow = ">=9.4"
|
||||
opencv-python = { version = ">=4.5.5.64", optional = true }
|
||||
opencv-python-headless = ">=4.5.5.64"
|
||||
requests = { version = ">=2.26.0,<=2.32.3", optional = true }
|
||||
tqdm = { version = ">=4.62.3,<=4.66.4", optional = true }
|
||||
pillow = ">=9.4"
|
||||
tqdm = { version = ">=4.62.3,<=4.66.5", optional = true }
|
||||
# pandas: picked lowest major version that supports Python 3.8
|
||||
pandas = { version = ">=2.0.0", optional = true }
|
||||
pandas-stubs = { version = ">=2.0.0.230412", optional = true }
|
||||
|
||||
[tool.poetry.extras]
|
||||
desktop = ["opencv-python"]
|
||||
assets = ["requests","tqdm"]
|
||||
assets = ["requests", "tqdm"]
|
||||
metrics = ["pandas", "pandas-stubs"]
|
||||
|
||||
[tool.poetry.group.dev.dependencies]
|
||||
twine = "^5.1.1"
|
||||
pytest = ">=7.2.2,<9.0.0"
|
||||
wheel = ">=0.40,<0.44"
|
||||
wheel = ">=0.40,<0.45"
|
||||
build = ">=0.10,<1.3"
|
||||
ruff = ">=0.1.0"
|
||||
mypy = "^1.4.1"
|
||||
@@ -65,13 +80,12 @@ jupytext = "^1.16.1"
|
||||
nbconvert = "^7.14.2"
|
||||
docutils = [
|
||||
{ version = "^0.20.1", python = "<3.9" },
|
||||
{ version = "^0.21.1", python = ">=3.9" }
|
||||
{ version = "^0.21.1", python = ">=3.9" },
|
||||
]
|
||||
|
||||
|
||||
[tool.poetry.group.docs.dependencies]
|
||||
mkdocs-material = {extras = ["imaging"], version = "^9.5.5"}
|
||||
mkdocstrings = {extras = ["python"], version = ">=0.20,<0.26"}
|
||||
mkdocs-material = { extras = ["imaging"], version = "^9.5.5" }
|
||||
mkdocstrings = { extras = ["python"], version = ">=0.25.2,<0.27.0" }
|
||||
mike = "^2.0.0"
|
||||
# For Documentation Development use Python 3.10 or above
|
||||
# Use Latest mkdocs-jupyter min 0.24.6 for Jupyter Notebook Theme support
|
||||
@@ -79,11 +93,15 @@ mkdocs-jupyter = "^0.24.3"
|
||||
mkdocs-git-committers-plugin-2 = "^2.2.3"
|
||||
mkdocs-git-revision-date-localized-plugin = "^1.2.4"
|
||||
|
||||
[tool.poetry.group.typecheck]
|
||||
optional = true
|
||||
|
||||
[tool.poetry.group.typecheck.dependencies]
|
||||
types-pyyaml = "^6.0.12.20240808"
|
||||
types-cffi = "^1.16.0.20240331"
|
||||
types-requests = "^2.32.0.20240712"
|
||||
types-tqdm = "^4.66.0.20240417"
|
||||
|
||||
[tool.isort]
|
||||
line_length = 88
|
||||
profile = "black"
|
||||
|
||||
[tool.bandit]
|
||||
target = ["test", "supervision"]
|
||||
@@ -93,7 +111,6 @@ tests = ["B201", "B301", "B318", "B314", "B303", "B413", "B412", "B410"]
|
||||
check = true
|
||||
imports = ["cv2", "supervision"]
|
||||
|
||||
|
||||
[tool.black]
|
||||
target-version = ["py38"]
|
||||
line-length = 88
|
||||
@@ -149,10 +166,55 @@ indent-width = 4
|
||||
|
||||
[tool.ruff.lint]
|
||||
# Enable pycodestyle (`E`) and Pyflakes (`F`) codes by default.
|
||||
select = ["E", "F"]
|
||||
select = ["E", "F", "I", "A", "Q", "W"]
|
||||
ignore = []
|
||||
# Allow autofix for all enabled rules (when `--fix`) is provided.
|
||||
fixable = ["A", "B", "C", "D", "E", "F", "G", "I", "N", "Q", "S", "T", "W", "ANN", "ARG", "BLE", "COM", "DJ", "DTZ", "EM", "ERA", "EXE", "FBT", "ICN", "INP", "ISC", "NPY", "PD", "PGH", "PIE", "PL", "PT", "PTH", "PYI", "RET", "RSE", "RUF", "SIM", "SLF", "TCH", "TID", "TRY", "UP", "YTT"]
|
||||
fixable = [
|
||||
"A",
|
||||
"B",
|
||||
"C",
|
||||
"D",
|
||||
"E",
|
||||
"F",
|
||||
"G",
|
||||
"I",
|
||||
"N",
|
||||
"Q",
|
||||
"S",
|
||||
"T",
|
||||
"W",
|
||||
"ANN",
|
||||
"ARG",
|
||||
"BLE",
|
||||
"COM",
|
||||
"DJ",
|
||||
"DTZ",
|
||||
"EM",
|
||||
"ERA",
|
||||
"EXE",
|
||||
"FBT",
|
||||
"ICN",
|
||||
"INP",
|
||||
"ISC",
|
||||
"NPY",
|
||||
"PD",
|
||||
"PGH",
|
||||
"PIE",
|
||||
"PL",
|
||||
"PT",
|
||||
"PTH",
|
||||
"PYI",
|
||||
"RET",
|
||||
"RSE",
|
||||
"RUF",
|
||||
"SIM",
|
||||
"SLF",
|
||||
"TCH",
|
||||
"TID",
|
||||
"TRY",
|
||||
"UP",
|
||||
"YTT",
|
||||
]
|
||||
unfixable = []
|
||||
# Allow unused variables when underscore-prefixed.
|
||||
dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
|
||||
@@ -167,12 +229,16 @@ docstring-quotes = "double"
|
||||
convention = "google"
|
||||
|
||||
[tool.ruff.lint.per-file-ignores]
|
||||
"__init__.py" = ["E402","F401"]
|
||||
"__init__.py" = ["E402", "F401"]
|
||||
|
||||
[tool.ruff.lint.mccabe]
|
||||
# Flag errors (`C901`) whenever the complexity level exceeds 5.
|
||||
max-complexity = 20
|
||||
|
||||
[tool.ruff.lint.isort]
|
||||
order-by-type = true
|
||||
no-sections = false
|
||||
|
||||
[tool.ruff.format]
|
||||
# Like Black, use double quotes for strings.
|
||||
quote-style = "double"
|
||||
@@ -190,7 +256,7 @@ line-ending = "auto"
|
||||
include-package-data = false
|
||||
|
||||
[tool.setuptools.packages.find]
|
||||
exclude = ["docs*", "test*","examples*"]
|
||||
exclude = ["docs*", "test*", "examples*"]
|
||||
|
||||
[build-system]
|
||||
requires = ["poetry-core"]
|
||||
|
||||
@@ -0,0 +1,24 @@
|
||||
# Release Process
|
||||
|
||||
This doc outlines how supervision is released into production.
|
||||
|
||||
It assumes you already have the code changes, as well as a draft of the release notes.
|
||||
|
||||
1. Make sure you have all required changes were merged into `develop`.
|
||||
2. Create and merge a PR, merging `develop` into `main`, containing:
|
||||
- A commit that updates the project version in `pyproject.toml`.
|
||||
- All changes made during the release.
|
||||
3. Tag the commit with the new supervision version.
|
||||
- make sure to pull from `main` !
|
||||
- Verify that the latest merge commits exists. `git log`.
|
||||
- Run `git tag x.y.z`, with your version
|
||||
- Check with `git log`.
|
||||
- Run `git push origin --tags`
|
||||
- Upon pushing the tag, the [PyPi](https://pypi.org/project/supervision/) should update to the new version. Check this!
|
||||
4. Open and merge a PR, merging `main` into `develop`.
|
||||
5. Update the docs by running the [Supervision Release Documentation Workflow 📚](https://github.com/roboflow/supervision/actions/workflows/publish-release-docs.yml) workflow from GitHub.
|
||||
- Select the `main` branch from the dropdown.
|
||||
6. Create a release on GitHub.
|
||||
- Go to releases
|
||||
- Assign the release notes to the tag created in step 3.
|
||||
- Publish the release.
|
||||
@@ -7,8 +7,10 @@ except importlib_metadata.PackageNotFoundError:
|
||||
__version__ = "development"
|
||||
|
||||
from supervision.annotators.core import (
|
||||
BackgroundOverlayAnnotator,
|
||||
BlurAnnotator,
|
||||
BoundingBoxAnnotator,
|
||||
BoxAnnotator,
|
||||
BoxCornerAnnotator,
|
||||
CircleAnnotator,
|
||||
ColorAnnotator,
|
||||
@@ -17,6 +19,7 @@ from supervision.annotators.core import (
|
||||
EllipseAnnotator,
|
||||
HaloAnnotator,
|
||||
HeatMapAnnotator,
|
||||
IconAnnotator,
|
||||
LabelAnnotator,
|
||||
MaskAnnotator,
|
||||
OrientedBoxAnnotator,
|
||||
@@ -36,7 +39,6 @@ from supervision.dataset.core import (
|
||||
DetectionDataset,
|
||||
)
|
||||
from supervision.dataset.utils import mask_to_rle, rle_to_mask
|
||||
from supervision.detection.annotate import BoxAnnotator
|
||||
from supervision.detection.core import Detections
|
||||
from supervision.detection.line_zone import LineZone, LineZoneAnnotator
|
||||
from supervision.detection.lmm import LMM
|
||||
@@ -67,6 +69,8 @@ from supervision.detection.utils import (
|
||||
polygon_to_mask,
|
||||
polygon_to_xyxy,
|
||||
scale_boxes,
|
||||
xcycwh_to_xyxy,
|
||||
xywh_to_xyxy,
|
||||
)
|
||||
from supervision.draw.color import Color, ColorPalette
|
||||
from supervision.draw.utils import (
|
||||
|
||||
+426
-54
@@ -1,9 +1,11 @@
|
||||
from functools import lru_cache
|
||||
from math import sqrt
|
||||
from typing import List, Optional, Tuple, Union
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
from PIL import ImageDraw, ImageFont
|
||||
import numpy.typing as npt
|
||||
from PIL import Image, ImageDraw, ImageFont
|
||||
|
||||
from supervision.annotators.base import BaseAnnotator, ImageType
|
||||
from supervision.annotators.utils import (
|
||||
@@ -22,9 +24,101 @@ from supervision.utils.conversion import (
|
||||
ensure_cv2_image_for_annotation,
|
||||
ensure_pil_image_for_annotation,
|
||||
)
|
||||
from supervision.utils.image import crop_image, overlay_image, scale_image
|
||||
from supervision.utils.image import (
|
||||
crop_image,
|
||||
letterbox_image,
|
||||
overlay_image,
|
||||
scale_image,
|
||||
)
|
||||
from supervision.utils.internal import deprecated
|
||||
|
||||
|
||||
class BoxAnnotator(BaseAnnotator):
|
||||
"""
|
||||
A class for drawing bounding boxes on an image using provided detections.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
color: Union[Color, ColorPalette] = ColorPalette.DEFAULT,
|
||||
thickness: int = 2,
|
||||
color_lookup: ColorLookup = ColorLookup.CLASS,
|
||||
):
|
||||
"""
|
||||
Args:
|
||||
color (Union[Color, ColorPalette]): The color or color palette to use for
|
||||
annotating detections.
|
||||
thickness (int): Thickness of the bounding box lines.
|
||||
color_lookup (ColorLookup): Strategy for mapping colors to annotations.
|
||||
Options are `INDEX`, `CLASS`, `TRACK`.
|
||||
"""
|
||||
self.color: Union[Color, ColorPalette] = color
|
||||
self.thickness: int = thickness
|
||||
self.color_lookup: ColorLookup = color_lookup
|
||||
|
||||
@ensure_cv2_image_for_annotation
|
||||
def annotate(
|
||||
self,
|
||||
scene: ImageType,
|
||||
detections: Detections,
|
||||
custom_color_lookup: Optional[np.ndarray] = None,
|
||||
) -> ImageType:
|
||||
"""
|
||||
Annotates the given scene with bounding boxes based on the provided detections.
|
||||
|
||||
Args:
|
||||
scene (ImageType): The image where bounding boxes will be drawn. `ImageType`
|
||||
is a flexible type, accepting either `numpy.ndarray` or `PIL.Image.Image`.
|
||||
detections (Detections): Object detections to annotate.
|
||||
custom_color_lookup (Optional[np.ndarray]): Custom color lookup array.
|
||||
Allows to override the default color mapping strategy.
|
||||
|
||||
Returns:
|
||||
The annotated image, matching the type of `scene` (`numpy.ndarray`
|
||||
or `PIL.Image.Image`)
|
||||
|
||||
Example:
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
image = ...
|
||||
detections = sv.Detections(...)
|
||||
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
annotated_frame = box_annotator.annotate(
|
||||
scene=image.copy(),
|
||||
detections=detections
|
||||
)
|
||||
```
|
||||
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
for detection_idx in range(len(detections)):
|
||||
x1, y1, x2, y2 = detections.xyxy[detection_idx].astype(int)
|
||||
color = resolve_color(
|
||||
color=self.color,
|
||||
detections=detections,
|
||||
detection_idx=detection_idx,
|
||||
color_lookup=self.color_lookup
|
||||
if custom_color_lookup is None
|
||||
else custom_color_lookup,
|
||||
)
|
||||
cv2.rectangle(
|
||||
img=scene,
|
||||
pt1=(x1, y1),
|
||||
pt2=(x2, y2),
|
||||
color=color.as_bgr(),
|
||||
thickness=self.thickness,
|
||||
)
|
||||
return scene
|
||||
|
||||
|
||||
@deprecated(
|
||||
"`BoundingBoxAnnotator` is deprecated and has been renamed to `BoxAnnotator`."
|
||||
" `BoundingBoxAnnotator` will be removed in supervision-0.26.0."
|
||||
)
|
||||
class BoundingBoxAnnotator(BaseAnnotator):
|
||||
"""
|
||||
A class for drawing bounding boxes on an image using provided detections.
|
||||
@@ -41,7 +135,7 @@ class BoundingBoxAnnotator(BaseAnnotator):
|
||||
color (Union[Color, ColorPalette]): The color or color palette to use for
|
||||
annotating detections.
|
||||
thickness (int): Thickness of the bounding box lines.
|
||||
color_lookup (str): Strategy for mapping colors to annotations.
|
||||
color_lookup (ColorLookup): Strategy for mapping colors to annotations.
|
||||
Options are `INDEX`, `CLASS`, `TRACK`.
|
||||
"""
|
||||
self.color: Union[Color, ColorPalette] = color
|
||||
@@ -86,6 +180,7 @@ class BoundingBoxAnnotator(BaseAnnotator):
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
for detection_idx in range(len(detections)):
|
||||
x1, y1, x2, y2 = detections.xyxy[detection_idx].astype(int)
|
||||
color = resolve_color(
|
||||
@@ -122,7 +217,7 @@ class OrientedBoxAnnotator(BaseAnnotator):
|
||||
color (Union[Color, ColorPalette]): The color or color palette to use for
|
||||
annotating detections.
|
||||
thickness (int): Thickness of the bounding box lines.
|
||||
color_lookup (str): Strategy for mapping colors to annotations.
|
||||
color_lookup (ColorLookup): Strategy for mapping colors to annotations.
|
||||
Options are `INDEX`, `CLASS`, `TRACK`.
|
||||
"""
|
||||
self.color: Union[Color, ColorPalette] = color
|
||||
@@ -170,12 +265,13 @@ class OrientedBoxAnnotator(BaseAnnotator):
|
||||
)
|
||||
```
|
||||
""" # noqa E501 // docs
|
||||
|
||||
assert isinstance(scene, np.ndarray)
|
||||
if detections.data is None or ORIENTED_BOX_COORDINATES not in detections.data:
|
||||
return scene
|
||||
obb_boxes = np.array(detections.data[ORIENTED_BOX_COORDINATES]).astype(int)
|
||||
|
||||
for detection_idx in range(len(detections)):
|
||||
bbox = np.intp(detections.data.get(ORIENTED_BOX_COORDINATES)[detection_idx])
|
||||
obb = obb_boxes[detection_idx]
|
||||
color = resolve_color(
|
||||
color=self.color,
|
||||
detections=detections,
|
||||
@@ -185,7 +281,7 @@ class OrientedBoxAnnotator(BaseAnnotator):
|
||||
else custom_color_lookup,
|
||||
)
|
||||
|
||||
cv2.drawContours(scene, [bbox], 0, color.as_bgr(), self.thickness)
|
||||
cv2.drawContours(scene, [obb], 0, color.as_bgr(), self.thickness)
|
||||
|
||||
return scene
|
||||
|
||||
@@ -210,7 +306,7 @@ class MaskAnnotator(BaseAnnotator):
|
||||
color (Union[Color, ColorPalette]): The color or color palette to use for
|
||||
annotating detections.
|
||||
opacity (float): Opacity of the overlay mask. Must be between `0` and `1`.
|
||||
color_lookup (str): Strategy for mapping colors to annotations.
|
||||
color_lookup (ColorLookup): Strategy for mapping colors to annotations.
|
||||
Options are `INDEX`, `CLASS`, `TRACK`.
|
||||
"""
|
||||
self.color: Union[Color, ColorPalette] = color
|
||||
@@ -256,6 +352,7 @@ class MaskAnnotator(BaseAnnotator):
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
if detections.mask is None:
|
||||
return scene
|
||||
|
||||
@@ -299,7 +396,7 @@ class PolygonAnnotator(BaseAnnotator):
|
||||
color (Union[Color, ColorPalette]): The color or color palette to use for
|
||||
annotating detections.
|
||||
thickness (int): Thickness of the polygon lines.
|
||||
color_lookup (str): Strategy for mapping colors to annotations.
|
||||
color_lookup (ColorLookup): Strategy for mapping colors to annotations.
|
||||
Options are `INDEX`, `CLASS`, `TRACK`.
|
||||
"""
|
||||
self.color: Union[Color, ColorPalette] = color
|
||||
@@ -345,6 +442,7 @@ class PolygonAnnotator(BaseAnnotator):
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
if detections.mask is None:
|
||||
return scene
|
||||
|
||||
@@ -385,7 +483,7 @@ class ColorAnnotator(BaseAnnotator):
|
||||
color (Union[Color, ColorPalette]): The color or color palette to use for
|
||||
annotating detections.
|
||||
opacity (float): Opacity of the overlay mask. Must be between `0` and `1`.
|
||||
color_lookup (str): Strategy for mapping colors to annotations.
|
||||
color_lookup (ColorLookup): Strategy for mapping colors to annotations.
|
||||
Options are `INDEX`, `CLASS`, `TRACK`.
|
||||
"""
|
||||
self.color: Union[Color, ColorPalette] = color
|
||||
@@ -431,6 +529,7 @@ class ColorAnnotator(BaseAnnotator):
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
scene_with_boxes = scene.copy()
|
||||
for detection_idx in range(len(detections)):
|
||||
x1, y1, x2, y2 = detections.xyxy[detection_idx].astype(int)
|
||||
@@ -479,7 +578,7 @@ class HaloAnnotator(BaseAnnotator):
|
||||
opacity (float): Opacity of the overlay mask. Must be between `0` and `1`.
|
||||
kernel_size (int): The size of the average pooling kernel used for creating
|
||||
the halo.
|
||||
color_lookup (str): Strategy for mapping colors to annotations.
|
||||
color_lookup (ColorLookup): Strategy for mapping colors to annotations.
|
||||
Options are `INDEX`, `CLASS`, `TRACK`.
|
||||
"""
|
||||
self.color: Union[Color, ColorPalette] = color
|
||||
@@ -526,6 +625,7 @@ class HaloAnnotator(BaseAnnotator):
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
if detections.mask is None:
|
||||
return scene
|
||||
colored_mask = np.zeros_like(scene, dtype=np.uint8)
|
||||
@@ -577,7 +677,7 @@ class EllipseAnnotator(BaseAnnotator):
|
||||
thickness (int): Thickness of the ellipse lines.
|
||||
start_angle (int): Starting angle of the ellipse.
|
||||
end_angle (int): Ending angle of the ellipse.
|
||||
color_lookup (str): Strategy for mapping colors to annotations.
|
||||
color_lookup (ColorLookup): Strategy for mapping colors to annotations.
|
||||
Options are `INDEX`, `CLASS`, `TRACK`.
|
||||
"""
|
||||
self.color: Union[Color, ColorPalette] = color
|
||||
@@ -625,6 +725,7 @@ class EllipseAnnotator(BaseAnnotator):
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
for detection_idx in range(len(detections)):
|
||||
x1, y1, x2, y2 = detections.xyxy[detection_idx].astype(int)
|
||||
color = resolve_color(
|
||||
@@ -669,7 +770,7 @@ class BoxCornerAnnotator(BaseAnnotator):
|
||||
annotating detections.
|
||||
thickness (int): Thickness of the corner lines.
|
||||
corner_length (int): Length of each corner line.
|
||||
color_lookup (str): Strategy for mapping colors to annotations.
|
||||
color_lookup (ColorLookup): Strategy for mapping colors to annotations.
|
||||
Options are `INDEX`, `CLASS`, `TRACK`.
|
||||
"""
|
||||
self.color: Union[Color, ColorPalette] = color
|
||||
@@ -716,6 +817,7 @@ class BoxCornerAnnotator(BaseAnnotator):
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
for detection_idx in range(len(detections)):
|
||||
x1, y1, x2, y2 = detections.xyxy[detection_idx].astype(int)
|
||||
color = resolve_color(
|
||||
@@ -757,7 +859,7 @@ class CircleAnnotator(BaseAnnotator):
|
||||
color (Union[Color, ColorPalette]): The color or color palette to use for
|
||||
annotating detections.
|
||||
thickness (int): Thickness of the circle line.
|
||||
color_lookup (str): Strategy for mapping colors to annotations.
|
||||
color_lookup (ColorLookup): Strategy for mapping colors to annotations.
|
||||
Options are `INDEX`, `CLASS`, `TRACK`.
|
||||
"""
|
||||
|
||||
@@ -805,6 +907,7 @@ class CircleAnnotator(BaseAnnotator):
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
for detection_idx in range(len(detections)):
|
||||
x1, y1, x2, y2 = detections.xyxy[detection_idx].astype(int)
|
||||
center = ((x1 + x2) // 2, (y1 + y2) // 2)
|
||||
@@ -841,6 +944,7 @@ class DotAnnotator(BaseAnnotator):
|
||||
position: Position = Position.CENTER,
|
||||
color_lookup: ColorLookup = ColorLookup.CLASS,
|
||||
outline_thickness: int = 0,
|
||||
outline_color: Union[Color, ColorPalette] = Color.BLACK,
|
||||
):
|
||||
"""
|
||||
Args:
|
||||
@@ -851,12 +955,16 @@ class DotAnnotator(BaseAnnotator):
|
||||
color_lookup (ColorLookup): Strategy for mapping colors to annotations.
|
||||
Options are `INDEX`, `CLASS`, `TRACK`.
|
||||
outline_thickness (int): Thickness of the outline of the dot.
|
||||
outline_color (Union[Color, ColorPalette]): The color or color palette to
|
||||
use for outline. It is activated by setting outline_thickness to a value
|
||||
greater than 0.
|
||||
"""
|
||||
self.color: Union[Color, ColorPalette] = color
|
||||
self.radius: int = radius
|
||||
self.position: Position = position
|
||||
self.color_lookup: ColorLookup = color_lookup
|
||||
self.outline_thickness = outline_thickness
|
||||
self.outline_color: Union[Color, ColorPalette] = outline_color
|
||||
|
||||
@ensure_cv2_image_for_annotation
|
||||
def annotate(
|
||||
@@ -897,6 +1005,7 @@ class DotAnnotator(BaseAnnotator):
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
xy = detections.get_anchors_coordinates(anchor=self.position)
|
||||
for detection_idx in range(len(detections)):
|
||||
color = resolve_color(
|
||||
@@ -911,8 +1020,20 @@ class DotAnnotator(BaseAnnotator):
|
||||
|
||||
cv2.circle(scene, center, self.radius, color.as_bgr(), -1)
|
||||
if self.outline_thickness:
|
||||
outline_color = resolve_color(
|
||||
color=self.outline_color,
|
||||
detections=detections,
|
||||
detection_idx=detection_idx,
|
||||
color_lookup=self.color_lookup
|
||||
if custom_color_lookup is None
|
||||
else custom_color_lookup,
|
||||
)
|
||||
cv2.circle(
|
||||
scene, center, self.radius, (0, 0, 0), self.outline_thickness
|
||||
scene,
|
||||
center,
|
||||
self.radius,
|
||||
outline_color.as_bgr(),
|
||||
self.outline_thickness,
|
||||
)
|
||||
return scene
|
||||
|
||||
@@ -925,7 +1046,7 @@ class LabelAnnotator(BaseAnnotator):
|
||||
def __init__(
|
||||
self,
|
||||
color: Union[Color, ColorPalette] = ColorPalette.DEFAULT,
|
||||
text_color: Color = Color.WHITE,
|
||||
text_color: Union[Color, ColorPalette] = Color.WHITE,
|
||||
text_scale: float = 0.5,
|
||||
text_thickness: int = 1,
|
||||
text_padding: int = 10,
|
||||
@@ -937,20 +1058,21 @@ class LabelAnnotator(BaseAnnotator):
|
||||
Args:
|
||||
color (Union[Color, ColorPalette]): The color or color palette to use for
|
||||
annotating the text background.
|
||||
text_color (Color): The color to use for the text.
|
||||
text_color (Union[Color, ColorPalette]): The color or color palette to use
|
||||
for the text.
|
||||
text_scale (float): Font scale for the text.
|
||||
text_thickness (int): Thickness of the text characters.
|
||||
text_padding (int): Padding around the text within its background box.
|
||||
text_position (Position): Position of the text relative to the detection.
|
||||
Possible values are defined in the `Position` enum.
|
||||
color_lookup (str): Strategy for mapping colors to annotations.
|
||||
color_lookup (ColorLookup): Strategy for mapping colors to annotations.
|
||||
Options are `INDEX`, `CLASS`, `TRACK`.
|
||||
border_radius (int): The radius to apply round edges. If the selected
|
||||
value is higher than the lower dimension, width or height, is clipped.
|
||||
"""
|
||||
self.border_radius: int = border_radius
|
||||
self.color: Union[Color, ColorPalette] = color
|
||||
self.text_color: Color = text_color
|
||||
self.text_color: Union[Color, ColorPalette] = text_color
|
||||
self.text_scale: float = text_scale
|
||||
self.text_thickness: int = text_thickness
|
||||
self.text_padding: int = text_padding
|
||||
@@ -1005,6 +1127,7 @@ class LabelAnnotator(BaseAnnotator):
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
font = cv2.FONT_HERSHEY_SIMPLEX
|
||||
anchors_coordinates = detections.get_anchors_coordinates(
|
||||
anchor=self.text_anchor
|
||||
@@ -1028,10 +1151,21 @@ class LabelAnnotator(BaseAnnotator):
|
||||
),
|
||||
)
|
||||
|
||||
text_color = resolve_color(
|
||||
color=self.text_color,
|
||||
detections=detections,
|
||||
detection_idx=detection_idx,
|
||||
color_lookup=(
|
||||
self.color_lookup
|
||||
if custom_color_lookup is None
|
||||
else custom_color_lookup
|
||||
),
|
||||
)
|
||||
|
||||
if labels is not None:
|
||||
text = labels[detection_idx]
|
||||
elif detections[CLASS_NAME_DATA_FIELD] is not None:
|
||||
text = detections[CLASS_NAME_DATA_FIELD][detection_idx]
|
||||
elif CLASS_NAME_DATA_FIELD in detections.data:
|
||||
text = detections.data[CLASS_NAME_DATA_FIELD][detection_idx]
|
||||
elif detections.class_id is not None:
|
||||
text = str(detections.class_id[detection_idx])
|
||||
else:
|
||||
@@ -1066,7 +1200,7 @@ class LabelAnnotator(BaseAnnotator):
|
||||
org=(text_x, text_y),
|
||||
fontFace=font,
|
||||
fontScale=self.text_scale,
|
||||
color=self.text_color.as_rgb(),
|
||||
color=text_color.as_bgr(),
|
||||
thickness=self.text_thickness,
|
||||
lineType=cv2.LINE_AA,
|
||||
)
|
||||
@@ -1124,7 +1258,7 @@ class RichLabelAnnotator(BaseAnnotator):
|
||||
def __init__(
|
||||
self,
|
||||
color: Union[Color, ColorPalette] = ColorPalette.DEFAULT,
|
||||
text_color: Color = Color.WHITE,
|
||||
text_color: Union[Color, ColorPalette] = Color.WHITE,
|
||||
font_path: Optional[str] = None,
|
||||
font_size: int = 10,
|
||||
text_padding: int = 10,
|
||||
@@ -1136,7 +1270,7 @@ class RichLabelAnnotator(BaseAnnotator):
|
||||
Args:
|
||||
color (Union[Color, ColorPalette]): The color or color palette to use for
|
||||
annotating the text background.
|
||||
text_color (Color): The color to use for the text.
|
||||
text_color (Union[Color, ColorPalette]): The color to use for the text.
|
||||
font_path (Optional[str]): Path to the font file (e.g., ".ttf" or ".otf")
|
||||
to use for rendering text. If `None`, the default PIL font will be used.
|
||||
font_size (int): Font size for the text.
|
||||
@@ -1210,6 +1344,7 @@ class RichLabelAnnotator(BaseAnnotator):
|
||||
```
|
||||
|
||||
"""
|
||||
assert isinstance(scene, Image.Image)
|
||||
draw = ImageDraw.Draw(scene)
|
||||
anchors_coordinates = detections.get_anchors_coordinates(
|
||||
anchor=self.text_anchor
|
||||
@@ -1231,10 +1366,22 @@ class RichLabelAnnotator(BaseAnnotator):
|
||||
else custom_color_lookup
|
||||
),
|
||||
)
|
||||
|
||||
text_color = resolve_color(
|
||||
color=self.text_color,
|
||||
detections=detections,
|
||||
detection_idx=detection_idx,
|
||||
color_lookup=(
|
||||
self.color_lookup
|
||||
if custom_color_lookup is None
|
||||
else custom_color_lookup
|
||||
),
|
||||
)
|
||||
|
||||
if labels is not None:
|
||||
text = labels[detection_idx]
|
||||
elif detections[CLASS_NAME_DATA_FIELD] is not None:
|
||||
text = detections[CLASS_NAME_DATA_FIELD][detection_idx]
|
||||
elif CLASS_NAME_DATA_FIELD in detections.data:
|
||||
text = detections.data[CLASS_NAME_DATA_FIELD][detection_idx]
|
||||
elif detections.class_id is not None:
|
||||
text = str(detections.class_id[detection_idx])
|
||||
else:
|
||||
@@ -1264,7 +1411,7 @@ class RichLabelAnnotator(BaseAnnotator):
|
||||
xy=(text_x, text_y),
|
||||
text=text,
|
||||
font=self.font,
|
||||
fill=self.text_color.as_rgb(),
|
||||
fill=text_color.as_rgb(),
|
||||
)
|
||||
return scene
|
||||
|
||||
@@ -1282,6 +1429,106 @@ class RichLabelAnnotator(BaseAnnotator):
|
||||
return font
|
||||
|
||||
|
||||
class IconAnnotator(BaseAnnotator):
|
||||
"""
|
||||
A class for drawing an icon on an image, using provided detections.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
icon_resolution_wh: Tuple[int, int] = (64, 64),
|
||||
icon_position: Position = Position.TOP_CENTER,
|
||||
offset_xy: Tuple[int, int] = (0, 0),
|
||||
):
|
||||
"""
|
||||
Args:
|
||||
icon_resolution_wh (Tuple[int, int]): The size of drawn icons.
|
||||
All icons will be resized to this resolution, keeping the aspect ratio.
|
||||
icon_position (Position): The position of the icon.
|
||||
offset_xy (Tuple[int, int]): The offset to apply to the icon position,
|
||||
in pixels. Can be both positive and negative.
|
||||
"""
|
||||
self.icon_resolution_wh = icon_resolution_wh
|
||||
self.position = icon_position
|
||||
self.offset_xy = offset_xy
|
||||
|
||||
@ensure_cv2_image_for_annotation
|
||||
def annotate(
|
||||
self, scene: ImageType, detections: Detections, icon_path: Union[str, List[str]]
|
||||
) -> ImageType:
|
||||
"""
|
||||
Annotates the given scene with given icons.
|
||||
|
||||
Args:
|
||||
scene (ImageType): The image where labels will be drawn.
|
||||
`ImageType` is a flexible type, accepting either `numpy.ndarray`
|
||||
or `PIL.Image.Image`.
|
||||
detections (Detections): Object detections to annotate.
|
||||
icon_path (Union[str, List[str]]): The path to the PNG image to use as an
|
||||
icon. Must be a single path or a list of paths, one for each detection.
|
||||
Pass an empty string `""` to draw nothing.
|
||||
|
||||
Returns:
|
||||
The annotated image, matching the type of `scene` (`numpy.ndarray`
|
||||
or `PIL.Image.Image`)
|
||||
|
||||
Example:
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
image = ...
|
||||
detections = sv.Detections(...)
|
||||
|
||||
available_icons = ["roboflow.png", "lenny.png"]
|
||||
icon_paths = [np.random.choice(available_icons) for _ in detections]
|
||||
|
||||
icon_annotator = sv.IconAnnotator()
|
||||
annotated_frame = icon_annotator.annotate(
|
||||
scene=image.copy(),
|
||||
detections=detections,
|
||||
icon_path=icon_paths
|
||||
)
|
||||
```
|
||||
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
if isinstance(icon_path, list) and len(icon_path) != len(detections):
|
||||
raise ValueError(
|
||||
f"The number of icon paths provided ({len(icon_path)}) does not match "
|
||||
f"the number of detections ({len(detections)}). Either provide a single"
|
||||
f" icon path or one for each detection."
|
||||
)
|
||||
|
||||
xy = detections.get_anchors_coordinates(anchor=self.position).astype(int)
|
||||
|
||||
for detection_idx in range(len(detections)):
|
||||
current_path = (
|
||||
icon_path if isinstance(icon_path, str) else icon_path[detection_idx]
|
||||
)
|
||||
if current_path == "":
|
||||
continue
|
||||
icon = self._load_icon(current_path)
|
||||
icon_h, icon_w = icon.shape[:2]
|
||||
|
||||
x = int(xy[detection_idx, 0] - icon_w / 2 + self.offset_xy[0])
|
||||
y = int(xy[detection_idx, 1] - icon_h / 2 + self.offset_xy[1])
|
||||
|
||||
scene[:] = overlay_image(scene, icon, (x, y))
|
||||
return scene
|
||||
|
||||
@lru_cache
|
||||
def _load_icon(self, icon_path: str) -> np.ndarray:
|
||||
icon = cv2.imread(icon_path, cv2.IMREAD_UNCHANGED)
|
||||
if icon is None:
|
||||
raise FileNotFoundError(
|
||||
f"Error: Couldn't load the icon image from {icon_path}"
|
||||
)
|
||||
icon = letterbox_image(image=icon, resolution_wh=self.icon_resolution_wh)
|
||||
return icon
|
||||
|
||||
|
||||
class BlurAnnotator(BaseAnnotator):
|
||||
"""
|
||||
A class for blurring regions in an image using provided detections.
|
||||
@@ -1330,6 +1577,7 @@ class BlurAnnotator(BaseAnnotator):
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
image_height, image_width = scene.shape[:2]
|
||||
clipped_xyxy = clip_boxes(
|
||||
xyxy=detections.xyxy, resolution_wh=(image_width, image_height)
|
||||
@@ -1371,7 +1619,7 @@ class TraceAnnotator(BaseAnnotator):
|
||||
trace_length (int): The maximum length of the trace in terms of historical
|
||||
points. Defaults to `30`.
|
||||
thickness (int): The thickness of the trace lines. Defaults to `2`.
|
||||
color_lookup (str): Strategy for mapping colors to annotations.
|
||||
color_lookup (ColorLookup): Strategy for mapping colors to annotations.
|
||||
Options are `INDEX`, `CLASS`, `TRACK`.
|
||||
"""
|
||||
self.color: Union[Color, ColorPalette] = color
|
||||
@@ -1428,8 +1676,14 @@ class TraceAnnotator(BaseAnnotator):
|
||||

|
||||
"""
|
||||
self.trace.put(detections)
|
||||
assert isinstance(scene, np.ndarray)
|
||||
if detections.tracker_id is None:
|
||||
raise ValueError(
|
||||
"The `tracker_id` field is missing in the provided detections."
|
||||
" See more: https://supervision.roboflow.com/latest/how_to/track_objects"
|
||||
)
|
||||
|
||||
self.trace.put(detections)
|
||||
for detection_idx in range(len(detections)):
|
||||
tracker_id = int(detections.tracker_id[detection_idx])
|
||||
color = resolve_color(
|
||||
@@ -1482,9 +1736,9 @@ class HeatMapAnnotator(BaseAnnotator):
|
||||
self.opacity = opacity
|
||||
self.radius = radius
|
||||
self.kernel_size = kernel_size
|
||||
self.heat_mask = None
|
||||
self.top_hue = top_hue
|
||||
self.low_hue = low_hue
|
||||
self.heat_mask: Optional[npt.NDArray[np.float32]] = None
|
||||
|
||||
@ensure_cv2_image_for_annotation
|
||||
def annotate(self, scene: ImageType, detections: Detections) -> ImageType:
|
||||
@@ -1511,7 +1765,7 @@ class HeatMapAnnotator(BaseAnnotator):
|
||||
heat_map_annotator = sv.HeatMapAnnotator()
|
||||
|
||||
video_info = sv.VideoInfo.from_video_path(video_path='...')
|
||||
frames_generator = get_video_frames_generator(source_path='...')
|
||||
frames_generator = sv.get_video_frames_generator(source_path='...')
|
||||
|
||||
with sv.VideoSink(target_path='...', video_info=video_info) as sink:
|
||||
for frame in frames_generator:
|
||||
@@ -1526,12 +1780,20 @@ class HeatMapAnnotator(BaseAnnotator):
|
||||

|
||||
"""
|
||||
|
||||
assert isinstance(scene, np.ndarray)
|
||||
if self.heat_mask is None:
|
||||
self.heat_mask = np.zeros(scene.shape[:2])
|
||||
self.heat_mask = np.zeros(scene.shape[:2], dtype=np.float32)
|
||||
|
||||
mask = np.zeros(scene.shape[:2])
|
||||
for xy in detections.get_anchors_coordinates(self.position):
|
||||
cv2.circle(mask, (int(xy[0]), int(xy[1])), self.radius, 1, -1)
|
||||
x, y = int(xy[0]), int(xy[1])
|
||||
cv2.circle(
|
||||
img=mask,
|
||||
center=(x, y),
|
||||
radius=self.radius,
|
||||
color=(1,),
|
||||
thickness=-1, # fill
|
||||
)
|
||||
self.heat_mask = mask + self.heat_mask
|
||||
temp = self.heat_mask.copy()
|
||||
temp = self.low_hue - temp / temp.max() * (self.low_hue - self.top_hue)
|
||||
@@ -1599,6 +1861,7 @@ class PixelateAnnotator(BaseAnnotator):
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
image_height, image_width = scene.shape[:2]
|
||||
clipped_xyxy = clip_boxes(
|
||||
xyxy=detections.xyxy, resolution_wh=(image_width, image_height)
|
||||
@@ -1634,6 +1897,7 @@ class TriangleAnnotator(BaseAnnotator):
|
||||
position: Position = Position.TOP_CENTER,
|
||||
color_lookup: ColorLookup = ColorLookup.CLASS,
|
||||
outline_thickness: int = 0,
|
||||
outline_color: Union[Color, ColorPalette] = Color.BLACK,
|
||||
):
|
||||
"""
|
||||
Args:
|
||||
@@ -1645,6 +1909,9 @@ class TriangleAnnotator(BaseAnnotator):
|
||||
color_lookup (ColorLookup): Strategy for mapping colors to annotations.
|
||||
Options are `INDEX`, `CLASS`, `TRACK`.
|
||||
outline_thickness (int): Thickness of the outline of the triangle.
|
||||
outline_color (Union[Color, ColorPalette]): The color or color palette to
|
||||
use for outline. It is activated by setting outline_thickness to a value
|
||||
greater than 0.
|
||||
"""
|
||||
self.color: Union[Color, ColorPalette] = color
|
||||
self.base: int = base
|
||||
@@ -1652,6 +1919,7 @@ class TriangleAnnotator(BaseAnnotator):
|
||||
self.position: Position = position
|
||||
self.color_lookup: ColorLookup = color_lookup
|
||||
self.outline_thickness: int = outline_thickness
|
||||
self.outline_color: Union[Color, ColorPalette] = outline_color
|
||||
|
||||
@ensure_cv2_image_for_annotation
|
||||
def annotate(
|
||||
@@ -1692,6 +1960,7 @@ class TriangleAnnotator(BaseAnnotator):
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
xy = detections.get_anchors_coordinates(anchor=self.position)
|
||||
for detection_idx in range(len(detections)):
|
||||
color = resolve_color(
|
||||
@@ -1714,8 +1983,20 @@ class TriangleAnnotator(BaseAnnotator):
|
||||
|
||||
cv2.fillPoly(scene, [vertices], color.as_bgr())
|
||||
if self.outline_thickness:
|
||||
outline_color = resolve_color(
|
||||
color=self.outline_color,
|
||||
detections=detections,
|
||||
detection_idx=detection_idx,
|
||||
color_lookup=self.color_lookup
|
||||
if custom_color_lookup is None
|
||||
else custom_color_lookup,
|
||||
)
|
||||
cv2.polylines(
|
||||
scene, [vertices], True, (0, 0, 0), thickness=self.outline_thickness
|
||||
scene,
|
||||
[vertices],
|
||||
True,
|
||||
outline_color.as_bgr(),
|
||||
thickness=self.outline_thickness,
|
||||
)
|
||||
return scene
|
||||
|
||||
@@ -1738,7 +2019,7 @@ class RoundBoxAnnotator(BaseAnnotator):
|
||||
color (Union[Color, ColorPalette]): The color or color palette to use for
|
||||
annotating detections.
|
||||
thickness (int): Thickness of the bounding box lines.
|
||||
color_lookup (str): Strategy for mapping colors to annotations.
|
||||
color_lookup (ColorLookup): Strategy for mapping colors to annotations.
|
||||
Options are `INDEX`, `CLASS`, `TRACK`.
|
||||
roundness (float): Percent of roundness for edges of bounding box.
|
||||
Value must be float 0 < roundness <= 1.0
|
||||
@@ -1792,7 +2073,7 @@ class RoundBoxAnnotator(BaseAnnotator):
|
||||

|
||||
"""
|
||||
|
||||
assert isinstance(scene, np.ndarray)
|
||||
for detection_idx in range(len(detections)):
|
||||
x1, y1, x2, y2 = detections.xyxy[detection_idx].astype(int)
|
||||
color = resolve_color(
|
||||
@@ -1865,7 +2146,7 @@ class PercentageBarAnnotator(BaseAnnotator):
|
||||
border_color: Color = Color.BLACK,
|
||||
position: Position = Position.TOP_CENTER,
|
||||
color_lookup: ColorLookup = ColorLookup.CLASS,
|
||||
border_thickness: int = None,
|
||||
border_thickness: Optional[int] = None,
|
||||
):
|
||||
"""
|
||||
Args:
|
||||
@@ -1875,9 +2156,9 @@ class PercentageBarAnnotator(BaseAnnotator):
|
||||
annotating detections.
|
||||
border_color (Color): The color of the border lines.
|
||||
position (Position): The anchor position of drawing the percentage bar.
|
||||
color_lookup (str): Strategy for mapping colors to annotations.
|
||||
color_lookup (ColorLookup): Strategy for mapping colors to annotations.
|
||||
Options are `INDEX`, `CLASS`, `TRACK`.
|
||||
border_thickness (int): The thickness of the border lines.
|
||||
border_thickness (Optional[int]): The thickness of the border lines.
|
||||
"""
|
||||
self.height: int = height
|
||||
self.width: int = width
|
||||
@@ -1936,9 +2217,9 @@ class PercentageBarAnnotator(BaseAnnotator):
|
||||

|
||||
"""
|
||||
self.validate_custom_values(
|
||||
custom_values=custom_values, detections_count=len(detections)
|
||||
)
|
||||
assert isinstance(scene, np.ndarray)
|
||||
self.validate_custom_values(custom_values=custom_values, detections=detections)
|
||||
|
||||
anchors = detections.get_anchors_coordinates(anchor=self.position)
|
||||
for detection_idx in range(len(detections)):
|
||||
anchor = anchors[detection_idx]
|
||||
@@ -1949,11 +2230,11 @@ class PercentageBarAnnotator(BaseAnnotator):
|
||||
)
|
||||
border_width = border_coordinates[1][0] - border_coordinates[0][0]
|
||||
|
||||
value = (
|
||||
custom_values[detection_idx]
|
||||
if custom_values is not None
|
||||
else detections.confidence[detection_idx]
|
||||
)
|
||||
if custom_values is not None:
|
||||
value = custom_values[detection_idx]
|
||||
else:
|
||||
assert detections.confidence is not None # MyPy type hint
|
||||
value = detections.confidence[detection_idx]
|
||||
|
||||
color = resolve_color(
|
||||
color=self.color,
|
||||
@@ -2013,15 +2294,23 @@ class PercentageBarAnnotator(BaseAnnotator):
|
||||
|
||||
@staticmethod
|
||||
def validate_custom_values(
|
||||
custom_values: Optional[Union[np.ndarray, List[float]]], detections_count: int
|
||||
custom_values: Optional[Union[np.ndarray, List[float]]], detections: Detections
|
||||
) -> None:
|
||||
if custom_values is not None:
|
||||
if custom_values is None:
|
||||
if detections.confidence is None:
|
||||
raise ValueError(
|
||||
"The provided detections do not contain confidence values. "
|
||||
"Please provide `custom_values` or ensure that the detections "
|
||||
"contain confidence values (e.g. by using a different model)."
|
||||
)
|
||||
|
||||
else:
|
||||
if not isinstance(custom_values, (np.ndarray, list)):
|
||||
raise TypeError(
|
||||
"custom_values must be either a numpy array or a list of floats."
|
||||
)
|
||||
|
||||
if len(custom_values) != detections_count:
|
||||
if len(custom_values) != len(detections):
|
||||
raise ValueError(
|
||||
"The length of custom_values must match the number of detections."
|
||||
)
|
||||
@@ -2038,7 +2327,7 @@ class CropAnnotator(BaseAnnotator):
|
||||
def __init__(
|
||||
self,
|
||||
position: Position = Position.TOP_CENTER,
|
||||
scale_factor: int = 2,
|
||||
scale_factor: float = 2.0,
|
||||
border_color: Union[Color, ColorPalette] = ColorPalette.DEFAULT,
|
||||
border_thickness: int = 2,
|
||||
border_color_lookup: ColorLookup = ColorLookup.CLASS,
|
||||
@@ -2047,7 +2336,7 @@ class CropAnnotator(BaseAnnotator):
|
||||
Args:
|
||||
position (Position): The anchor position for placing the cropped and scaled
|
||||
part of the detection in the scene.
|
||||
scale_factor (int): The factor by which to scale the cropped image part. A
|
||||
scale_factor (float): The factor by which to scale the cropped image part. A
|
||||
factor of 2, for example, would double the size of the cropped area,
|
||||
allowing for a closer view of the detection.
|
||||
border_color (Union[Color, ColorPalette]): The color or color palette to
|
||||
@@ -2057,7 +2346,7 @@ class CropAnnotator(BaseAnnotator):
|
||||
annotations. Options are `INDEX`, `CLASS`, `TRACK`.
|
||||
"""
|
||||
self.position: Position = position
|
||||
self.scale_factor: int = scale_factor
|
||||
self.scale_factor: float = scale_factor
|
||||
self.border_color: Union[Color, ColorPalette] = border_color
|
||||
self.border_thickness: int = border_thickness
|
||||
self.border_color_lookup: ColorLookup = border_color_lookup
|
||||
@@ -2101,6 +2390,7 @@ class CropAnnotator(BaseAnnotator):
|
||||
)
|
||||
```
|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
crops = [
|
||||
crop_image(image=scene, xyxy=xyxy) for xyxy in detections.xyxy.astype(int)
|
||||
]
|
||||
@@ -2173,3 +2463,85 @@ class CropAnnotator(BaseAnnotator):
|
||||
)
|
||||
elif position == Position.BOTTOM_RIGHT:
|
||||
return (anchor_x, anchor_y), (anchor_x + width, anchor_y + height)
|
||||
|
||||
|
||||
class BackgroundOverlayAnnotator(BaseAnnotator):
|
||||
"""
|
||||
A class for drawing a colored overlay on the background of an image outside
|
||||
the region of detections.
|
||||
|
||||
If masks are provided, the background is colored outside the masks.
|
||||
If masks are not provided, the background is colored outside the bounding boxes.
|
||||
|
||||
You can use the `force_box` parameter to force the annotator to use bounding boxes.
|
||||
|
||||
!!! warning
|
||||
|
||||
This annotator uses `sv.Detections.mask`.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
color: Color = Color.BLACK,
|
||||
opacity: float = 0.5,
|
||||
force_box: bool = False,
|
||||
):
|
||||
"""
|
||||
Args:
|
||||
color (Color): The color to use for annotating detections.
|
||||
opacity (float): Opacity of the overlay mask. Must be between `0` and `1`.
|
||||
force_box (bool): If `True`, forces the annotator to use bounding boxes when
|
||||
masks are provided in the supplied sv.Detections.
|
||||
"""
|
||||
self.color: Color = color
|
||||
self.opacity = opacity
|
||||
self.force_box = force_box
|
||||
|
||||
@ensure_cv2_image_for_annotation
|
||||
def annotate(self, scene: ImageType, detections: Detections) -> ImageType:
|
||||
"""
|
||||
Applies a colored overlay to the scene outside of the detected regions.
|
||||
|
||||
Args:
|
||||
scene (ImageType): The image where masks will be drawn.
|
||||
`ImageType` is a flexible type, accepting either `numpy.ndarray`
|
||||
or `PIL.Image.Image`.
|
||||
detections (Detections): Object detections to annotate.
|
||||
|
||||
Returns:
|
||||
The annotated image, matching the type of `scene` (`numpy.ndarray`
|
||||
or `PIL.Image.Image`)
|
||||
|
||||
Example:
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
image = ...
|
||||
detections = sv.Detections(...)
|
||||
|
||||
background_overlay_annotator = sv.BackgroundOverlayAnnotator()
|
||||
annotated_frame = background_overlay_annotator.annotate(
|
||||
scene=image.copy(),
|
||||
detections=detections
|
||||
)
|
||||
```
|
||||
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
colored_mask = np.full_like(scene, self.color.as_bgr(), dtype=np.uint8)
|
||||
|
||||
cv2.addWeighted(
|
||||
scene, 1 - self.opacity, colored_mask, self.opacity, 0, dst=colored_mask
|
||||
)
|
||||
|
||||
if detections.mask is None or self.force_box:
|
||||
for x1, y1, x2, y2 in detections.xyxy.astype(int):
|
||||
colored_mask[y1:y2, x1:x2] = scene[y1:y2, x1:x2]
|
||||
else:
|
||||
for mask in detections.mask:
|
||||
colored_mask[mask] = scene[mask]
|
||||
|
||||
np.copyto(scene, colored_mask)
|
||||
return scene
|
||||
|
||||
+379
-152
@@ -3,8 +3,9 @@ from __future__ import annotations
|
||||
import os
|
||||
from abc import ABC, abstractmethod
|
||||
from dataclasses import dataclass
|
||||
from itertools import chain
|
||||
from pathlib import Path
|
||||
from typing import Dict, Iterator, List, Optional, Tuple
|
||||
from typing import Dict, Iterator, List, Optional, Tuple, Union
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
@@ -31,9 +32,10 @@ from supervision.dataset.utils import (
|
||||
train_test_split,
|
||||
)
|
||||
from supervision.detection.core import Detections
|
||||
from supervision.utils.internal import deprecated, warn_deprecated
|
||||
from supervision.utils.iterables import find_duplicates
|
||||
|
||||
|
||||
@dataclass
|
||||
class BaseDataset(ABC):
|
||||
@abstractmethod
|
||||
def __len__(self) -> int:
|
||||
@@ -41,35 +43,103 @@ class BaseDataset(ABC):
|
||||
|
||||
@abstractmethod
|
||||
def split(
|
||||
self, split_ratio=0.8, random_state=None, shuffle: bool = True
|
||||
self,
|
||||
split_ratio: float = 0.8,
|
||||
random_state: Optional[int] = None,
|
||||
shuffle: bool = True,
|
||||
) -> Tuple[BaseDataset, BaseDataset]:
|
||||
pass
|
||||
|
||||
|
||||
@dataclass
|
||||
class DetectionDataset(BaseDataset):
|
||||
"""
|
||||
Dataclass containing information about object detection dataset.
|
||||
Contains information about a detection dataset. Handles lazy image loading
|
||||
and annotation retrieval, dataset splitting, conversions into multiple
|
||||
formats.
|
||||
|
||||
Attributes:
|
||||
classes (List[str]): List containing dataset class names.
|
||||
images (Dict[str, np.ndarray]): Dictionary mapping image name to image.
|
||||
images (Union[List[str], Dict[str, np.ndarray]]):
|
||||
Accepts a list of image paths, or dictionaries of loaded cv2 images
|
||||
with paths as keys. If you pass a list of paths, the dataset will
|
||||
lazily load images on demand, which is much more memory-efficient.
|
||||
annotations (Dict[str, Detections]): Dictionary mapping
|
||||
image name to annotations.
|
||||
image path to annotations. The dictionary keys match
|
||||
match the keys in `images` or entries in the list of
|
||||
image paths.
|
||||
"""
|
||||
|
||||
classes: List[str]
|
||||
images: Dict[str, np.ndarray]
|
||||
annotations: Dict[str, Detections]
|
||||
def __init__(
|
||||
self,
|
||||
classes: List[str],
|
||||
images: Union[List[str], Dict[str, np.ndarray]],
|
||||
annotations: Dict[str, Detections],
|
||||
) -> None:
|
||||
self.classes = classes
|
||||
|
||||
if set(images) != set(annotations):
|
||||
raise ValueError(
|
||||
"The keys of the images and annotations dictionaries must match."
|
||||
)
|
||||
self.annotations = annotations
|
||||
|
||||
# Eliminate duplicates while preserving order
|
||||
self.image_paths = list(dict.fromkeys(images))
|
||||
|
||||
self._images_in_memory: Dict[str, np.ndarray] = {}
|
||||
if isinstance(images, dict):
|
||||
self._images_in_memory = images
|
||||
warn_deprecated(
|
||||
"Passing a `Dict[str, np.ndarray]` into `DetectionDataset` is "
|
||||
"deprecated and will be removed in `supervision-0.26.0`. Use "
|
||||
"a list of paths `List[str]` instead."
|
||||
)
|
||||
# TODO: when supervision-0.26.0 is released, and Dict[str, np.ndarray]
|
||||
# for images is no longer supported, also simplify the rest of
|
||||
# the code. E.g. list(images) is no longer needed, and merge can
|
||||
# be simplified.
|
||||
|
||||
@property
|
||||
@deprecated(
|
||||
"`DetectionDataset.images` property is deprecated and will be removed in "
|
||||
"`supervision-0.26.0`. Iterate with `for path, image, annotation in dataset:` "
|
||||
"instead."
|
||||
)
|
||||
def images(self) -> Dict[str, np.ndarray]:
|
||||
"""
|
||||
Load all images to memory and return them as a dictionary.
|
||||
|
||||
!!! warning
|
||||
|
||||
Only use this when you need all images at once.
|
||||
It is much more memory-efficient to initialize dataset with
|
||||
image paths and use `for path, image, annotation in dataset:`.
|
||||
"""
|
||||
if self._images_in_memory:
|
||||
return self._images_in_memory
|
||||
|
||||
images = {image_path: cv2.imread(image_path) for image_path in self.image_paths}
|
||||
return images
|
||||
|
||||
def _get_image(self, image_path: str) -> np.ndarray:
|
||||
"""Assumes that image is in dataset"""
|
||||
if self._images_in_memory:
|
||||
return self._images_in_memory[image_path]
|
||||
return cv2.imread(image_path)
|
||||
|
||||
def __len__(self) -> int:
|
||||
"""
|
||||
Return the number of images in the dataset.
|
||||
return len(self._images_in_memory) or len(self.image_paths)
|
||||
|
||||
Returns:
|
||||
int: The number of images.
|
||||
def __getitem__(self, i: int) -> Tuple[str, np.ndarray, Detections]:
|
||||
"""
|
||||
return len(self.images)
|
||||
Returns:
|
||||
Tuple[str, np.ndarray, Detections]: The image path, image data,
|
||||
and its corresponding annotation at index i.
|
||||
"""
|
||||
image_path = self.image_paths[i]
|
||||
image = self._get_image(image_path)
|
||||
annotation = self.annotations[image_path]
|
||||
return image_path, image, annotation
|
||||
|
||||
def __iter__(self) -> Iterator[Tuple[str, np.ndarray, Detections]]:
|
||||
"""
|
||||
@@ -77,40 +147,51 @@ class DetectionDataset(BaseDataset):
|
||||
|
||||
Yields:
|
||||
Iterator[Tuple[str, np.ndarray, Detections]]:
|
||||
An iterator that yields tuples containing the image name,
|
||||
An iterator that yields tuples containing the image path,
|
||||
the image data, and its corresponding annotation.
|
||||
"""
|
||||
for image_name, image in self.images.items():
|
||||
yield image_name, image, self.annotations.get(image_name, None)
|
||||
for i in range(len(self)):
|
||||
image_path, image, annotation = self[i]
|
||||
yield image_path, image, annotation
|
||||
|
||||
def __eq__(self, other):
|
||||
def __eq__(self, other) -> bool:
|
||||
if not isinstance(other, DetectionDataset):
|
||||
return False
|
||||
|
||||
if set(self.classes) != set(other.classes):
|
||||
return False
|
||||
|
||||
for key in self.images:
|
||||
if not np.array_equal(self.images[key], other.images[key]):
|
||||
return False
|
||||
if not self.annotations[key] == other.annotations[key]:
|
||||
if self.image_paths != other.image_paths:
|
||||
return False
|
||||
|
||||
if self._images_in_memory or other._images_in_memory:
|
||||
if not np.array_equal(
|
||||
list(self._images_in_memory.values()),
|
||||
list(other._images_in_memory.values()),
|
||||
):
|
||||
return False
|
||||
|
||||
if self.annotations != other.annotations:
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
def split(
|
||||
self, split_ratio=0.8, random_state=None, shuffle: bool = True
|
||||
self,
|
||||
split_ratio: float = 0.8,
|
||||
random_state: Optional[int] = None,
|
||||
shuffle: bool = True,
|
||||
) -> Tuple[DetectionDataset, DetectionDataset]:
|
||||
"""
|
||||
Splits the dataset into two parts (training and testing)
|
||||
using the provided split_ratio.
|
||||
|
||||
Args:
|
||||
split_ratio (float, optional): The ratio of the training
|
||||
split_ratio (float): The ratio of the training
|
||||
set to the entire dataset.
|
||||
random_state (int, optional): The seed for the random number generator.
|
||||
random_state (Optional[int]): The seed for the random number generator.
|
||||
This is used for reproducibility.
|
||||
shuffle (bool, optional): Whether to shuffle the data before splitting.
|
||||
shuffle (bool): Whether to shuffle the data before splitting.
|
||||
|
||||
Returns:
|
||||
Tuple[DetectionDataset, DetectionDataset]: A tuple containing
|
||||
@@ -127,26 +208,129 @@ class DetectionDataset(BaseDataset):
|
||||
```
|
||||
"""
|
||||
|
||||
image_names = list(self.images.keys())
|
||||
train_names, test_names = train_test_split(
|
||||
data=image_names,
|
||||
train_paths, test_paths = train_test_split(
|
||||
data=self.image_paths,
|
||||
train_ratio=split_ratio,
|
||||
random_state=random_state,
|
||||
shuffle=shuffle,
|
||||
)
|
||||
|
||||
train_input: Union[List[str], Dict[str, np.ndarray]]
|
||||
test_input: Union[List[str], Dict[str, np.ndarray]]
|
||||
if self._images_in_memory:
|
||||
train_input = {path: self._images_in_memory[path] for path in train_paths}
|
||||
test_input = {path: self._images_in_memory[path] for path in test_paths}
|
||||
else:
|
||||
train_input = train_paths
|
||||
test_input = test_paths
|
||||
train_annotations = {path: self.annotations[path] for path in train_paths}
|
||||
test_annotations = {path: self.annotations[path] for path in test_paths}
|
||||
|
||||
train_dataset = DetectionDataset(
|
||||
classes=self.classes,
|
||||
images={name: self.images[name] for name in train_names},
|
||||
annotations={name: self.annotations[name] for name in train_names},
|
||||
images=train_input,
|
||||
annotations=train_annotations,
|
||||
)
|
||||
test_dataset = DetectionDataset(
|
||||
classes=self.classes,
|
||||
images={name: self.images[name] for name in test_names},
|
||||
annotations={name: self.annotations[name] for name in test_names},
|
||||
images=test_input,
|
||||
annotations=test_annotations,
|
||||
)
|
||||
return train_dataset, test_dataset
|
||||
|
||||
@classmethod
|
||||
def merge(cls, dataset_list: List[DetectionDataset]) -> DetectionDataset:
|
||||
"""
|
||||
Merge a list of `DetectionDataset` objects into a single
|
||||
`DetectionDataset` object.
|
||||
|
||||
This method takes a list of `DetectionDataset` objects and combines
|
||||
their respective fields (`classes`, `images`,
|
||||
`annotations`) into a single `DetectionDataset` object.
|
||||
|
||||
Args:
|
||||
dataset_list (List[DetectionDataset]): A list of `DetectionDataset`
|
||||
objects to merge.
|
||||
|
||||
Returns:
|
||||
(DetectionDataset): A single `DetectionDataset` object containing
|
||||
the merged data from the input list.
|
||||
|
||||
Examples:
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
ds_1 = sv.DetectionDataset(...)
|
||||
len(ds_1)
|
||||
# 100
|
||||
ds_1.classes
|
||||
# ['dog', 'person']
|
||||
|
||||
ds_2 = sv.DetectionDataset(...)
|
||||
len(ds_2)
|
||||
# 200
|
||||
ds_2.classes
|
||||
# ['cat']
|
||||
|
||||
ds_merged = sv.DetectionDataset.merge([ds_1, ds_2])
|
||||
len(ds_merged)
|
||||
# 300
|
||||
ds_merged.classes
|
||||
# ['cat', 'dog', 'person']
|
||||
```
|
||||
"""
|
||||
|
||||
def is_in_memory(dataset: DetectionDataset) -> bool:
|
||||
return len(dataset._images_in_memory) > 0 or len(dataset.image_paths) == 0
|
||||
|
||||
def is_lazy(dataset: DetectionDataset) -> bool:
|
||||
return len(dataset._images_in_memory) == 0
|
||||
|
||||
all_in_memory = all([is_in_memory(dataset) for dataset in dataset_list])
|
||||
all_lazy = all([is_lazy(dataset) for dataset in dataset_list])
|
||||
if not all_in_memory and not all_lazy:
|
||||
raise ValueError(
|
||||
"Merging lazy and in-memory DetectionDatasets is not supported."
|
||||
)
|
||||
|
||||
images_in_memory = {}
|
||||
for dataset in dataset_list:
|
||||
images_in_memory.update(dataset._images_in_memory)
|
||||
|
||||
image_paths = list(
|
||||
chain.from_iterable(dataset.image_paths for dataset in dataset_list)
|
||||
)
|
||||
image_paths_unique = list(dict.fromkeys(image_paths))
|
||||
if len(image_paths) != len(image_paths_unique):
|
||||
duplicates = find_duplicates(image_paths)
|
||||
raise ValueError(
|
||||
f"Image paths {duplicates} are not unique across datasets."
|
||||
)
|
||||
image_paths = image_paths_unique
|
||||
|
||||
classes = merge_class_lists(
|
||||
class_lists=[dataset.classes for dataset in dataset_list]
|
||||
)
|
||||
|
||||
annotations = {}
|
||||
for dataset in dataset_list:
|
||||
annotations.update(dataset.annotations)
|
||||
for dataset in dataset_list:
|
||||
class_index_mapping = build_class_index_mapping(
|
||||
source_classes=dataset.classes, target_classes=classes
|
||||
)
|
||||
for image_path in dataset.image_paths:
|
||||
annotations[image_path] = map_detections_class_id(
|
||||
source_to_target_mapping=class_index_mapping,
|
||||
detections=annotations[image_path],
|
||||
)
|
||||
|
||||
return cls(
|
||||
classes=classes,
|
||||
images=images_in_memory or image_paths,
|
||||
annotations=annotations,
|
||||
)
|
||||
|
||||
def as_pascal_voc(
|
||||
self,
|
||||
images_directory_path: Optional[str] = None,
|
||||
@@ -180,25 +364,22 @@ class DetectionDataset(BaseDataset):
|
||||
"""
|
||||
if images_directory_path:
|
||||
save_dataset_images(
|
||||
images_directory_path=images_directory_path, images=self.images
|
||||
dataset=self,
|
||||
images_directory_path=images_directory_path,
|
||||
)
|
||||
if annotations_directory_path:
|
||||
Path(annotations_directory_path).mkdir(parents=True, exist_ok=True)
|
||||
|
||||
for image_path, image in self.images.items():
|
||||
detections = self.annotations[image_path]
|
||||
|
||||
if annotations_directory_path:
|
||||
for image_path, image, annotations in self:
|
||||
annotation_name = Path(image_path).stem
|
||||
annotations_path = os.path.join(
|
||||
annotations_directory_path, f"{annotation_name}.xml"
|
||||
)
|
||||
image_name = Path(image_path).name
|
||||
pascal_voc_xml = detections_to_pascal_voc(
|
||||
detections=detections,
|
||||
detections=annotations,
|
||||
classes=self.classes,
|
||||
filename=image_name,
|
||||
image_shape=image.shape,
|
||||
image_shape=image.shape, # type: ignore
|
||||
min_image_area_percentage=min_image_area_percentage,
|
||||
max_image_area_percentage=max_image_area_percentage,
|
||||
approximation_percentage=approximation_percentage,
|
||||
@@ -221,7 +402,7 @@ class DetectionDataset(BaseDataset):
|
||||
images_directory_path (str): Path to the directory containing the images.
|
||||
annotations_directory_path (str): Path to the directory
|
||||
containing the PASCAL VOC XML annotations.
|
||||
force_masks (bool, optional): If True, forces masks to
|
||||
force_masks (bool): If True, forces masks to
|
||||
be loaded for all annotations, regardless of whether they are present.
|
||||
|
||||
Returns:
|
||||
@@ -251,13 +432,15 @@ class DetectionDataset(BaseDataset):
|
||||
```
|
||||
"""
|
||||
|
||||
classes, images, annotations = load_pascal_voc_annotations(
|
||||
classes, image_paths, annotations = load_pascal_voc_annotations(
|
||||
images_directory_path=images_directory_path,
|
||||
annotations_directory_path=annotations_directory_path,
|
||||
force_masks=force_masks,
|
||||
)
|
||||
|
||||
return DetectionDataset(classes=classes, images=images, annotations=annotations)
|
||||
return DetectionDataset(
|
||||
classes=classes, images=image_paths, annotations=annotations
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def from_yolo(
|
||||
@@ -278,10 +461,10 @@ class DetectionDataset(BaseDataset):
|
||||
containing the YOLO annotation files.
|
||||
data_yaml_path (str): The path to the data
|
||||
YAML file containing class information.
|
||||
force_masks (bool, optional): If True, forces
|
||||
force_masks (bool): If True, forces
|
||||
masks to be loaded for all annotations,
|
||||
regardless of whether they are present.
|
||||
is_obb (bool, optional): If True, loads the annotations in OBB format.
|
||||
is_obb (bool): If True, loads the annotations in OBB format.
|
||||
OBB annotations are defined as `[class_id, x, y, x, y, x, y, x, y]`,
|
||||
where pairs of [x, y] are box corners.
|
||||
|
||||
@@ -311,14 +494,16 @@ class DetectionDataset(BaseDataset):
|
||||
# ['dog', 'person']
|
||||
```
|
||||
"""
|
||||
classes, images, annotations = load_yolo_annotations(
|
||||
classes, image_paths, annotations = load_yolo_annotations(
|
||||
images_directory_path=images_directory_path,
|
||||
annotations_directory_path=annotations_directory_path,
|
||||
data_yaml_path=data_yaml_path,
|
||||
force_masks=force_masks,
|
||||
is_obb=is_obb,
|
||||
)
|
||||
return DetectionDataset(classes=classes, images=images, annotations=annotations)
|
||||
return DetectionDataset(
|
||||
classes=classes, images=image_paths, annotations=annotations
|
||||
)
|
||||
|
||||
def as_yolo(
|
||||
self,
|
||||
@@ -359,13 +544,12 @@ class DetectionDataset(BaseDataset):
|
||||
"""
|
||||
if images_directory_path is not None:
|
||||
save_dataset_images(
|
||||
images_directory_path=images_directory_path, images=self.images
|
||||
dataset=self, images_directory_path=images_directory_path
|
||||
)
|
||||
if annotations_directory_path is not None:
|
||||
save_yolo_annotations(
|
||||
dataset=self,
|
||||
annotations_directory_path=annotations_directory_path,
|
||||
images=self.images,
|
||||
annotations=self.annotations,
|
||||
min_image_area_percentage=min_image_area_percentage,
|
||||
max_image_area_percentage=max_image_area_percentage,
|
||||
approximation_percentage=approximation_percentage,
|
||||
@@ -387,7 +571,7 @@ class DetectionDataset(BaseDataset):
|
||||
images_directory_path (str): The path to the
|
||||
directory containing the images.
|
||||
annotations_path (str): The path to the json annotation files.
|
||||
force_masks (bool, optional): If True,
|
||||
force_masks (bool): If True,
|
||||
forces masks to be loaded for all annotations,
|
||||
regardless of whether they are present.
|
||||
|
||||
@@ -469,117 +653,151 @@ class DetectionDataset(BaseDataset):
|
||||
"""
|
||||
if images_directory_path is not None:
|
||||
save_dataset_images(
|
||||
images_directory_path=images_directory_path, images=self.images
|
||||
dataset=self, images_directory_path=images_directory_path
|
||||
)
|
||||
if annotations_path is not None:
|
||||
save_coco_annotations(
|
||||
dataset=self,
|
||||
annotation_path=annotations_path,
|
||||
images=self.images,
|
||||
annotations=self.annotations,
|
||||
classes=self.classes,
|
||||
min_image_area_percentage=min_image_area_percentage,
|
||||
max_image_area_percentage=max_image_area_percentage,
|
||||
approximation_percentage=approximation_percentage,
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def merge(cls, dataset_list: List[DetectionDataset]) -> DetectionDataset:
|
||||
"""
|
||||
Merge a list of `DetectionDataset` objects into a single
|
||||
`DetectionDataset` object.
|
||||
|
||||
This method takes a list of `DetectionDataset` objects and combines
|
||||
their respective fields (`classes`, `images`,
|
||||
`annotations`) into a single `DetectionDataset` object.
|
||||
|
||||
Args:
|
||||
dataset_list (List[DetectionDataset]): A list of `DetectionDataset`
|
||||
objects to merge.
|
||||
|
||||
Returns:
|
||||
(DetectionDataset): A single `DetectionDataset` object containing
|
||||
the merged data from the input list.
|
||||
|
||||
Examples:
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
ds_1 = sv.DetectionDataset(...)
|
||||
len(ds_1)
|
||||
# 100
|
||||
ds_1.classes
|
||||
# ['dog', 'person']
|
||||
|
||||
ds_2 = sv.DetectionDataset(...)
|
||||
len(ds_2)
|
||||
# 200
|
||||
ds_2.classes
|
||||
# ['cat']
|
||||
|
||||
ds_merged = sv.DetectionDataset.merge([ds_1, ds_2])
|
||||
len(ds_merged)
|
||||
# 300
|
||||
ds_merged.classes
|
||||
# ['cat', 'dog', 'person']
|
||||
```
|
||||
"""
|
||||
merged_images, merged_annotations = {}, {}
|
||||
class_lists = [dataset.classes for dataset in dataset_list]
|
||||
merged_classes = merge_class_lists(class_lists=class_lists)
|
||||
|
||||
for dataset in dataset_list:
|
||||
class_index_mapping = build_class_index_mapping(
|
||||
source_classes=dataset.classes, target_classes=merged_classes
|
||||
)
|
||||
for image_name, image, detections in dataset:
|
||||
if image_name in merged_annotations:
|
||||
raise ValueError(
|
||||
f"Image name {image_name} is not unique across datasets."
|
||||
)
|
||||
|
||||
merged_images[image_name] = image
|
||||
merged_annotations[image_name] = map_detections_class_id(
|
||||
source_to_target_mapping=class_index_mapping,
|
||||
detections=detections,
|
||||
)
|
||||
|
||||
return cls(
|
||||
classes=merged_classes, images=merged_images, annotations=merged_annotations
|
||||
)
|
||||
|
||||
|
||||
@dataclass
|
||||
class ClassificationDataset(BaseDataset):
|
||||
"""
|
||||
Dataclass containing information about a classification dataset.
|
||||
Contains information about a classification dataset, handles lazy image
|
||||
loading, dataset splitting.
|
||||
|
||||
Attributes:
|
||||
classes (List[str]): List containing dataset class names.
|
||||
images (Dict[str, np.ndarray]): Dictionary mapping image name to image.
|
||||
annotations (Dict[str, Detections]): Dictionary mapping
|
||||
images (Union[List[str], Dict[str, np.ndarray]]):
|
||||
List of image paths or dictionary mapping image name to image data.
|
||||
annotations (Dict[str, Classifications]): Dictionary mapping
|
||||
image name to annotations.
|
||||
"""
|
||||
|
||||
classes: List[str]
|
||||
images: Dict[str, np.ndarray]
|
||||
annotations: Dict[str, Classifications]
|
||||
def __init__(
|
||||
self,
|
||||
classes: List[str],
|
||||
images: Union[List[str], Dict[str, np.ndarray]],
|
||||
annotations: Dict[str, Classifications],
|
||||
) -> None:
|
||||
self.classes = classes
|
||||
|
||||
if set(images) != set(annotations):
|
||||
raise ValueError(
|
||||
"The keys of the images and annotations dictionaries must match."
|
||||
)
|
||||
self.annotations = annotations
|
||||
|
||||
# Eliminate duplicates while preserving order
|
||||
self.image_paths = list(dict.fromkeys(images))
|
||||
|
||||
self._images_in_memory: Dict[str, np.ndarray] = {}
|
||||
if isinstance(images, dict):
|
||||
self._images_in_memory = images
|
||||
warn_deprecated(
|
||||
"Passing a `Dict[str, np.ndarray]` into `ClassificationDataset` is "
|
||||
"deprecated and will be removed in a future release. Use "
|
||||
"a list of paths `List[str]` instead."
|
||||
)
|
||||
|
||||
@property
|
||||
@deprecated(
|
||||
"`DetectionDataset.images` property is deprecated and will be removed in "
|
||||
"`supervision-0.26.0`. Iterate with `for path, image, annotation in dataset:` "
|
||||
"instead."
|
||||
)
|
||||
def images(self) -> Dict[str, np.ndarray]:
|
||||
"""
|
||||
Load all images to memory and return them as a dictionary.
|
||||
|
||||
!!! warning
|
||||
|
||||
Only use this when you need all images at once.
|
||||
It is much more memory-efficient to initialize dataset with
|
||||
image paths and use `for path, image, annotation in dataset:`.
|
||||
"""
|
||||
if self._images_in_memory:
|
||||
return self._images_in_memory
|
||||
|
||||
images = {image_path: cv2.imread(image_path) for image_path in self.image_paths}
|
||||
return images
|
||||
|
||||
def _get_image(self, image_path: str) -> np.ndarray:
|
||||
"""Assumes that image is in dataset"""
|
||||
if self._images_in_memory:
|
||||
return self._images_in_memory[image_path]
|
||||
return cv2.imread(image_path)
|
||||
|
||||
def __len__(self) -> int:
|
||||
return len(self.images)
|
||||
return len(self._images_in_memory) or len(self.image_paths)
|
||||
|
||||
def __getitem__(self, i: int) -> Tuple[str, np.ndarray, Classifications]:
|
||||
"""
|
||||
Returns:
|
||||
Tuple[str, np.ndarray, Classifications]: The image path, image data,
|
||||
and its corresponding annotation at index i.
|
||||
"""
|
||||
image_path = self.image_paths[i]
|
||||
image = self._get_image(image_path)
|
||||
annotation = self.annotations[image_path]
|
||||
return image_path, image, annotation
|
||||
|
||||
def __iter__(self) -> Iterator[Tuple[str, np.ndarray, Classifications]]:
|
||||
"""
|
||||
Iterate over the images and annotations in the dataset.
|
||||
|
||||
Yields:
|
||||
Iterator[Tuple[str, np.ndarray, Detections]]:
|
||||
An iterator that yields tuples containing the image path,
|
||||
the image data, and its corresponding annotation.
|
||||
"""
|
||||
for i in range(len(self)):
|
||||
image_path, image, annotation = self[i]
|
||||
yield image_path, image, annotation
|
||||
|
||||
def __eq__(self, other) -> bool:
|
||||
if not isinstance(other, ClassificationDataset):
|
||||
return False
|
||||
|
||||
if set(self.classes) != set(other.classes):
|
||||
return False
|
||||
|
||||
if self.image_paths != other.image_paths:
|
||||
return False
|
||||
|
||||
if self._images_in_memory or other._images_in_memory:
|
||||
if not np.array_equal(
|
||||
list(self._images_in_memory.values()),
|
||||
list(other._images_in_memory.values()),
|
||||
):
|
||||
return False
|
||||
|
||||
if self.annotations != other.annotations:
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
def split(
|
||||
self, split_ratio=0.8, random_state=None, shuffle: bool = True
|
||||
self,
|
||||
split_ratio: float = 0.8,
|
||||
random_state: Optional[int] = None,
|
||||
shuffle: bool = True,
|
||||
) -> Tuple[ClassificationDataset, ClassificationDataset]:
|
||||
"""
|
||||
Splits the dataset into two parts (training and testing)
|
||||
using the provided split_ratio.
|
||||
|
||||
Args:
|
||||
split_ratio (float, optional): The ratio of the training
|
||||
split_ratio (float): The ratio of the training
|
||||
set to the entire dataset.
|
||||
random_state (int, optional): The seed for the
|
||||
random_state (Optional[int]): The seed for the
|
||||
random number generator. This is used for reproducibility.
|
||||
shuffle (bool, optional): Whether to shuffle the data before splitting.
|
||||
shuffle (bool): Whether to shuffle the data before splitting.
|
||||
|
||||
Returns:
|
||||
Tuple[ClassificationDataset, ClassificationDataset]: A tuple containing
|
||||
@@ -595,24 +813,35 @@ class ClassificationDataset(BaseDataset):
|
||||
# (700, 300)
|
||||
```
|
||||
"""
|
||||
image_names = list(self.images.keys())
|
||||
train_names, test_names = train_test_split(
|
||||
data=image_names,
|
||||
train_paths, test_paths = train_test_split(
|
||||
data=self.image_paths,
|
||||
train_ratio=split_ratio,
|
||||
random_state=random_state,
|
||||
shuffle=shuffle,
|
||||
)
|
||||
|
||||
train_input: Union[List[str], Dict[str, np.ndarray]]
|
||||
test_input: Union[List[str], Dict[str, np.ndarray]]
|
||||
if self._images_in_memory:
|
||||
train_input = {path: self._images_in_memory[path] for path in train_paths}
|
||||
test_input = {path: self._images_in_memory[path] for path in test_paths}
|
||||
else:
|
||||
train_input = train_paths
|
||||
test_input = test_paths
|
||||
train_annotations = {path: self.annotations[path] for path in train_paths}
|
||||
test_annotations = {path: self.annotations[path] for path in test_paths}
|
||||
|
||||
train_dataset = ClassificationDataset(
|
||||
classes=self.classes,
|
||||
images={name: self.images[name] for name in train_names},
|
||||
annotations={name: self.annotations[name] for name in train_names},
|
||||
images=train_input,
|
||||
annotations=train_annotations,
|
||||
)
|
||||
test_dataset = ClassificationDataset(
|
||||
classes=self.classes,
|
||||
images={name: self.images[name] for name in test_names},
|
||||
annotations={name: self.annotations[name] for name in test_names},
|
||||
images=test_input,
|
||||
annotations=test_annotations,
|
||||
)
|
||||
|
||||
return train_dataset, test_dataset
|
||||
|
||||
def as_folder_structure(self, root_directory_path: str) -> None:
|
||||
@@ -628,18 +857,16 @@ class ClassificationDataset(BaseDataset):
|
||||
for class_name in self.classes:
|
||||
os.makedirs(os.path.join(root_directory_path, class_name), exist_ok=True)
|
||||
|
||||
for image_path in self.images:
|
||||
classification = self.annotations[image_path]
|
||||
image = self.images[image_path]
|
||||
image_name = Path(image_path).name
|
||||
for image_save_path, image, annotation in self:
|
||||
image_name = Path(image_save_path).name
|
||||
class_id = (
|
||||
classification.class_id[0]
|
||||
if classification.confidence is None
|
||||
else classification.get_top_k(1)[0][0]
|
||||
annotation.class_id[0]
|
||||
if annotation.confidence is None
|
||||
else annotation.get_top_k(1)[0][0]
|
||||
)
|
||||
class_name = self.classes[class_id]
|
||||
image_path = os.path.join(root_directory_path, class_name, image_name)
|
||||
cv2.imwrite(image_path, image)
|
||||
image_save_path = os.path.join(root_directory_path, class_name, image_name)
|
||||
cv2.imwrite(image_save_path, image)
|
||||
|
||||
@classmethod
|
||||
def from_folder_structure(cls, root_directory_path: str) -> ClassificationDataset:
|
||||
@@ -672,7 +899,7 @@ class ClassificationDataset(BaseDataset):
|
||||
classes = os.listdir(root_directory_path)
|
||||
classes = sorted(set(classes))
|
||||
|
||||
images = {}
|
||||
image_paths = []
|
||||
annotations = {}
|
||||
|
||||
for class_name in classes:
|
||||
@@ -680,13 +907,13 @@ class ClassificationDataset(BaseDataset):
|
||||
|
||||
for image in os.listdir(os.path.join(root_directory_path, class_name)):
|
||||
image_path = str(os.path.join(root_directory_path, class_name, image))
|
||||
images[image_path] = cv2.imread(image_path)
|
||||
image_paths.append(image_path)
|
||||
annotations[image_path] = Classifications(
|
||||
class_id=np.array([class_id]),
|
||||
)
|
||||
|
||||
return cls(
|
||||
classes=classes,
|
||||
images=images,
|
||||
images=image_paths,
|
||||
annotations=annotations,
|
||||
)
|
||||
|
||||
@@ -1,9 +1,8 @@
|
||||
import os
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from typing import Dict, List, Tuple
|
||||
from typing import TYPE_CHECKING, Dict, List, Tuple
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
import numpy.typing as npt
|
||||
|
||||
@@ -21,6 +20,9 @@ from supervision.detection.utils import (
|
||||
)
|
||||
from supervision.utils.file import read_json_file, save_json_file
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from supervision.dataset.core import DetectionDataset
|
||||
|
||||
|
||||
def coco_categories_to_classes(coco_categories: List[dict]) -> List[str]:
|
||||
return [
|
||||
@@ -161,7 +163,7 @@ def load_coco_annotations(
|
||||
images_directory_path: str,
|
||||
annotations_path: str,
|
||||
force_masks: bool = False,
|
||||
) -> Tuple[List[str], Dict[str, np.ndarray], Dict[str, Detections]]:
|
||||
) -> Tuple[List[str], List[str], Dict[str, Detections]]:
|
||||
coco_data = read_json_file(file_path=annotations_path)
|
||||
classes = coco_categories_to_classes(coco_categories=coco_data["categories"])
|
||||
class_index_mapping = build_coco_class_index_mapping(
|
||||
@@ -172,7 +174,7 @@ def load_coco_annotations(
|
||||
coco_annotations=coco_data["annotations"]
|
||||
)
|
||||
|
||||
images = {}
|
||||
images = []
|
||||
annotations = {}
|
||||
|
||||
for coco_image in coco_images:
|
||||
@@ -184,7 +186,6 @@ def load_coco_annotations(
|
||||
image_annotations = coco_annotations_groups.get(coco_image["id"], [])
|
||||
image_path = os.path.join(images_directory_path, image_name)
|
||||
|
||||
image = cv2.imread(image_path)
|
||||
annotation = coco_annotations_to_detections(
|
||||
image_annotations=image_annotations,
|
||||
resolution_wh=(image_width, image_height),
|
||||
@@ -195,23 +196,20 @@ def load_coco_annotations(
|
||||
detections=annotation,
|
||||
)
|
||||
|
||||
images[image_path] = image
|
||||
images.append(image_path)
|
||||
annotations[image_path] = annotation
|
||||
|
||||
return classes, images, annotations
|
||||
|
||||
|
||||
def save_coco_annotations(
|
||||
dataset: "DetectionDataset",
|
||||
annotation_path: str,
|
||||
images: Dict[str, np.ndarray],
|
||||
annotations: Dict[str, Detections],
|
||||
classes: List[str],
|
||||
min_image_area_percentage: float = 0.0,
|
||||
max_image_area_percentage: float = 1.0,
|
||||
approximation_percentage: float = 0.75,
|
||||
) -> None:
|
||||
Path(annotation_path).parent.mkdir(parents=True, exist_ok=True)
|
||||
info = {}
|
||||
licenses = [
|
||||
{
|
||||
"id": 1,
|
||||
@@ -222,10 +220,10 @@ def save_coco_annotations(
|
||||
|
||||
coco_annotations = []
|
||||
coco_images = []
|
||||
coco_categories = classes_to_coco_categories(classes=classes)
|
||||
coco_categories = classes_to_coco_categories(classes=dataset.classes)
|
||||
|
||||
image_id, annotation_id = 1, 1
|
||||
for image_path, image in images.items():
|
||||
for image_path, image, annotation in dataset:
|
||||
image_height, image_width, _ = image.shape
|
||||
image_name = f"{Path(image_path).stem}{Path(image_path).suffix}"
|
||||
coco_image = {
|
||||
@@ -238,10 +236,8 @@ def save_coco_annotations(
|
||||
}
|
||||
|
||||
coco_images.append(coco_image)
|
||||
detections = annotations[image_path]
|
||||
|
||||
coco_annotation, annotation_id = detections_to_coco_annotations(
|
||||
detections=detections,
|
||||
detections=annotation,
|
||||
image_id=image_id,
|
||||
annotation_id=annotation_id,
|
||||
min_image_area_percentage=min_image_area_percentage,
|
||||
@@ -253,7 +249,7 @@ def save_coco_annotations(
|
||||
image_id += 1
|
||||
|
||||
annotation_dict = {
|
||||
"info": info,
|
||||
"info": {},
|
||||
"licenses": licenses,
|
||||
"categories": coco_categories,
|
||||
"images": coco_images,
|
||||
|
||||
@@ -5,7 +5,8 @@ from xml.etree.ElementTree import Element, SubElement
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
from defusedxml.ElementTree import fromstring, parse, tostring
|
||||
from defusedxml.ElementTree import parse, tostring
|
||||
from defusedxml.minidom import parseString
|
||||
|
||||
from supervision.dataset.utils import approximate_mask_with_polygons
|
||||
from supervision.detection.core import Detections
|
||||
@@ -129,8 +130,7 @@ def detections_to_pascal_voc(
|
||||
annotation.append(next_object)
|
||||
|
||||
# Generate XML string
|
||||
xml_string = fromstring(tostring(annotation)).toprettyxml(indent=" ")
|
||||
|
||||
xml_string = parseString(tostring(annotation)).toprettyxml(indent=" ")
|
||||
return xml_string
|
||||
|
||||
|
||||
@@ -138,7 +138,7 @@ def load_pascal_voc_annotations(
|
||||
images_directory_path: str,
|
||||
annotations_directory_path: str,
|
||||
force_masks: bool = False,
|
||||
) -> Tuple[List[str], Dict[str, np.ndarray], Dict[str, Detections]]:
|
||||
) -> Tuple[List[str], List[str], Dict[str, Detections]]:
|
||||
"""
|
||||
Loads PASCAL VOC XML annotations and returns the image name,
|
||||
a Detections instance, and a list of class names.
|
||||
@@ -147,48 +147,43 @@ def load_pascal_voc_annotations(
|
||||
images_directory_path (str): The path to the directory containing the images.
|
||||
annotations_directory_path (str): The path to the directory containing the
|
||||
PASCAL VOC annotation files.
|
||||
force_masks (bool, optional): If True, forces masks to be loaded for all
|
||||
force_masks (bool): If True, forces masks to be loaded for all
|
||||
annotations, regardless of whether they are present.
|
||||
|
||||
Returns:
|
||||
Tuple[List[str], Dict[str, np.ndarray], Dict[str, Detections]]: A tuple
|
||||
containing a list of class names,
|
||||
a dictionary with image names as keys and
|
||||
images as values, and a dictionary with image names as
|
||||
keys and corresponding Detections instances as values.
|
||||
Tuple[List[str], List[str], Dict[str, Detections]]: A tuple with a list
|
||||
of class names, a list of paths to images, and a dictionary with image
|
||||
paths as keys and corresponding Detections instances as values.
|
||||
"""
|
||||
|
||||
image_paths = list_files_with_extensions(
|
||||
directory=images_directory_path, extensions=["jpg", "jpeg", "png"]
|
||||
)
|
||||
image_paths = [
|
||||
str(path)
|
||||
for path in list_files_with_extensions(
|
||||
directory=images_directory_path, extensions=["jpg", "jpeg", "png"]
|
||||
)
|
||||
]
|
||||
|
||||
classes = []
|
||||
images = {}
|
||||
classes: List[str] = []
|
||||
annotations = {}
|
||||
|
||||
for image_path in image_paths:
|
||||
image_name = Path(image_path).stem
|
||||
image_path = str(image_path)
|
||||
image = cv2.imread(image_path)
|
||||
|
||||
annotation_path = os.path.join(annotations_directory_path, f"{image_name}.xml")
|
||||
image_stem = Path(image_path).stem
|
||||
annotation_path = os.path.join(annotations_directory_path, f"{image_stem}.xml")
|
||||
if not os.path.exists(annotation_path):
|
||||
images[image_path] = image
|
||||
annotations[image_path] = Detections.empty()
|
||||
continue
|
||||
|
||||
tree = parse(annotation_path)
|
||||
root = tree.getroot()
|
||||
|
||||
image = cv2.imread(image_path)
|
||||
resolution_wh = (image.shape[1], image.shape[0])
|
||||
annotation, classes = detections_from_xml_obj(
|
||||
root, classes, resolution_wh, force_masks
|
||||
)
|
||||
|
||||
images[image_path] = image
|
||||
annotations[image_path] = annotation
|
||||
|
||||
return classes, images, annotations
|
||||
return classes, image_paths, annotations
|
||||
|
||||
|
||||
def detections_from_xml_obj(
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import os
|
||||
from pathlib import Path
|
||||
from typing import Dict, List, Optional, Tuple
|
||||
from typing import TYPE_CHECKING, Dict, List, Optional, Tuple
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
@@ -17,6 +17,9 @@ from supervision.utils.file import (
|
||||
save_yaml_file,
|
||||
)
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from supervision.dataset.core import DetectionDataset
|
||||
|
||||
|
||||
def _parse_box(values: List[str]) -> np.ndarray:
|
||||
x_center, y_center, width, height = values
|
||||
@@ -124,7 +127,7 @@ def load_yolo_annotations(
|
||||
data_yaml_path: str,
|
||||
force_masks: bool = False,
|
||||
is_obb: bool = False,
|
||||
) -> Tuple[List[str], Dict[str, np.ndarray], Dict[str, Detections]]:
|
||||
) -> Tuple[List[str], List[str], Dict[str, Detections]]:
|
||||
"""
|
||||
Loads YOLO annotations and returns class names, images,
|
||||
and their corresponding detections.
|
||||
@@ -135,37 +138,36 @@ def load_yolo_annotations(
|
||||
containing the YOLO annotation files.
|
||||
data_yaml_path (str): The path to the data
|
||||
YAML file containing class information.
|
||||
force_masks (bool, optional): If True, forces masks to be loaded
|
||||
force_masks (bool): If True, forces masks to be loaded
|
||||
for all annotations, regardless of whether they are present.
|
||||
is_obb (bool, optional): If True, loads the annotations in OBB format.
|
||||
is_obb (bool): If True, loads the annotations in OBB format.
|
||||
OBB annotations are defined as `[class_id, x, y, x, y, x, y, x, y]`,
|
||||
where pairs of [x, y] are box corners.
|
||||
|
||||
Returns:
|
||||
Tuple[List[str], Dict[str, np.ndarray], Dict[str, Detections]]:
|
||||
Tuple[List[str], List[str], Dict[str, Detections]]:
|
||||
A tuple containing a list of class names, a dictionary with
|
||||
image names as keys and images as values, and a dictionary
|
||||
with image names as keys and corresponding Detections instances as values.
|
||||
"""
|
||||
image_paths = list_files_with_extensions(
|
||||
directory=images_directory_path, extensions=["jpg", "jpeg", "png"]
|
||||
)
|
||||
image_paths = [
|
||||
str(path)
|
||||
for path in list_files_with_extensions(
|
||||
directory=images_directory_path, extensions=["jpg", "jpeg", "png"]
|
||||
)
|
||||
]
|
||||
|
||||
classes = _extract_class_names(file_path=data_yaml_path)
|
||||
images = {}
|
||||
annotations = {}
|
||||
|
||||
for image_path in image_paths:
|
||||
image_stem = Path(image_path).stem
|
||||
image_path = str(image_path)
|
||||
image = cv2.imread(image_path)
|
||||
|
||||
annotation_path = os.path.join(annotations_directory_path, f"{image_stem}.txt")
|
||||
if not os.path.exists(annotation_path):
|
||||
images[image_path] = image
|
||||
annotations[image_path] = Detections.empty()
|
||||
continue
|
||||
|
||||
image = cv2.imread(image_path)
|
||||
lines = read_txt_file(file_path=annotation_path, skip_empty=True)
|
||||
h, w, _ = image.shape
|
||||
resolution_wh = (w, h)
|
||||
@@ -178,9 +180,8 @@ def load_yolo_annotations(
|
||||
with_masks=with_masks,
|
||||
is_obb=is_obb,
|
||||
)
|
||||
images[image_path] = image
|
||||
annotations[image_path] = annotation
|
||||
return classes, images, annotations
|
||||
return classes, image_paths, annotations
|
||||
|
||||
|
||||
def object_to_yolo(
|
||||
@@ -214,6 +215,9 @@ def detections_to_yolo_annotations(
|
||||
) -> List[str]:
|
||||
annotation = []
|
||||
for xyxy, mask, _, class_id, _, _ in detections:
|
||||
if class_id is None:
|
||||
raise ValueError("Class ID is required for YOLO annotations.")
|
||||
|
||||
if mask is not None:
|
||||
polygons = approximate_mask_with_polygons(
|
||||
mask=mask,
|
||||
@@ -239,24 +243,22 @@ def detections_to_yolo_annotations(
|
||||
|
||||
|
||||
def save_yolo_annotations(
|
||||
dataset: "DetectionDataset",
|
||||
annotations_directory_path: str,
|
||||
images: Dict[str, np.ndarray],
|
||||
annotations: Dict[str, Detections],
|
||||
min_image_area_percentage: float = 0.0,
|
||||
max_image_area_percentage: float = 1.0,
|
||||
approximation_percentage: float = 0.75,
|
||||
) -> None:
|
||||
Path(annotations_directory_path).mkdir(parents=True, exist_ok=True)
|
||||
for image_path, image in images.items():
|
||||
detections = annotations[image_path]
|
||||
for image_path, image, annotation in dataset:
|
||||
image_name = Path(image_path).name
|
||||
yolo_annotations_name = _image_name_to_annotation_name(image_name=image_name)
|
||||
yolo_annotations_path = os.path.join(
|
||||
annotations_directory_path, yolo_annotations_name
|
||||
)
|
||||
lines = detections_to_yolo_annotations(
|
||||
detections=detections,
|
||||
image_shape=image.shape,
|
||||
detections=annotation,
|
||||
image_shape=image.shape, # type: ignore
|
||||
min_image_area_percentage=min_image_area_percentage,
|
||||
max_image_area_percentage=max_image_area_percentage,
|
||||
approximation_percentage=approximation_percentage,
|
||||
|
||||
@@ -1,8 +1,9 @@
|
||||
import copy
|
||||
import os
|
||||
import random
|
||||
import shutil
|
||||
from pathlib import Path
|
||||
from typing import Dict, List, Optional, Tuple, TypeVar, Union
|
||||
from typing import TYPE_CHECKING, Dict, List, Optional, Tuple, TypeVar, Union
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
@@ -15,6 +16,9 @@ from supervision.detection.utils import (
|
||||
mask_to_polygons,
|
||||
)
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from supervision.dataset.core import DetectionDataset
|
||||
|
||||
T = TypeVar("T")
|
||||
|
||||
|
||||
@@ -59,6 +63,7 @@ def merge_class_lists(class_lists: List[List[str]]) -> List[str]:
|
||||
def build_class_index_mapping(
|
||||
source_classes: List[str], target_classes: List[str]
|
||||
) -> Dict[int, int]:
|
||||
"""Returns the index map of source classes -> target classes."""
|
||||
index_mapping = {}
|
||||
|
||||
for i, class_name in enumerate(source_classes):
|
||||
@@ -94,14 +99,16 @@ def map_detections_class_id(
|
||||
|
||||
|
||||
def save_dataset_images(
|
||||
images_directory_path: str, images: Dict[str, np.ndarray]
|
||||
dataset: "DetectionDataset", images_directory_path: str
|
||||
) -> None:
|
||||
Path(images_directory_path).mkdir(parents=True, exist_ok=True)
|
||||
|
||||
for image_path, image in images.items():
|
||||
image_name = Path(image_path).name
|
||||
target_image_path = os.path.join(images_directory_path, image_name)
|
||||
cv2.imwrite(target_image_path, image)
|
||||
for image_path in dataset.image_paths:
|
||||
final_path = os.path.join(images_directory_path, Path(image_path).name)
|
||||
if image_path in dataset._images_in_memory:
|
||||
image = dataset._images_in_memory[image_path]
|
||||
cv2.imwrite(final_path, image)
|
||||
else:
|
||||
shutil.copyfile(image_path, final_path)
|
||||
|
||||
|
||||
def train_test_split(
|
||||
|
||||
@@ -1,155 +0,0 @@
|
||||
from typing import List, Optional, Union
|
||||
|
||||
import cv2
|
||||
|
||||
from supervision.annotators.base import ImageType
|
||||
from supervision.detection.core import Detections
|
||||
from supervision.draw.color import Color, ColorPalette
|
||||
from supervision.utils.conversion import ensure_cv2_image_for_annotation
|
||||
from supervision.utils.internal import deprecated
|
||||
|
||||
|
||||
class BoxAnnotator:
|
||||
"""
|
||||
A class for drawing bounding boxes on an image using detections provided.
|
||||
|
||||
Attributes:
|
||||
color (Union[Color, ColorPalette]): The color to draw the bounding box,
|
||||
can be a single color or a color palette
|
||||
thickness (int): The thickness of the bounding box lines, default is 2
|
||||
text_color (Color): The color of the text on the bounding box, default is white
|
||||
text_scale (float): The scale of the text on the bounding box, default is 0.5
|
||||
text_thickness (int): The thickness of the text on the bounding box,
|
||||
default is 1
|
||||
text_padding (int): The padding around the text on the bounding box,
|
||||
default is 5
|
||||
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
color: Union[Color, ColorPalette] = ColorPalette.DEFAULT,
|
||||
thickness: int = 2,
|
||||
text_color: Color = Color.BLACK,
|
||||
text_scale: float = 0.5,
|
||||
text_thickness: int = 1,
|
||||
text_padding: int = 10,
|
||||
):
|
||||
self.color: Union[Color, ColorPalette] = color
|
||||
self.thickness: int = thickness
|
||||
self.text_color: Color = text_color
|
||||
self.text_scale: float = text_scale
|
||||
self.text_thickness: int = text_thickness
|
||||
self.text_padding: int = text_padding
|
||||
|
||||
@deprecated(
|
||||
"`BoxAnnotator` is deprecated and will be removed in "
|
||||
"`supervision-0.22.0`. Use `BoundingBoxAnnotator` and `LabelAnnotator` instead"
|
||||
)
|
||||
@ensure_cv2_image_for_annotation
|
||||
def annotate(
|
||||
self,
|
||||
scene: ImageType,
|
||||
detections: Detections,
|
||||
labels: Optional[List[str]] = None,
|
||||
skip_label: bool = False,
|
||||
) -> ImageType:
|
||||
"""
|
||||
Draws bounding boxes on the frame using the detections provided.
|
||||
|
||||
Args:
|
||||
scene (ImageType): The image on which the bounding boxes will be drawn.
|
||||
`ImageType` is a flexible type, accepting either `numpy.ndarray`
|
||||
or `PIL.Image.Image`.
|
||||
detections (Detections): The detections for which the
|
||||
bounding boxes will be drawn
|
||||
labels (Optional[List[str]]): An optional list of labels
|
||||
corresponding to each detection. If `labels` are not provided,
|
||||
corresponding `class_id` will be used as label.
|
||||
skip_label (bool): Is set to `True`, skips bounding box label annotation.
|
||||
Returns:
|
||||
ImageType: The image with the bounding boxes drawn on it, matching the
|
||||
type of `scene` (`numpy.ndarray` or `PIL.Image.Image`)
|
||||
|
||||
Example:
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
classes = ['person', ...]
|
||||
image = ...
|
||||
detections = sv.Detections(...)
|
||||
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
labels = [
|
||||
f"{classes[class_id]} {confidence:0.2f}"
|
||||
for _, _, confidence, class_id, _ in detections
|
||||
]
|
||||
annotated_frame = box_annotator.annotate(
|
||||
scene=image.copy(),
|
||||
detections=detections,
|
||||
labels=labels
|
||||
)
|
||||
```
|
||||
"""
|
||||
font = cv2.FONT_HERSHEY_SIMPLEX
|
||||
for i in range(len(detections)):
|
||||
x1, y1, x2, y2 = detections.xyxy[i].astype(int)
|
||||
class_id = (
|
||||
detections.class_id[i] if detections.class_id is not None else None
|
||||
)
|
||||
idx = class_id if class_id is not None else i
|
||||
color = (
|
||||
self.color.by_idx(idx)
|
||||
if isinstance(self.color, ColorPalette)
|
||||
else self.color
|
||||
)
|
||||
cv2.rectangle(
|
||||
img=scene,
|
||||
pt1=(x1, y1),
|
||||
pt2=(x2, y2),
|
||||
color=color.as_bgr(),
|
||||
thickness=self.thickness,
|
||||
)
|
||||
if skip_label:
|
||||
continue
|
||||
|
||||
text = (
|
||||
f"{class_id}"
|
||||
if (labels is None or len(detections) != len(labels))
|
||||
else labels[i]
|
||||
)
|
||||
|
||||
text_width, text_height = cv2.getTextSize(
|
||||
text=text,
|
||||
fontFace=font,
|
||||
fontScale=self.text_scale,
|
||||
thickness=self.text_thickness,
|
||||
)[0]
|
||||
|
||||
text_x = x1 + self.text_padding
|
||||
text_y = y1 - self.text_padding
|
||||
|
||||
text_background_x1 = x1
|
||||
text_background_y1 = y1 - 2 * self.text_padding - text_height
|
||||
|
||||
text_background_x2 = x1 + 2 * self.text_padding + text_width
|
||||
text_background_y2 = y1
|
||||
|
||||
cv2.rectangle(
|
||||
img=scene,
|
||||
pt1=(text_background_x1, text_background_y1),
|
||||
pt2=(text_background_x2, text_background_y2),
|
||||
color=color.as_bgr(),
|
||||
thickness=cv2.FILLED,
|
||||
)
|
||||
cv2.putText(
|
||||
img=scene,
|
||||
text=text,
|
||||
org=(text_x, text_y),
|
||||
fontFace=font,
|
||||
fontScale=self.text_scale,
|
||||
color=self.text_color.as_rgb(),
|
||||
thickness=self.text_thickness,
|
||||
lineType=cv2.LINE_AA,
|
||||
)
|
||||
return scene
|
||||
@@ -18,6 +18,11 @@ from supervision.detection.overlap_filter import (
|
||||
box_non_max_suppression,
|
||||
mask_non_max_suppression,
|
||||
)
|
||||
from supervision.detection.tools.transformers import (
|
||||
process_transformers_detection_result,
|
||||
process_transformers_v4_segmentation_result,
|
||||
process_transformers_v5_segmentation_result,
|
||||
)
|
||||
from supervision.detection.utils import (
|
||||
box_iou_batch,
|
||||
calculate_masks_centroids,
|
||||
@@ -30,7 +35,7 @@ from supervision.detection.utils import (
|
||||
xywh_to_xyxy,
|
||||
)
|
||||
from supervision.geometry.core import Position
|
||||
from supervision.utils.internal import deprecated, get_instance_variables
|
||||
from supervision.utils.internal import get_instance_variables
|
||||
from supervision.validators import validate_detections_fields
|
||||
|
||||
|
||||
@@ -244,10 +249,6 @@ class Detections:
|
||||
results = model(image)[0]
|
||||
detections = sv.Detections.from_ultralytics(results)
|
||||
```
|
||||
|
||||
!!! tip
|
||||
|
||||
Class names values can be accessed using `detections["class_name"]`.
|
||||
""" # noqa: E501 // docs
|
||||
|
||||
if hasattr(ultralytics_results, "obb") and ultralytics_results.obb is not None:
|
||||
@@ -267,6 +268,14 @@ class Detections:
|
||||
},
|
||||
)
|
||||
|
||||
if hasattr(ultralytics_results, "boxes") and ultralytics_results.boxes is None:
|
||||
masks = extract_ultralytics_masks(ultralytics_results)
|
||||
return cls(
|
||||
xyxy=mask_to_xyxy(masks),
|
||||
mask=masks,
|
||||
class_id=np.arange(len(ultralytics_results)),
|
||||
)
|
||||
|
||||
class_id = ultralytics_results.boxes.cls.cpu().numpy().astype(int)
|
||||
class_names = np.array([ultralytics_results.names[i] for i in class_id])
|
||||
return cls(
|
||||
@@ -438,15 +447,19 @@ class Detections:
|
||||
cls, transformers_results: dict, id2label: Optional[Dict[int, str]] = None
|
||||
) -> Detections:
|
||||
"""
|
||||
Creates a Detections instance from object detection or segmentation
|
||||
Creates a Detections instance from object detection or panoptic, semantic
|
||||
and instance segmentation
|
||||
[Transformer](https://github.com/huggingface/transformers) inference result.
|
||||
|
||||
Args:
|
||||
transformers_results (dict): The output of Transformers model inference. A
|
||||
dictionary containing the `scores`, `labels`, `boxes` and `masks` keys.
|
||||
transformers_results (Union[dict, torch.Tensor]): Inference results from
|
||||
your Transformers model. This can be either a dictionary containing
|
||||
valuable outputs like `scores`, `labels`, `boxes`, `masks`,
|
||||
`segments_info`, and `segmentation`, or a `torch.Tensor` holding a
|
||||
segmentation map where values represent class IDs.
|
||||
id2label (Optional[Dict[int, str]]): A dictionary mapping class IDs to
|
||||
class names. If provided, the resulting Detections object will contain
|
||||
`class_name` data field with the class names.
|
||||
labels, typically part of the `transformers` model configuration. If
|
||||
provided, the resulting dictionary will include class names.
|
||||
|
||||
Returns:
|
||||
Detections: A new Detections object.
|
||||
@@ -477,36 +490,28 @@ class Detections:
|
||||
id2label=model.config.id2label
|
||||
)
|
||||
```
|
||||
|
||||
!!! tip
|
||||
|
||||
Class names values can be accessed using `detections["class_name"]`.
|
||||
""" # noqa: E501 // docs
|
||||
|
||||
class_ids = transformers_results["labels"].cpu().detach().numpy().astype(int)
|
||||
data = {}
|
||||
if id2label is not None:
|
||||
class_names = np.array([id2label[class_id] for class_id in class_ids])
|
||||
data[CLASS_NAME_DATA_FIELD] = class_names
|
||||
if (
|
||||
transformers_results.__class__.__name__ == "Tensor"
|
||||
or "segmentation" in transformers_results
|
||||
):
|
||||
return cls(
|
||||
**process_transformers_v5_segmentation_result(
|
||||
transformers_results, id2label
|
||||
)
|
||||
)
|
||||
|
||||
if "masks" in transformers_results or "png_string" in transformers_results:
|
||||
return cls(
|
||||
**process_transformers_v4_segmentation_result(
|
||||
transformers_results, id2label
|
||||
)
|
||||
)
|
||||
|
||||
if "boxes" in transformers_results:
|
||||
return cls(
|
||||
xyxy=transformers_results["boxes"].cpu().detach().numpy(),
|
||||
confidence=transformers_results["scores"].cpu().detach().numpy(),
|
||||
class_id=class_ids,
|
||||
data=data,
|
||||
)
|
||||
elif "masks" in transformers_results:
|
||||
masks = transformers_results["masks"].cpu().detach().numpy().astype(bool)
|
||||
return cls(
|
||||
xyxy=mask_to_xyxy(masks),
|
||||
mask=masks,
|
||||
confidence=transformers_results["scores"].cpu().detach().numpy(),
|
||||
class_id=class_ids,
|
||||
data=data,
|
||||
)
|
||||
else:
|
||||
raise NotImplementedError(
|
||||
"Only object detection and semantic segmentation results are supported."
|
||||
**process_transformers_detection_result(transformers_results, id2label)
|
||||
)
|
||||
|
||||
@classmethod
|
||||
@@ -583,10 +588,6 @@ class Detections:
|
||||
result = model.infer(image)[0]
|
||||
detections = sv.Detections.from_inference(result)
|
||||
```
|
||||
|
||||
!!! tip
|
||||
|
||||
Class names values can be accessed using `detections["class_name"]`.
|
||||
"""
|
||||
with suppress(AttributeError):
|
||||
roboflow_result = roboflow_result.dict(exclude_none=True, by_alias=True)
|
||||
@@ -608,45 +609,6 @@ class Detections:
|
||||
data=data,
|
||||
)
|
||||
|
||||
@classmethod
|
||||
@deprecated(
|
||||
"`Detections.from_roboflow` is deprecated and will be removed in "
|
||||
"`supervision-0.22.0`. Use `Detections.from_inference` instead."
|
||||
)
|
||||
def from_roboflow(cls, roboflow_result: Union[dict, Any]) -> Detections:
|
||||
"""
|
||||
!!! failure "Deprecated"
|
||||
|
||||
`Detections.from_roboflow` is deprecated and will be removed in
|
||||
`supervision-0.22.0`. Use `Detections.from_inference` instead.
|
||||
|
||||
Create a Detections object from the [Roboflow](https://roboflow.com/)
|
||||
API inference result or the [Inference](https://inference.roboflow.com/)
|
||||
package results.
|
||||
|
||||
Args:
|
||||
roboflow_result (dict): The result from the
|
||||
Roboflow API containing predictions.
|
||||
|
||||
Returns:
|
||||
(Detections): A Detections object containing the bounding boxes, class IDs,
|
||||
and confidences of the predictions.
|
||||
|
||||
Example:
|
||||
```python
|
||||
import cv2
|
||||
import supervision as sv
|
||||
from inference import get_model
|
||||
|
||||
image = cv2.imread(<SOURCE_IMAGE_PATH>)
|
||||
model = get_model(model_id="yolov8s-640")
|
||||
|
||||
result = model.infer(image)[0]
|
||||
detections = sv.Detections.from_roboflow(result)
|
||||
```
|
||||
"""
|
||||
return cls.from_inference(roboflow_result)
|
||||
|
||||
@classmethod
|
||||
def from_sam(cls, sam_result: List[dict]) -> Detections:
|
||||
"""
|
||||
@@ -686,7 +648,7 @@ class Detections:
|
||||
if np.asarray(xywh).shape[0] == 0:
|
||||
return cls.empty()
|
||||
|
||||
xyxy = xywh_to_xyxy(boxes_xywh=xywh)
|
||||
xyxy = xywh_to_xyxy(xywh=xywh)
|
||||
return cls(xyxy=xyxy, mask=mask)
|
||||
|
||||
@classmethod
|
||||
@@ -1196,10 +1158,10 @@ class Detections:
|
||||
from a segmentation model, the IoU mask is applied. Otherwise, box IoU is used.
|
||||
|
||||
Args:
|
||||
threshold (float, optional): The intersection-over-union threshold
|
||||
threshold (float): The intersection-over-union threshold
|
||||
to use for non-maximum suppression. I'm the lower the value the more
|
||||
restrictive the NMS becomes. Defaults to 0.5.
|
||||
class_agnostic (bool, optional): Whether to perform class-agnostic
|
||||
class_agnostic (bool): Whether to perform class-agnostic
|
||||
non-maximum suppression. If True, the class_id of each detection
|
||||
will be ignored. Defaults to False.
|
||||
|
||||
@@ -1251,9 +1213,9 @@ class Detections:
|
||||
Perform non-maximum merging on the current set of object detections.
|
||||
|
||||
Args:
|
||||
threshold (float, optional): The intersection-over-union threshold
|
||||
threshold (float): The intersection-over-union threshold
|
||||
to use for non-maximum merging. Defaults to 0.5.
|
||||
class_agnostic (bool, optional): Whether to perform class-agnostic
|
||||
class_agnostic (bool): Whether to perform class-agnostic
|
||||
non-maximum merging. If True, the class_id of each detection
|
||||
will be ignored. Defaults to False.
|
||||
|
||||
|
||||
@@ -174,7 +174,9 @@ def from_florence_2(
|
||||
match is not None
|
||||
), f"Expected string to end in location tags, but got {result}"
|
||||
|
||||
w, h = resolution_wh
|
||||
xyxy = np.array([match.groups()], dtype=np.float32)
|
||||
xyxy *= np.array([w, h, w, h]) / 1000
|
||||
result_string = result[: match.start()]
|
||||
labels = np.array([result_string])
|
||||
return xyxy, labels, None, None
|
||||
|
||||
@@ -1,3 +1,5 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from enum import Enum
|
||||
from typing import List, Union
|
||||
|
||||
@@ -53,9 +55,9 @@ def mask_non_max_suppression(
|
||||
masks (np.ndarray): A 3D array of binary masks corresponding to the predictions.
|
||||
Shape: `(N, H, W)`, where N is the number of predictions, and H, W are the
|
||||
dimensions of each mask.
|
||||
iou_threshold (float, optional): The intersection-over-union threshold
|
||||
iou_threshold (float): The intersection-over-union threshold
|
||||
to use for non-maximum suppression.
|
||||
mask_dimension (int, optional): The dimension to which the masks should be
|
||||
mask_dimension (int): The dimension to which the masks should be
|
||||
resized before computing IOU values. Defaults to 640.
|
||||
|
||||
Returns:
|
||||
@@ -101,7 +103,7 @@ def box_non_max_suppression(
|
||||
predictions (np.ndarray): An array of object detection predictions in
|
||||
the format of `(x_min, y_min, x_max, y_max, score)`
|
||||
or `(x_min, y_min, x_max, y_max, score, class)`.
|
||||
iou_threshold (float, optional): The intersection-over-union threshold
|
||||
iou_threshold (float): The intersection-over-union threshold
|
||||
to use for non-maximum suppression.
|
||||
|
||||
Returns:
|
||||
@@ -156,7 +158,7 @@ def group_overlapping_boxes(
|
||||
predictions (npt.NDArray[np.float64]): An array of shape `(n, 5)` containing
|
||||
the bounding boxes coordinates in format `[x1, y1, x2, y2]`
|
||||
and the confidence scores.
|
||||
iou_threshold (float, optional): The intersection-over-union threshold
|
||||
iou_threshold (float): The intersection-over-union threshold
|
||||
to use for non-maximum suppression. Defaults to 0.5.
|
||||
|
||||
Returns:
|
||||
@@ -200,7 +202,7 @@ def box_non_max_merge(
|
||||
containing the bounding boxes coordinates in format `[x1, y1, x2, y2]`,
|
||||
the confidence scores and class_ids. Omit class_id column to allow
|
||||
detections of different classes to be merged.
|
||||
iou_threshold (float, optional): The intersection-over-union threshold
|
||||
iou_threshold (float): The intersection-over-union threshold
|
||||
to use for non-maximum suppression. Defaults to 0.5.
|
||||
|
||||
Returns:
|
||||
@@ -248,16 +250,21 @@ class OverlapFilter(Enum):
|
||||
NON_MAX_SUPPRESSION = "non_max_suppression"
|
||||
NON_MAX_MERGE = "non_max_merge"
|
||||
|
||||
@classmethod
|
||||
def list(cls):
|
||||
return list(map(lambda c: c.value, cls))
|
||||
|
||||
def validate_overlap_filter(
|
||||
strategy: Union[OverlapFilter, str],
|
||||
) -> OverlapFilter:
|
||||
if isinstance(strategy, str):
|
||||
try:
|
||||
strategy = OverlapFilter(strategy.lower())
|
||||
except ValueError:
|
||||
raise ValueError(
|
||||
f"Invalid strategy value: {strategy}. Must be one of "
|
||||
f"{[e.value for e in OverlapFilter]}"
|
||||
)
|
||||
return strategy
|
||||
@classmethod
|
||||
def from_value(cls, value: Union[OverlapFilter, str]) -> OverlapFilter:
|
||||
if isinstance(value, cls):
|
||||
return value
|
||||
if isinstance(value, str):
|
||||
value = value.lower()
|
||||
try:
|
||||
return cls(value)
|
||||
except ValueError:
|
||||
raise ValueError(f"Invalid value: {value}. Must be one of {cls.list()}")
|
||||
raise ValueError(
|
||||
f"Invalid value type: {type(value)}. Must be an instance of "
|
||||
f"{cls.__name__} or str."
|
||||
)
|
||||
|
||||
@@ -4,11 +4,16 @@ from typing import Callable, Optional, Tuple, Union
|
||||
|
||||
import numpy as np
|
||||
|
||||
from supervision.config import ORIENTED_BOX_COORDINATES
|
||||
from supervision.detection.core import Detections
|
||||
from supervision.detection.overlap_filter import OverlapFilter, validate_overlap_filter
|
||||
from supervision.detection.utils import move_boxes, move_masks
|
||||
from supervision.detection.overlap_filter import OverlapFilter
|
||||
from supervision.detection.utils import move_boxes, move_masks, move_oriented_boxes
|
||||
from supervision.utils.image import crop_image
|
||||
from supervision.utils.internal import SupervisionWarnings
|
||||
from supervision.utils.internal import (
|
||||
SupervisionWarnings,
|
||||
deprecated_parameter,
|
||||
warn_deprecated,
|
||||
)
|
||||
|
||||
|
||||
def move_detections(
|
||||
@@ -28,6 +33,10 @@ def move_detections(
|
||||
(sv.Detections) repositioned Detections object.
|
||||
"""
|
||||
detections.xyxy = move_boxes(xyxy=detections.xyxy, offset=offset)
|
||||
if ORIENTED_BOX_COORDINATES in detections.data:
|
||||
detections.data[ORIENTED_BOX_COORDINATES] = move_oriented_boxes(
|
||||
xyxyxyxy=detections.data[ORIENTED_BOX_COORDINATES], offset=offset
|
||||
)
|
||||
if detections.mask is not None:
|
||||
if resolution_wh is None:
|
||||
raise ValueError(
|
||||
@@ -49,11 +58,16 @@ class InferenceSlicer:
|
||||
slice, and then merging the detections.
|
||||
|
||||
Args:
|
||||
slice_wh (Tuple[int, int]): Dimensions of each slice in the format
|
||||
`(width, height)`.
|
||||
overlap_ratio_wh (Tuple[float, float]): Overlap ratio between consecutive
|
||||
slices in the format `(width_ratio, height_ratio)`.
|
||||
overlap_filter_strategy (Union[OverlapFilter, str]): Strategy for
|
||||
slice_wh (Tuple[int, int]): Dimensions of each slice measured in pixels. The
|
||||
tuple should be in the format `(width, height)`.
|
||||
overlap_ratio_wh (Optional[Tuple[float, float]]): A tuple representing the
|
||||
desired overlap ratio for width and height between consecutive slices.
|
||||
Each value should be in the range [0, 1), where 0 means no overlap and
|
||||
a value close to 1 means high overlap.
|
||||
overlap_wh (Optional[Tuple[int, int]]): A tuple representing the desired
|
||||
overlap for width and height between consecutive slices measured in pixels.
|
||||
Each value should be greater than or equal to 0.
|
||||
overlap_filter (Union[OverlapFilter, str]): Strategy for
|
||||
filtering or merging overlapping detections in slices.
|
||||
iou_threshold (float): Intersection over Union (IoU) threshold
|
||||
used when filtering by overlap.
|
||||
@@ -68,23 +82,37 @@ class InferenceSlicer:
|
||||
not a multiple of the slice's width or height minus the overlap.
|
||||
"""
|
||||
|
||||
@deprecated_parameter(
|
||||
old_parameter="overlap_filter_strategy",
|
||||
new_parameter="overlap_filter",
|
||||
map_function=lambda x: x,
|
||||
warning_message="`{old_parameter}` in `{function_name}` is deprecated and will "
|
||||
"be removed in `supervision-0.27.0`. Use '{new_parameter}' "
|
||||
"instead.",
|
||||
)
|
||||
def __init__(
|
||||
self,
|
||||
callback: Callable[[np.ndarray], Detections],
|
||||
slice_wh: Tuple[int, int] = (320, 320),
|
||||
overlap_ratio_wh: Tuple[float, float] = (0.2, 0.2),
|
||||
overlap_filter_strategy: Union[
|
||||
OverlapFilter, str
|
||||
] = OverlapFilter.NON_MAX_SUPPRESSION,
|
||||
overlap_ratio_wh: Optional[Tuple[float, float]] = (0.2, 0.2),
|
||||
overlap_wh: Optional[Tuple[int, int]] = None,
|
||||
overlap_filter: Union[OverlapFilter, str] = OverlapFilter.NON_MAX_SUPPRESSION,
|
||||
iou_threshold: float = 0.5,
|
||||
thread_workers: int = 1,
|
||||
):
|
||||
overlap_filter_strategy = validate_overlap_filter(overlap_filter_strategy)
|
||||
if overlap_ratio_wh is not None:
|
||||
warn_deprecated(
|
||||
"`overlap_ratio_wh` in `InferenceSlicer.__init__` is deprecated and "
|
||||
"will be removed in `supervision-0.27.0`. Use `overlap_wh` instead."
|
||||
)
|
||||
|
||||
self._validate_overlap(overlap_ratio_wh, overlap_wh)
|
||||
self.overlap_ratio_wh = overlap_ratio_wh
|
||||
self.overlap_wh = overlap_wh
|
||||
|
||||
self.slice_wh = slice_wh
|
||||
self.overlap_ratio_wh = overlap_ratio_wh
|
||||
self.iou_threshold = iou_threshold
|
||||
self.overlap_filter_strategy = overlap_filter_strategy
|
||||
self.overlap_filter = OverlapFilter.from_value(overlap_filter)
|
||||
self.callback = callback
|
||||
self.thread_workers = thread_workers
|
||||
|
||||
@@ -129,6 +157,7 @@ class InferenceSlicer:
|
||||
resolution_wh=resolution_wh,
|
||||
slice_wh=self.slice_wh,
|
||||
overlap_ratio_wh=self.overlap_ratio_wh,
|
||||
overlap_wh=self.overlap_wh,
|
||||
)
|
||||
|
||||
with ThreadPoolExecutor(max_workers=self.thread_workers) as executor:
|
||||
@@ -139,15 +168,15 @@ class InferenceSlicer:
|
||||
detections_list.append(future.result())
|
||||
|
||||
merged = Detections.merge(detections_list=detections_list)
|
||||
if self.overlap_filter_strategy == OverlapFilter.NONE:
|
||||
if self.overlap_filter == OverlapFilter.NONE:
|
||||
return merged
|
||||
elif self.overlap_filter_strategy == OverlapFilter.NON_MAX_SUPPRESSION:
|
||||
elif self.overlap_filter == OverlapFilter.NON_MAX_SUPPRESSION:
|
||||
return merged.with_nms(threshold=self.iou_threshold)
|
||||
elif self.overlap_filter_strategy == OverlapFilter.NON_MAX_MERGE:
|
||||
elif self.overlap_filter == OverlapFilter.NON_MAX_MERGE:
|
||||
return merged.with_nmm(threshold=self.iou_threshold)
|
||||
else:
|
||||
warnings.warn(
|
||||
f"Invalid overlap filter strategy: {self.overlap_filter_strategy}",
|
||||
f"Invalid overlap filter strategy: {self.overlap_filter}",
|
||||
category=SupervisionWarnings,
|
||||
)
|
||||
return merged
|
||||
@@ -177,7 +206,8 @@ class InferenceSlicer:
|
||||
def _generate_offset(
|
||||
resolution_wh: Tuple[int, int],
|
||||
slice_wh: Tuple[int, int],
|
||||
overlap_ratio_wh: Tuple[float, float],
|
||||
overlap_ratio_wh: Optional[Tuple[float, float]],
|
||||
overlap_wh: Optional[Tuple[int, int]],
|
||||
) -> np.ndarray:
|
||||
"""
|
||||
Generate offset coordinates for slicing an image based on the given resolution,
|
||||
@@ -186,12 +216,15 @@ class InferenceSlicer:
|
||||
Args:
|
||||
resolution_wh (Tuple[int, int]): A tuple representing the width and height
|
||||
of the image to be sliced.
|
||||
slice_wh (Tuple[int, int]): A tuple representing the desired width and
|
||||
height of each slice.
|
||||
overlap_ratio_wh (Tuple[float, float]): A tuple representing the desired
|
||||
overlap ratio for width and height between consecutive slices. Each
|
||||
value should be in the range [0, 1), where 0 means no overlap and a
|
||||
value close to 1 means high overlap.
|
||||
slice_wh (Tuple[int, int]): Dimensions of each slice measured in pixels. The
|
||||
tuple should be in the format `(width, height)`.
|
||||
overlap_ratio_wh (Optional[Tuple[float, float]]): A tuple representing the
|
||||
desired overlap ratio for width and height between consecutive slices.
|
||||
Each value should be in the range [0, 1), where 0 means no overlap and
|
||||
a value close to 1 means high overlap.
|
||||
overlap_wh (Optional[Tuple[int, int]]): A tuple representing the desired
|
||||
overlap for width and height between consecutive slices measured in
|
||||
pixels. Each value should be greater than or equal to 0.
|
||||
|
||||
Returns:
|
||||
np.ndarray: An array of shape `(n, 4)` containing coordinates for each
|
||||
@@ -206,10 +239,19 @@ class InferenceSlicer:
|
||||
"""
|
||||
slice_width, slice_height = slice_wh
|
||||
image_width, image_height = resolution_wh
|
||||
overlap_ratio_width, overlap_ratio_height = overlap_ratio_wh
|
||||
overlap_width = (
|
||||
overlap_wh[0]
|
||||
if overlap_wh is not None
|
||||
else int(overlap_ratio_wh[0] * slice_width)
|
||||
)
|
||||
overlap_height = (
|
||||
overlap_wh[1]
|
||||
if overlap_wh is not None
|
||||
else int(overlap_ratio_wh[1] * slice_height)
|
||||
)
|
||||
|
||||
width_stride = slice_width - int(overlap_ratio_width * slice_width)
|
||||
height_stride = slice_height - int(overlap_ratio_height * slice_height)
|
||||
width_stride = slice_width - overlap_width
|
||||
height_stride = slice_height - overlap_height
|
||||
|
||||
ws = np.arange(0, image_width, width_stride)
|
||||
hs = np.arange(0, image_height, height_stride)
|
||||
@@ -221,3 +263,32 @@ class InferenceSlicer:
|
||||
offsets = np.stack([xmin, ymin, xmax, ymax], axis=-1).reshape(-1, 4)
|
||||
|
||||
return offsets
|
||||
|
||||
@staticmethod
|
||||
def _validate_overlap(
|
||||
overlap_ratio_wh: Optional[Tuple[float, float]],
|
||||
overlap_wh: Optional[Tuple[int, int]],
|
||||
) -> None:
|
||||
if overlap_ratio_wh is not None and overlap_wh is not None:
|
||||
raise ValueError(
|
||||
"Both `overlap_ratio_wh` and `overlap_wh` cannot be provided. "
|
||||
"Please provide only one of them."
|
||||
)
|
||||
if overlap_ratio_wh is None and overlap_wh is None:
|
||||
raise ValueError(
|
||||
"Either `overlap_ratio_wh` or `overlap_wh` must be provided. "
|
||||
"Please provide one of them."
|
||||
)
|
||||
|
||||
if overlap_ratio_wh is not None:
|
||||
if not (0 <= overlap_ratio_wh[0] < 1 and 0 <= overlap_ratio_wh[1] < 1):
|
||||
raise ValueError(
|
||||
"Overlap ratios must be in the range [0, 1). "
|
||||
f"Received: {overlap_ratio_wh}"
|
||||
)
|
||||
if overlap_wh is not None:
|
||||
if not (overlap_wh[0] >= 0 and overlap_wh[1] >= 0):
|
||||
raise ValueError(
|
||||
"Overlap values must be greater than or equal to 0. "
|
||||
f"Received: {overlap_wh}"
|
||||
)
|
||||
|
||||
@@ -12,7 +12,7 @@ from supervision.draw.color import Color
|
||||
from supervision.draw.utils import draw_polygon, draw_text
|
||||
from supervision.geometry.core import Position
|
||||
from supervision.geometry.utils import get_polygon_center
|
||||
from supervision.utils.internal import SupervisionWarnings, deprecated_parameter
|
||||
from supervision.utils.internal import SupervisionWarnings
|
||||
|
||||
|
||||
class PolygonZone:
|
||||
@@ -30,14 +30,6 @@ class PolygonZone:
|
||||
mask (np.ndarray): The 2D bool mask for the polygon zone
|
||||
"""
|
||||
|
||||
@deprecated_parameter(
|
||||
old_parameter="triggering_position",
|
||||
new_parameter="triggering_anchors",
|
||||
map_function=lambda x: [x],
|
||||
warning_message="`{old_parameter}` in `{function_name}` is deprecated and will "
|
||||
"be remove in `supervision-0.23.0`. Use '{new_parameter}' "
|
||||
"instead.",
|
||||
)
|
||||
def __init__(
|
||||
self,
|
||||
polygon: npt.NDArray[np.int64],
|
||||
@@ -147,7 +139,7 @@ class PolygonZoneAnnotator:
|
||||
|
||||
Parameters:
|
||||
scene (np.ndarray): The image on which the polygon zone will be annotated
|
||||
label (Optional[str]): An optional label for the count of detected objects
|
||||
label (Optional[str]): A label for the count of detected objects
|
||||
within the polygon zone (default: None)
|
||||
|
||||
Returns:
|
||||
|
||||
@@ -41,7 +41,7 @@ class DetectionsSmoother:
|
||||
tracker = sv.ByteTrack(frame_rate=video_info.fps)
|
||||
smoother = sv.DetectionsSmoother()
|
||||
|
||||
annotator = sv.BoundingBoxAnnotator()
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
|
||||
with sv.VideoSink(<TARGET_FILE_PATH>, video_info=video_info) as sink:
|
||||
for frame in frame_generator:
|
||||
@@ -50,7 +50,7 @@ class DetectionsSmoother:
|
||||
detections = tracker.update_with_detections(detections)
|
||||
detections = smoother.update_with_detections(detections)
|
||||
|
||||
annotated_frame = bounding_box_annotator.annotate(frame.copy(), detections)
|
||||
annotated_frame = box_annotator.annotate(frame.copy(), detections)
|
||||
sink.write_frame(annotated_frame)
|
||||
```
|
||||
""" # noqa: E501 // docs
|
||||
|
||||
@@ -0,0 +1,247 @@
|
||||
import io
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
import numpy as np
|
||||
from PIL import Image
|
||||
|
||||
from supervision.config import CLASS_NAME_DATA_FIELD
|
||||
from supervision.detection.utils import mask_to_xyxy
|
||||
|
||||
|
||||
def process_transformers_detection_result(
|
||||
detection_result: dict, id2label: Optional[Dict[int, str]]
|
||||
) -> dict:
|
||||
"""
|
||||
Process the result of Transformers object detection functions such as
|
||||
`post_process` (v4) and `post_process_detection` (v5).
|
||||
|
||||
Args:
|
||||
detection_result (dict): Dictionary containing detection results with keys
|
||||
'boxes', 'labels', and 'scores'.
|
||||
id2label (Optional[Dict[int, str]]): A dictionary mapping class IDs to labels,
|
||||
typically part of the `transformers` model configuration. If provided, the
|
||||
resulting dictionary will include class names.
|
||||
|
||||
Returns:
|
||||
dict: Processed detection result including bounding boxes, confidence scores,
|
||||
class IDs, and data.
|
||||
"""
|
||||
class_ids = detection_result["labels"].cpu().detach().numpy().astype(int)
|
||||
data = append_class_names_to_data(class_ids, id2label, {})
|
||||
|
||||
return dict(
|
||||
xyxy=detection_result["boxes"].cpu().detach().numpy(),
|
||||
confidence=detection_result["scores"].cpu().detach().numpy(),
|
||||
class_id=class_ids,
|
||||
data=data,
|
||||
)
|
||||
|
||||
|
||||
def process_transformers_v4_segmentation_result(
|
||||
segmentation_result: dict, id2label: Optional[Dict[int, str]]
|
||||
) -> dict:
|
||||
"""
|
||||
Process the result of Transformers segmentation functions such as
|
||||
`post_process_panoptic`, `post_process_segmentation`, and `post_process_instance`
|
||||
(v4).
|
||||
|
||||
Args:
|
||||
segmentation_result (dict): Dictionary containing segmentation results with keys
|
||||
'masks', 'labels', and 'scores'.
|
||||
id2label (Optional[Dict[int, str]]): A dictionary mapping class IDs to labels,
|
||||
typically part of the `transformers` model configuration. If provided, the
|
||||
resulting dictionary will include class names.
|
||||
|
||||
Returns:
|
||||
dict: Processed segmentation result including bounding boxes, masks, confidence
|
||||
scores, class IDs, and data.
|
||||
"""
|
||||
if "png_string" in segmentation_result:
|
||||
return process_transformers_v4_panoptic_segmentation_result(
|
||||
segmentation_result, id2label
|
||||
)
|
||||
else:
|
||||
boxes = None
|
||||
if "boxes" in segmentation_result:
|
||||
boxes = segmentation_result["boxes"].cpu().detach().numpy()
|
||||
masks = segmentation_result["masks"].cpu().detach().numpy().astype(bool)
|
||||
class_ids = segmentation_result["labels"].cpu().detach().numpy().astype(int)
|
||||
|
||||
return dict(
|
||||
xyxy=boxes if boxes is not None else mask_to_xyxy(masks),
|
||||
mask=np.squeeze(masks, axis=1) if boxes is not None else masks,
|
||||
confidence=segmentation_result["scores"].cpu().detach().numpy(),
|
||||
class_id=class_ids,
|
||||
data=append_class_names_to_data(class_ids, id2label, {}),
|
||||
)
|
||||
|
||||
|
||||
def process_transformers_v5_segmentation_result(
|
||||
segmentation_result: dict, id2label: Optional[Dict[int, str]]
|
||||
) -> dict:
|
||||
"""
|
||||
Process the result of Transformers segmentation functions such as
|
||||
`post_process_semantic_segmentation`, `post_process_instance_segmentation`, and
|
||||
`post_process_panoptic_segmentation` (v5).
|
||||
|
||||
Args:
|
||||
segmentation_result (Union[dict, np.ndarray]): Either a dictionary containing
|
||||
segmentation results or an ndarray representing a segmentation map.
|
||||
id2label (Optional[Dict[int, str]]): A dictionary mapping class IDs to labels,
|
||||
typically part of the `transformers` model configuration. If provided, the
|
||||
resulting dictionary will include class names.
|
||||
|
||||
Returns:
|
||||
dict: Processed segmentation result including bounding boxes, masks, confidence
|
||||
scores, class IDs, and data.
|
||||
"""
|
||||
if segmentation_result.__class__.__name__ == "Tensor":
|
||||
segmentation_array = segmentation_result.cpu().detach().numpy()
|
||||
return process_transformers_v5_panoptic_segmentation_result(
|
||||
segmentation_array, id2label
|
||||
)
|
||||
|
||||
return process_transformers_v5_semantic_or_instance_segmentation_result(
|
||||
segmentation_result, id2label
|
||||
)
|
||||
|
||||
|
||||
def process_transformers_v5_semantic_or_instance_segmentation_result(
|
||||
segmentation_result: dict, id2label: Optional[Dict[int, str]]
|
||||
) -> dict:
|
||||
"""
|
||||
Process the result of Transformers segmentation functions such as
|
||||
`post_process_semantic_segmentation` and `post_process_instance_segmentation` (v5).
|
||||
|
||||
Args:
|
||||
segmentation_result (dict): Dictionary containing segmentation results with keys
|
||||
`segments_info` and `segmentation`.
|
||||
id2label (Optional[Dict[int, str]]): A dictionary mapping class IDs to labels,
|
||||
typically part of the `transformers` model configuration. If provided, the
|
||||
resulting dictionary will include class names.
|
||||
|
||||
Returns:
|
||||
dict: Processed segmentation result including bounding boxes, masks, confidence
|
||||
scores, class IDs, and data.
|
||||
"""
|
||||
segments_info = segmentation_result["segments_info"]
|
||||
scores = np.array([segment["score"] for segment in segments_info])
|
||||
class_ids = np.array([segment["label_id"] for segment in segments_info])
|
||||
segmentation_array = segmentation_result["segmentation"].cpu().detach().numpy()
|
||||
masks = np.array(
|
||||
[segmentation_array == segment["id"] for segment in segments_info]
|
||||
).astype(bool)
|
||||
data = append_class_names_to_data(class_ids, id2label, {})
|
||||
|
||||
return dict(
|
||||
xyxy=mask_to_xyxy(masks),
|
||||
mask=masks,
|
||||
confidence=scores,
|
||||
class_id=class_ids,
|
||||
data=data,
|
||||
)
|
||||
|
||||
|
||||
def process_transformers_v4_panoptic_segmentation_result(
|
||||
segmentation_result: dict, id2label: Optional[Dict[int, str]]
|
||||
) -> dict:
|
||||
"""
|
||||
Process the result of the Transformers function `post_process_panoptic` (v4).
|
||||
|
||||
Args:
|
||||
segmentation_result (dict): Dictionary containing segmentation results with keys
|
||||
such as 'png_string' and 'segments_info'.
|
||||
id2label (Optional[Dict[int, str]]): A dictionary mapping class IDs to labels,
|
||||
typically part of the `transformers` model configuration. If provided, the
|
||||
resulting dictionary will include class names.
|
||||
|
||||
Returns:
|
||||
dict: Processed segmentation result including bounding boxes, masks,
|
||||
class IDs, and data.
|
||||
"""
|
||||
segments_info = segmentation_result["segments_info"]
|
||||
png_string = segmentation_result["png_string"]
|
||||
class_ids = np.array([segment["category_id"] for segment in segments_info])
|
||||
segmentation_array = png_string_to_segmentation_array(png_string=png_string)
|
||||
masks = np.array(
|
||||
[segmentation_array == segment["id"] for segment in segments_info]
|
||||
).astype(bool)
|
||||
data = append_class_names_to_data(class_ids, id2label, {})
|
||||
|
||||
return dict(
|
||||
xyxy=mask_to_xyxy(masks),
|
||||
mask=masks,
|
||||
class_id=class_ids,
|
||||
data=data,
|
||||
)
|
||||
|
||||
|
||||
def process_transformers_v5_panoptic_segmentation_result(
|
||||
segmentation_array: np.ndarray, id2label: Optional[Dict[int, str]]
|
||||
) -> dict:
|
||||
"""
|
||||
Process the result of the Transformers function
|
||||
`post_process_panoptic_segmentation` (v5).
|
||||
|
||||
Args:
|
||||
segmentation_array (np.ndarray): Segmentation array.
|
||||
id2label (Optional[Dict[int, str]]): A dictionary mapping class IDs to labels,
|
||||
typically part of the `transformers` model configuration. If provided, the
|
||||
resulting dictionary will include class names.
|
||||
|
||||
Returns:
|
||||
dict: Processed segmentation result including bounding boxes, masks,
|
||||
class IDs, and data.
|
||||
"""
|
||||
class_ids = np.unique(segmentation_array)
|
||||
masks = np.stack(
|
||||
[segmentation_array == class_id for class_id in class_ids], axis=0
|
||||
).astype(bool)
|
||||
data = append_class_names_to_data(class_ids, id2label, {})
|
||||
return dict(xyxy=mask_to_xyxy(masks), mask=masks, class_id=class_ids, data=data)
|
||||
|
||||
|
||||
def png_string_to_segmentation_array(png_string: bytes) -> np.ndarray:
|
||||
"""
|
||||
Convert a PNG byte string to a label mask array.
|
||||
|
||||
Args:
|
||||
png_string (bytes): A byte string representing the PNG image.
|
||||
|
||||
Returns:
|
||||
np.ndarray: A label mask array with shape (H, W), where H and W
|
||||
are the height and width of the image. Each unique value in the array
|
||||
represents a different object or category.
|
||||
"""
|
||||
image = Image.open(io.BytesIO(png_string))
|
||||
mask = np.array(image, dtype=np.uint8)
|
||||
return mask[:, :, 0]
|
||||
|
||||
|
||||
def append_class_names_to_data(
|
||||
class_ids: np.ndarray,
|
||||
id2label: Optional[Dict[int, str]],
|
||||
data: Optional[Dict[str, Any]] = None,
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Helper function to create or append to a data dictionary with class names if
|
||||
available.
|
||||
|
||||
Args:
|
||||
class_ids (np.ndarray): Array of class IDs.
|
||||
id2label (Optional[Dict[int, str]]): A dictionary mapping class IDs to labels,
|
||||
typically part of the `transformers` model configuration. If provided, the
|
||||
resulting dictionary will include class names.
|
||||
data (Optional[Dict[str, Any]]): An existing data dictionary to append to.
|
||||
|
||||
Returns:
|
||||
Dict[str, Any]: Dictionary containing class names if id2label is provided.
|
||||
"""
|
||||
if data is None:
|
||||
data = {}
|
||||
|
||||
if id2label is not None:
|
||||
class_names = np.array([id2label[class_id] for class_id in class_ids])
|
||||
data[CLASS_NAME_DATA_FIELD] = class_names
|
||||
|
||||
return data
|
||||
@@ -106,7 +106,7 @@ def mask_iou_batch(
|
||||
Args:
|
||||
masks_true (np.ndarray): 3D `np.ndarray` representing ground-truth masks.
|
||||
masks_detection (np.ndarray): 3D `np.ndarray` representing detection masks.
|
||||
memory_limit (int, optional): memory limit in MB, default is 1024 * 5 MB (5GB).
|
||||
memory_limit (int): memory limit in MB, default is 1024 * 5 MB (5GB).
|
||||
|
||||
Returns:
|
||||
np.ndarray: Pairwise IoU of masks from `masks_true` and `masks_detection`.
|
||||
@@ -228,10 +228,78 @@ def pad_boxes(xyxy: np.ndarray, px: int, py: Optional[int] = None) -> np.ndarray
|
||||
return result
|
||||
|
||||
|
||||
def xywh_to_xyxy(boxes_xywh: np.ndarray) -> np.ndarray:
|
||||
xyxy = boxes_xywh.copy()
|
||||
xyxy[:, 2] = boxes_xywh[:, 0] + boxes_xywh[:, 2]
|
||||
xyxy[:, 3] = boxes_xywh[:, 1] + boxes_xywh[:, 3]
|
||||
def xywh_to_xyxy(xywh: np.ndarray) -> np.ndarray:
|
||||
"""
|
||||
Converts bounding box coordinates from `(x, y, width, height)`
|
||||
format to `(x_min, y_min, x_max, y_max)` format.
|
||||
|
||||
Args:
|
||||
xywh (np.ndarray): A numpy array of shape `(N, 4)` where each row
|
||||
corresponds to a bounding box in the format `(x, y, width, height)`.
|
||||
|
||||
Returns:
|
||||
np.ndarray: A numpy array of shape `(N, 4)` where each row corresponds
|
||||
to a bounding box in the format `(x_min, y_min, x_max, y_max)`.
|
||||
|
||||
Examples:
|
||||
```python
|
||||
import numpy as np
|
||||
import supervision as sv
|
||||
|
||||
xywh = np.array([
|
||||
[10, 20, 30, 40],
|
||||
[15, 25, 35, 45]
|
||||
])
|
||||
|
||||
sv.xywh_to_xyxy(xywh=xywh)
|
||||
# array([
|
||||
# [10, 20, 40, 60],
|
||||
# [15, 25, 50, 70]
|
||||
# ])
|
||||
```
|
||||
"""
|
||||
xyxy = xywh.copy()
|
||||
xyxy[:, 2] = xywh[:, 0] + xywh[:, 2]
|
||||
xyxy[:, 3] = xywh[:, 1] + xywh[:, 3]
|
||||
return xyxy
|
||||
|
||||
|
||||
def xcycwh_to_xyxy(xcycwh: np.ndarray) -> np.ndarray:
|
||||
"""
|
||||
Converts bounding box coordinates from `(center_x, center_y, width, height)`
|
||||
format to `(x_min, y_min, x_max, y_max)` format.
|
||||
|
||||
Args:
|
||||
xcycwh (np.ndarray): A numpy array of shape `(N, 4)` where each row
|
||||
corresponds to a bounding box in the format `(center_x, center_y, width,
|
||||
height)`.
|
||||
|
||||
Returns:
|
||||
np.ndarray: A numpy array of shape `(N, 4)` where each row corresponds
|
||||
to a bounding box in the format `(x_min, y_min, x_max, y_max)`.
|
||||
|
||||
Examples:
|
||||
```python
|
||||
import numpy as np
|
||||
import supervision as sv
|
||||
|
||||
xcycwh = np.array([
|
||||
[50, 50, 20, 30],
|
||||
[30, 40, 10, 15]
|
||||
])
|
||||
|
||||
sv.xcycwh_to_xyxy(xcycwh=xcycwh)
|
||||
# array([
|
||||
# [40, 35, 60, 65],
|
||||
# [25, 32.5, 35, 47.5]
|
||||
# ])
|
||||
```
|
||||
"""
|
||||
xyxy = xcycwh.copy()
|
||||
xyxy[:, 0] = xcycwh[:, 0] - xcycwh[:, 2] / 2
|
||||
xyxy[:, 1] = xcycwh[:, 1] - xcycwh[:, 3] / 2
|
||||
xyxy[:, 2] = xcycwh[:, 0] + xcycwh[:, 2] / 2
|
||||
xyxy[:, 3] = xcycwh[:, 1] + xcycwh[:, 3] / 2
|
||||
return xyxy
|
||||
|
||||
|
||||
@@ -528,6 +596,61 @@ def move_boxes(
|
||||
return xyxy + np.hstack([offset, offset])
|
||||
|
||||
|
||||
def move_oriented_boxes(
|
||||
xyxyxyxy: npt.NDArray[np.float64], offset: npt.NDArray[np.int32]
|
||||
) -> npt.NDArray[np.float64]:
|
||||
"""
|
||||
Parameters:
|
||||
xyxyxyxy (npt.NDArray[np.float64]): An array of shape `(n, 4, 2)` containing the
|
||||
oriented bounding boxes coordinates in format
|
||||
`[[x1, y1], [x2, y2], [x3, y3], [x3, y3]]`
|
||||
offset (np.array): An array of shape `(2,)` containing offset values in format
|
||||
is `[dx, dy]`.
|
||||
|
||||
Returns:
|
||||
npt.NDArray[np.float64]: Repositioned bounding boxes.
|
||||
|
||||
Examples:
|
||||
```python
|
||||
import numpy as np
|
||||
import supervision as sv
|
||||
|
||||
xyxyxyxy = np.array([
|
||||
[
|
||||
[20, 10],
|
||||
[10, 20],
|
||||
[20, 30],
|
||||
[30, 20]
|
||||
],
|
||||
[
|
||||
[30 ,30],
|
||||
[20, 40],
|
||||
[30, 50],
|
||||
[40, 40]
|
||||
]
|
||||
])
|
||||
offset = np.array([5, 5])
|
||||
|
||||
sv.move_oriented_boxes(xyxy=xyxy, offset=offset)
|
||||
# array([
|
||||
# [
|
||||
# [25, 15],
|
||||
# [15, 25],
|
||||
# [25, 35],
|
||||
# [35, 25]
|
||||
# ],
|
||||
# [
|
||||
# [35, 35],
|
||||
# [25, 45],
|
||||
# [35, 55],
|
||||
# [45, 45]
|
||||
# ]
|
||||
# ])
|
||||
```
|
||||
"""
|
||||
return xyxyxyxy + offset
|
||||
|
||||
|
||||
def move_masks(
|
||||
masks: npt.NDArray[np.bool_],
|
||||
offset: npt.NDArray[np.int32],
|
||||
|
||||
+10
-73
@@ -5,7 +5,7 @@ from typing import List, Tuple, Union
|
||||
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
from supervision.utils.internal import classproperty, deprecated
|
||||
from supervision.utils.internal import classproperty
|
||||
|
||||
DEFAULT_COLOR_PALETTE = [
|
||||
"A351FB",
|
||||
@@ -255,46 +255,6 @@ class Color:
|
||||
def ROBOFLOW(cls) -> Color:
|
||||
return Color.from_hex("#A351FB")
|
||||
|
||||
@classmethod
|
||||
@deprecated(
|
||||
"`Color.white()` is deprecated and will be removed in "
|
||||
"`supervision-0.22.0`. Use `Color.WHITE` instead."
|
||||
)
|
||||
def white(cls) -> Color:
|
||||
return Color.from_hex(color_hex="#ffffff")
|
||||
|
||||
@classmethod
|
||||
@deprecated(
|
||||
"`Color.black()` is deprecated and will be removed in "
|
||||
"`supervision-0.22.0`. Use `Color.BLACK` instead."
|
||||
)
|
||||
def black(cls) -> Color:
|
||||
return Color.from_hex(color_hex="#000000")
|
||||
|
||||
@classmethod
|
||||
@deprecated(
|
||||
"`Color.red()` is deprecated and will be removed in "
|
||||
"`supervision-0.22.0`. Use `Color.RED` instead."
|
||||
)
|
||||
def red(cls) -> Color:
|
||||
return Color.from_hex(color_hex="#ff0000")
|
||||
|
||||
@classmethod
|
||||
@deprecated(
|
||||
"`Color.green()` is deprecated and will be removed in "
|
||||
"`supervision-0.22.0`. Use `Color.GREEN` instead."
|
||||
)
|
||||
def green(cls) -> Color:
|
||||
return Color.from_hex(color_hex="#00ff00")
|
||||
|
||||
@classmethod
|
||||
@deprecated(
|
||||
"`Color.blue()` is deprecated and will be removed in "
|
||||
"`supervision-0.22.0`. Use `Color.BLUE` instead."
|
||||
)
|
||||
def blue(cls) -> Color:
|
||||
return Color.from_hex(color_hex="#0000ff")
|
||||
|
||||
|
||||
@dataclass
|
||||
class ColorPalette:
|
||||
@@ -346,33 +306,6 @@ class ColorPalette:
|
||||
def LEGACY(cls) -> ColorPalette:
|
||||
return ColorPalette.from_hex(color_hex_list=LEGACY_COLOR_PALETTE)
|
||||
|
||||
@classmethod
|
||||
@deprecated(
|
||||
"`ColorPalette.default()` is deprecated and will be removed in "
|
||||
"`supervision-0.22.0`. Use `Color.DEFAULT` instead."
|
||||
)
|
||||
def default(cls) -> ColorPalette:
|
||||
"""
|
||||
!!! failure "Deprecated"
|
||||
|
||||
`ColorPalette.default()` is deprecated and will be removed in
|
||||
`supervision-0.22.0`. Use `Color.DEFAULT` instead.
|
||||
|
||||
Returns a default color palette.
|
||||
|
||||
Returns:
|
||||
ColorPalette: A ColorPalette instance with default colors.
|
||||
|
||||
Example:
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
sv.ColorPalette.default()
|
||||
# ColorPalette(colors=[Color(r=255, g=64, b=64), Color(r=255, g=161, b=160), ...])
|
||||
```
|
||||
""" # noqa: E501 // docs
|
||||
return ColorPalette.from_hex(color_hex_list=DEFAULT_COLOR_PALETTE)
|
||||
|
||||
@classmethod
|
||||
def from_hex(cls, color_hex_list: List[str]) -> ColorPalette:
|
||||
"""
|
||||
@@ -419,11 +352,15 @@ class ColorPalette:
|
||||
supervision-annotator-examples/visualized_color_palette.png)
|
||||
""" # noqa: E501 // docs
|
||||
mpl_palette = plt.get_cmap(palette_name, color_count)
|
||||
colors = [
|
||||
Color(int(r * 255), int(g * 255), int(b * 255))
|
||||
for r, g, b, _ in mpl_palette.colors
|
||||
]
|
||||
return cls(colors)
|
||||
|
||||
if hasattr(mpl_palette, "colors"):
|
||||
colors = mpl_palette.colors
|
||||
else:
|
||||
colors = [mpl_palette(i / (color_count - 1)) for i in range(color_count)]
|
||||
|
||||
return cls(
|
||||
[Color(int(r * 255), int(g * 255), int(b * 255)) for r, g, b, _ in colors]
|
||||
)
|
||||
|
||||
def by_idx(self, idx: int) -> Color:
|
||||
"""
|
||||
|
||||
@@ -142,7 +142,7 @@ def draw_polygon(
|
||||
scene (np.ndarray): The scene to draw the polygon on.
|
||||
polygon (np.ndarray): The polygon to be drawn, given as a list of vertices.
|
||||
color (Color): The color of the polygon.
|
||||
thickness (int, optional): The thickness of the polygon lines, by default 2.
|
||||
thickness (int): The thickness of the polygon lines, by default 2.
|
||||
|
||||
Returns:
|
||||
np.ndarray: The scene with the polygon drawn on it.
|
||||
@@ -172,14 +172,14 @@ def draw_text(
|
||||
text (str): The text to be drawn.
|
||||
text_anchor (Point): The anchor point for the text, represented as a
|
||||
Point object with x and y attributes.
|
||||
text_color (Color, optional): The color of the text. Defaults to black.
|
||||
text_scale (float, optional): The scale of the text. Defaults to 0.5.
|
||||
text_thickness (int, optional): The thickness of the text. Defaults to 1.
|
||||
text_padding (int, optional): The amount of padding to add around the text
|
||||
text_color (Color): The color of the text. Defaults to black.
|
||||
text_scale (float): The scale of the text. Defaults to 0.5.
|
||||
text_thickness (int): The thickness of the text. Defaults to 1.
|
||||
text_padding (int): The amount of padding to add around the text
|
||||
when drawing a rectangle in the background. Defaults to 10.
|
||||
text_font (int, optional): The font to use for the text.
|
||||
text_font (int): The font to use for the text.
|
||||
Defaults to cv2.FONT_HERSHEY_SIMPLEX.
|
||||
background_color (Color, optional): The color of the background rectangle,
|
||||
background_color (Optional[Color]): The color of the background rectangle,
|
||||
if one is to be drawn. Defaults to None.
|
||||
|
||||
Returns:
|
||||
@@ -295,8 +295,8 @@ def calculate_optimal_text_scale(resolution_wh: Tuple[int, int]) -> float:
|
||||
Calculate font scale based on the resolution of an image.
|
||||
|
||||
Parameters:
|
||||
resolution_wh (Tuple[int, int]): A tuple representing the width and height
|
||||
of the image.
|
||||
resolution_wh (Tuple[int, int]): A tuple representing the width and height
|
||||
of the image.
|
||||
|
||||
Returns:
|
||||
float: The calculated font scale factor.
|
||||
|
||||
@@ -34,8 +34,8 @@ class VertexAnnotator(BaseKeyPointAnnotator):
|
||||
) -> None:
|
||||
"""
|
||||
Args:
|
||||
color (Color, optional): The color to use for annotating key points.
|
||||
radius (int, optional): The radius of the circles used to represent the key
|
||||
color (Color): The color to use for annotating key points.
|
||||
radius (int): The radius of the circles used to represent the key
|
||||
points.
|
||||
"""
|
||||
self.color = color
|
||||
@@ -78,6 +78,7 @@ class VertexAnnotator(BaseKeyPointAnnotator):
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
if len(key_points) == 0:
|
||||
return scene
|
||||
|
||||
@@ -108,8 +109,8 @@ class EdgeAnnotator(BaseKeyPointAnnotator):
|
||||
) -> None:
|
||||
"""
|
||||
Args:
|
||||
color (Color, optional): The color to use for the edges.
|
||||
thickness (int, optional): The thickness of the edges.
|
||||
color (Color): The color to use for the edges.
|
||||
thickness (int): The thickness of the edges.
|
||||
edges (Optional[List[Tuple[int, int]]]): The edges to draw.
|
||||
If set to `None`, will attempt to select automatically.
|
||||
"""
|
||||
@@ -155,6 +156,7 @@ class EdgeAnnotator(BaseKeyPointAnnotator):
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
if len(key_points) == 0:
|
||||
return scene
|
||||
|
||||
@@ -194,7 +196,7 @@ class VertexLabelAnnotator:
|
||||
def __init__(
|
||||
self,
|
||||
color: Union[Color, List[Color]] = Color.ROBOFLOW,
|
||||
text_color: Color = Color.WHITE,
|
||||
text_color: Union[Color, List[Color]] = Color.WHITE,
|
||||
text_scale: float = 0.5,
|
||||
text_thickness: int = 1,
|
||||
text_padding: int = 10,
|
||||
@@ -202,25 +204,30 @@ class VertexLabelAnnotator:
|
||||
):
|
||||
"""
|
||||
Args:
|
||||
color (Union[Color, List[Color]], optional): The color to use for each
|
||||
color (Union[Color, List[Color]]): The color to use for each
|
||||
keypoint label. If a list is provided, the colors will be used in order
|
||||
for each keypoint.
|
||||
text_color (Color, optional): The color to use for the labels.
|
||||
text_scale (float, optional): The scale of the text.
|
||||
text_thickness (int, optional): The thickness of the text.
|
||||
text_padding (int, optional): The padding around the text.
|
||||
border_radius (int, optional): The radius of the rounded corners of the
|
||||
text_color (Union[Color, List[Color]]): The color to use
|
||||
for the labels. If a list is provided, the colors will be used in order
|
||||
for each keypoint.
|
||||
text_scale (float): The scale of the text.
|
||||
text_thickness (int): The thickness of the text.
|
||||
text_padding (int): The padding around the text.
|
||||
border_radius (int): The radius of the rounded corners of the
|
||||
boxes. Set to a high value to produce circles.
|
||||
"""
|
||||
self.border_radius: int = border_radius
|
||||
self.color: Union[Color, List[Color]] = color
|
||||
self.text_color: Color = text_color
|
||||
self.text_color: Union[Color, List[Color]] = text_color
|
||||
self.text_scale: float = text_scale
|
||||
self.text_thickness: int = text_thickness
|
||||
self.text_padding: int = text_padding
|
||||
|
||||
def annotate(
|
||||
self, scene: ImageType, key_points: KeyPoints, labels: List[str] = None
|
||||
self,
|
||||
scene: ImageType,
|
||||
key_points: KeyPoints,
|
||||
labels: Optional[List[str]] = None,
|
||||
) -> ImageType:
|
||||
"""
|
||||
A class that draws labels of skeleton vertices on images. It uses specified key
|
||||
@@ -232,7 +239,7 @@ class VertexLabelAnnotator:
|
||||
`PIL.Image.Image`.
|
||||
key_points (KeyPoints): A collection of key points where each key point
|
||||
consists of x and y coordinates.
|
||||
labels (List[str], optional): A list of labels to be displayed on the
|
||||
labels (Optional[List[str]]): A list of labels to be displayed on the
|
||||
annotated image. If not provided, keypoint indices will be used.
|
||||
|
||||
Returns:
|
||||
@@ -303,6 +310,7 @@ class VertexLabelAnnotator:
|
||||

|
||||
"""
|
||||
assert isinstance(scene, np.ndarray)
|
||||
font = cv2.FONT_HERSHEY_SIMPLEX
|
||||
|
||||
skeletons_count, points_count, _ = key_points.xy.shape
|
||||
@@ -321,12 +329,19 @@ class VertexLabelAnnotator:
|
||||
skeletons_count=skeletons_count,
|
||||
)
|
||||
|
||||
text_colors = self.preprocess_and_validate_colors(
|
||||
colors=self.text_color,
|
||||
points_count=points_count,
|
||||
skeletons_count=skeletons_count,
|
||||
)
|
||||
|
||||
labels = self.preprocess_and_validate_labels(
|
||||
labels=labels, points_count=points_count, skeletons_count=skeletons_count
|
||||
)
|
||||
|
||||
anchors = anchors[mask]
|
||||
colors = colors[mask]
|
||||
text_colors = text_colors[mask]
|
||||
labels = labels[mask]
|
||||
|
||||
xyxy = np.array(
|
||||
@@ -344,7 +359,9 @@ class VertexLabelAnnotator:
|
||||
|
||||
xyxy_padded = pad_boxes(xyxy=xyxy, px=self.text_padding)
|
||||
|
||||
for text, color, box, box_padded in zip(labels, colors, xyxy, xyxy_padded):
|
||||
for text, color, text_color, box, box_padded in zip(
|
||||
labels, colors, text_colors, xyxy, xyxy_padded
|
||||
):
|
||||
draw_rounded_rectangle(
|
||||
scene=scene,
|
||||
rect=Rect.from_xyxy(box_padded),
|
||||
@@ -354,10 +371,10 @@ class VertexLabelAnnotator:
|
||||
cv2.putText(
|
||||
img=scene,
|
||||
text=text,
|
||||
org=(box[0], box[1] + self.text_padding),
|
||||
org=(box[0], box[3]),
|
||||
fontFace=font,
|
||||
fontScale=self.text_scale,
|
||||
color=self.text_color.as_rgb(),
|
||||
color=text_color.as_bgr(),
|
||||
thickness=self.text_thickness,
|
||||
lineType=cv2.LINE_AA,
|
||||
)
|
||||
@@ -389,7 +406,7 @@ class VertexLabelAnnotator:
|
||||
@staticmethod
|
||||
def preprocess_and_validate_labels(
|
||||
labels: Optional[List[str]], points_count: int, skeletons_count: int
|
||||
) -> np.array:
|
||||
) -> np.ndarray:
|
||||
if labels and len(labels) != points_count:
|
||||
raise ValueError(
|
||||
f"Number of labels ({len(labels)}) must match number of key points "
|
||||
@@ -405,7 +422,7 @@ class VertexLabelAnnotator:
|
||||
colors: Optional[Union[Color, List[Color]]],
|
||||
points_count: int,
|
||||
skeletons_count: int,
|
||||
) -> np.array:
|
||||
) -> np.ndarray:
|
||||
if isinstance(colors, list) and len(colors) != points_count:
|
||||
raise ValueError(
|
||||
f"Number of colors ({len(colors)}) must match number of key points "
|
||||
|
||||
+108
-13
@@ -88,15 +88,17 @@ class KeyPoints:
|
||||
```
|
||||
|
||||
Attributes:
|
||||
xy (np.ndarray): An array of shape `(n, 2)` containing
|
||||
the bounding boxes coordinates in format `[x1, y1]`
|
||||
xy (np.ndarray): An array of shape `(n, m, 2)` containing
|
||||
`n` detected objects, each composed of `m` equally-sized
|
||||
sets of keypoints, where each point is `[x, y]`.
|
||||
confidence (Optional[np.ndarray]): An array of shape
|
||||
`(n,)` containing the confidence scores of the keypoint keypoints.
|
||||
`(n, m)` containing the confidence scores of each keypoint.
|
||||
class_id (Optional[np.ndarray]): An array of shape
|
||||
`(n,)` containing the class ids of the keypoint keypoints.
|
||||
`(n,)` containing the class ids of the detected objects.
|
||||
data (Dict[str, Union[np.ndarray, List]]): A dictionary containing additional
|
||||
data where each key is a string representing the data type, and the value
|
||||
is either a NumPy array or a list of corresponding data.
|
||||
is either a NumPy array or a list of corresponding data of length `n`
|
||||
(one entry per detected object).
|
||||
""" # noqa: E501 // docs
|
||||
|
||||
xy: npt.NDArray[np.float32]
|
||||
@@ -132,7 +134,7 @@ class KeyPoints:
|
||||
]:
|
||||
"""
|
||||
Iterates over the Keypoint object and yield a tuple of
|
||||
`(xy, confidence, class_id, data)` for each keypoint detection.
|
||||
`(xy, confidence, class_id, data)` for each object detection.
|
||||
"""
|
||||
for i in range(len(self.xy)):
|
||||
yield (
|
||||
@@ -243,9 +245,10 @@ class KeyPoints:
|
||||
pose landmark detection inference result.
|
||||
|
||||
Args:
|
||||
mediapipe_results (Union[PoseLandmarkerResult, SolutionOutputs]):
|
||||
The output results from Mediapipe. It supports both: the inference
|
||||
result `PoseLandmarker` and the legacy one from `Pose`.
|
||||
mediapipe_results (Union[PoseLandmarkerResult, FaceLandmarkerResult, SolutionOutputs]):
|
||||
The output results from Mediapipe. It support pose and face landmarks
|
||||
from `PoseLandmaker`, `FaceLandmarker` and the legacy ones
|
||||
from `Pose` and `FaceMesh`.
|
||||
resolution_wh (Tuple[int, int]): A tuple of the form `(width, height)`
|
||||
representing the resolution of the frame.
|
||||
|
||||
@@ -283,14 +286,55 @@ class KeyPoints:
|
||||
key_points = sv.KeyPoints.from_mediapipe(
|
||||
pose_landmarker_result, (image_width, image_height))
|
||||
```
|
||||
|
||||
```python
|
||||
import cv2
|
||||
import mediapipe as mp
|
||||
import supervision as sv
|
||||
|
||||
image = cv2.imread(<SOURCE_IMAGE_PATH>)
|
||||
image_height, image_width, _ = image.shape
|
||||
mediapipe_image = mp.Image(
|
||||
image_format=mp.ImageFormat.SRGB,
|
||||
data=cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
|
||||
|
||||
options = mp.tasks.vision.FaceLandmarkerOptions(
|
||||
base_options=mp.tasks.BaseOptions(
|
||||
model_asset_path="face_landmarker.task"
|
||||
),
|
||||
output_face_blendshapes=True,
|
||||
output_facial_transformation_matrixes=True,
|
||||
num_faces=2)
|
||||
|
||||
FaceLandmarker = mp.tasks.vision.FaceLandmarker
|
||||
with FaceLandmarker.create_from_options(options) as landmarker:
|
||||
face_landmarker_result = landmarker.detect(mediapipe_image)
|
||||
|
||||
key_points = sv.KeyPoints.from_mediapipe(
|
||||
face_landmarker_result, (image_width, image_height))
|
||||
```
|
||||
""" # noqa: E501 // docs
|
||||
results = mediapipe_results.pose_landmarks
|
||||
if not isinstance(mediapipe_results.pose_landmarks, list):
|
||||
if mediapipe_results.pose_landmarks is None:
|
||||
if hasattr(mediapipe_results, "pose_landmarks"):
|
||||
results = mediapipe_results.pose_landmarks
|
||||
if not isinstance(mediapipe_results.pose_landmarks, list):
|
||||
if mediapipe_results.pose_landmarks is None:
|
||||
results = []
|
||||
else:
|
||||
results = [
|
||||
[
|
||||
landmark
|
||||
for landmark in mediapipe_results.pose_landmarks.landmark
|
||||
]
|
||||
]
|
||||
elif hasattr(mediapipe_results, "face_landmarks"):
|
||||
results = mediapipe_results.face_landmarks
|
||||
elif hasattr(mediapipe_results, "multi_face_landmarks"):
|
||||
if mediapipe_results.multi_face_landmarks is None:
|
||||
results = []
|
||||
else:
|
||||
results = [
|
||||
[landmark for landmark in mediapipe_results.pose_landmarks.landmark]
|
||||
face_landmark.landmark
|
||||
for face_landmark in mediapipe_results.multi_face_landmarks
|
||||
]
|
||||
|
||||
if len(results) == 0:
|
||||
@@ -414,6 +458,57 @@ class KeyPoints:
|
||||
data=data,
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def from_detectron2(cls, detectron2_results) -> KeyPoints:
|
||||
"""
|
||||
Create a `sv.KeyPoints` object from the
|
||||
[Detectron2](https://github.com/facebookresearch/detectron2) inference result.
|
||||
|
||||
Args:
|
||||
detectron2_results: The output of a
|
||||
Detectron2 model containing instances with prediction data.
|
||||
|
||||
Returns:
|
||||
A `sv.KeyPoints` object containing the keypoint coordinates, class IDs,
|
||||
and class names, and confidences of each keypoint.
|
||||
|
||||
Example:
|
||||
```python
|
||||
import cv2
|
||||
import supervision as sv
|
||||
from detectron2.engine import DefaultPredictor
|
||||
from detectron2.config import get_cfg
|
||||
|
||||
|
||||
image = cv2.imread(<SOURCE_IMAGE_PATH>)
|
||||
cfg = get_cfg()
|
||||
cfg.merge_from_file(<CONFIG_PATH>)
|
||||
cfg.MODEL.WEIGHTS = <WEIGHTS_PATH>
|
||||
predictor = DefaultPredictor(cfg)
|
||||
|
||||
result = predictor(image)
|
||||
keypoints = sv.KeyPoints.from_detectron2(result)
|
||||
```
|
||||
"""
|
||||
|
||||
if hasattr(detectron2_results["instances"], "pred_keypoints"):
|
||||
if detectron2_results["instances"].pred_keypoints.cpu().numpy().size == 0:
|
||||
return cls.empty()
|
||||
return cls(
|
||||
xy=detectron2_results["instances"]
|
||||
.pred_keypoints.cpu()
|
||||
.numpy()[:, :, :2],
|
||||
confidence=detectron2_results["instances"]
|
||||
.pred_keypoints.cpu()
|
||||
.numpy()[:, :, 2],
|
||||
class_id=detectron2_results["instances"]
|
||||
.pred_classes.cpu()
|
||||
.numpy()
|
||||
.astype(int),
|
||||
)
|
||||
else:
|
||||
return cls.empty()
|
||||
|
||||
def __getitem__(
|
||||
self, index: Union[int, slice, List[int], np.ndarray, str]
|
||||
) -> Union[KeyPoints, List, np.ndarray, None]:
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,10 @@
|
||||
from supervision.metrics.core import CLASS_ID_NONE, Metric, MetricTarget
|
||||
from supervision.metrics.mean_average_precision import (
|
||||
MeanAveragePrecision,
|
||||
MeanAveragePrecisionResult,
|
||||
)
|
||||
from supervision.metrics.utils.object_size import (
|
||||
ObjectSizeCategory,
|
||||
get_detection_size_category,
|
||||
get_object_size_category,
|
||||
)
|
||||
|
||||
@@ -0,0 +1,50 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from abc import ABC, abstractmethod
|
||||
from enum import Enum
|
||||
from typing import Any
|
||||
|
||||
CLASS_ID_NONE = -1
|
||||
"""Used by metrics module as class ID, when none is present"""
|
||||
|
||||
|
||||
class Metric(ABC):
|
||||
"""
|
||||
The base class for all supervision metrics.
|
||||
"""
|
||||
|
||||
@abstractmethod
|
||||
def update(self, *args, **kwargs) -> "Metric":
|
||||
"""
|
||||
Add data to the metric, without computing the result.
|
||||
Return the metric itself to allow method chaining.
|
||||
"""
|
||||
raise NotImplementedError
|
||||
|
||||
@abstractmethod
|
||||
def reset(self) -> None:
|
||||
"""
|
||||
Reset internal metric state.
|
||||
"""
|
||||
raise NotImplementedError
|
||||
|
||||
@abstractmethod
|
||||
def compute(self, *args, **kwargs) -> Any:
|
||||
"""
|
||||
Compute the metric from the internal state and return the result.
|
||||
"""
|
||||
raise NotImplementedError
|
||||
|
||||
|
||||
class MetricTarget(Enum):
|
||||
"""
|
||||
Specifies what type of detection is used to compute the metric.
|
||||
|
||||
* BOXES: xyxy bounding boxes
|
||||
* MASKS: Binary masks
|
||||
* ORIENTED_BOUNDING_BOXES: Oriented bounding boxes (OBB)
|
||||
"""
|
||||
|
||||
BOXES = "boxes"
|
||||
MASKS = "masks"
|
||||
ORIENTED_BOUNDING_BOXES = "obb"
|
||||
@@ -391,11 +391,10 @@ class ConfusionMatrix:
|
||||
```
|
||||
"""
|
||||
predictions, targets = [], []
|
||||
for img_name, img in dataset.images.items():
|
||||
predictions_batch = callback(img)
|
||||
for _, image, annotation in dataset:
|
||||
predictions_batch = callback(image)
|
||||
predictions.append(predictions_batch)
|
||||
targets_batch = dataset.annotations[img_name]
|
||||
targets.append(targets_batch)
|
||||
targets.append(annotation)
|
||||
return cls.from_detections(
|
||||
predictions=predictions,
|
||||
targets=targets,
|
||||
@@ -604,11 +603,10 @@ class MeanAveragePrecision:
|
||||
```
|
||||
"""
|
||||
predictions, targets = [], []
|
||||
for img_name, img in dataset.images.items():
|
||||
predictions_batch = callback(img)
|
||||
for _, image, annotation in dataset:
|
||||
predictions_batch = callback(image)
|
||||
predictions.append(predictions_batch)
|
||||
targets_batch = dataset.annotations[img_name]
|
||||
targets.append(targets_batch)
|
||||
targets.append(annotation)
|
||||
return cls.from_detections(
|
||||
predictions=predictions,
|
||||
targets=targets,
|
||||
@@ -666,12 +664,12 @@ class MeanAveragePrecision:
|
||||
np.array([[1.0, 1.0, 2.0, 2.0, 2, 0.8]])
|
||||
]
|
||||
|
||||
mean_average_precison = sv.MeanAveragePrecision.from_tensors(
|
||||
mean_average_precision = sv.MeanAveragePrecision.from_tensors(
|
||||
predictions=predictions,
|
||||
targets=targets,
|
||||
)
|
||||
|
||||
print(mean_average_precison.map50_95)
|
||||
print(mean_average_precision.map50_95)
|
||||
# 0.6649
|
||||
```
|
||||
"""
|
||||
@@ -808,7 +806,7 @@ class MeanAveragePrecision:
|
||||
prediction_confidence (np.ndarray): Objectness value from 0-1.
|
||||
prediction_class_ids (np.ndarray): Predicted object classes.
|
||||
true_class_ids (np.ndarray): True object classes.
|
||||
eps (float, optional): Small value to prevent division by zero.
|
||||
eps (float): Small value to prevent division by zero.
|
||||
|
||||
Returns:
|
||||
np.ndarray: Average precision for different IoU levels.
|
||||
|
||||
@@ -0,0 +1,552 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from copy import deepcopy
|
||||
from dataclasses import dataclass
|
||||
from typing import TYPE_CHECKING, List, Optional, Union
|
||||
|
||||
import numpy as np
|
||||
from matplotlib import pyplot as plt
|
||||
|
||||
from supervision.config import ORIENTED_BOX_COORDINATES
|
||||
from supervision.detection.core import Detections
|
||||
from supervision.detection.utils import box_iou_batch, mask_iou_batch
|
||||
from supervision.draw.color import LEGACY_COLOR_PALETTE
|
||||
from supervision.metrics.core import Metric, MetricTarget
|
||||
from supervision.metrics.utils.object_size import (
|
||||
ObjectSizeCategory,
|
||||
get_detection_size_category,
|
||||
)
|
||||
from supervision.metrics.utils.utils import ensure_pandas_installed
|
||||
|
||||
if TYPE_CHECKING:
|
||||
import pandas as pd
|
||||
|
||||
|
||||
class MeanAveragePrecision(Metric):
|
||||
def __init__(
|
||||
self,
|
||||
metric_target: MetricTarget = MetricTarget.BOXES,
|
||||
class_agnostic: bool = False,
|
||||
):
|
||||
"""
|
||||
Initialize the Mean Average Precision metric.
|
||||
|
||||
Args:
|
||||
metric_target (MetricTarget): The type of detection data to use.
|
||||
class_agnostic (bool): Whether to treat all data as a single class.
|
||||
"""
|
||||
self._metric_target = metric_target
|
||||
if self._metric_target == MetricTarget.ORIENTED_BOUNDING_BOXES:
|
||||
raise NotImplementedError(
|
||||
"Mean Average Precision is not implemented for oriented bounding boxes."
|
||||
)
|
||||
|
||||
self._class_agnostic = class_agnostic
|
||||
|
||||
self._predictions_list: List[Detections] = []
|
||||
self._targets_list: List[Detections] = []
|
||||
|
||||
def reset(self) -> None:
|
||||
self._predictions_list = []
|
||||
self._targets_list = []
|
||||
|
||||
def update(
|
||||
self,
|
||||
predictions: Union[Detections, List[Detections]],
|
||||
targets: Union[Detections, List[Detections]],
|
||||
) -> MeanAveragePrecision:
|
||||
"""
|
||||
Add new predictions and targets to the metric, but do not compute the result.
|
||||
|
||||
Args:
|
||||
predictions (Union[Detections, List[Detections]]): The predicted detections.
|
||||
targets (Union[Detections, List[Detections]]): The ground-truth detections.
|
||||
|
||||
Returns:
|
||||
(MeanAveragePrecision): The updated metric instance.
|
||||
"""
|
||||
if not isinstance(predictions, list):
|
||||
predictions = [predictions]
|
||||
if not isinstance(targets, list):
|
||||
targets = [targets]
|
||||
|
||||
if len(predictions) != len(targets):
|
||||
raise ValueError(
|
||||
f"The number of predictions ({len(predictions)}) and"
|
||||
f" targets ({len(targets)}) during the update must be the same."
|
||||
)
|
||||
|
||||
self._predictions_list.extend(predictions)
|
||||
self._targets_list.extend(targets)
|
||||
|
||||
return self
|
||||
|
||||
def compute(
|
||||
self,
|
||||
) -> MeanAveragePrecisionResult:
|
||||
"""
|
||||
Calculate Mean Average Precision based on predicted and ground-truth
|
||||
detections at different thresholds.
|
||||
|
||||
Returns:
|
||||
(MeanAveragePrecisionResult): New instance of MeanAveragePrecision.
|
||||
|
||||
Example:
|
||||
```python
|
||||
import supervision as sv
|
||||
from supervision.metrics import MeanAveragePrecision
|
||||
|
||||
predictions = sv.Detections(...)
|
||||
targets = sv.Detections(...)
|
||||
|
||||
map_metric = MeanAveragePrecision()
|
||||
map_result = map_metric.update(predictions, targets).compute()
|
||||
|
||||
print(map_result)
|
||||
print(map_result.map50_95)
|
||||
map_result.plot()
|
||||
```
|
||||
"""
|
||||
result = self._compute(self._predictions_list, self._targets_list)
|
||||
|
||||
small_predictions = []
|
||||
small_targets = []
|
||||
for predictions, targets in zip(self._predictions_list, self._targets_list):
|
||||
small_predictions.append(
|
||||
self._filter_detections_by_size(predictions, ObjectSizeCategory.SMALL)
|
||||
)
|
||||
small_targets.append(
|
||||
self._filter_detections_by_size(targets, ObjectSizeCategory.SMALL)
|
||||
)
|
||||
result.small_objects = self._compute(small_predictions, small_targets)
|
||||
|
||||
medium_predictions = []
|
||||
medium_targets = []
|
||||
for predictions, targets in zip(self._predictions_list, self._targets_list):
|
||||
medium_predictions.append(
|
||||
self._filter_detections_by_size(predictions, ObjectSizeCategory.MEDIUM)
|
||||
)
|
||||
medium_targets.append(
|
||||
self._filter_detections_by_size(targets, ObjectSizeCategory.MEDIUM)
|
||||
)
|
||||
result.medium_objects = self._compute(medium_predictions, medium_targets)
|
||||
|
||||
large_predictions = []
|
||||
large_targets = []
|
||||
for predictions, targets in zip(self._predictions_list, self._targets_list):
|
||||
large_predictions.append(
|
||||
self._filter_detections_by_size(predictions, ObjectSizeCategory.LARGE)
|
||||
)
|
||||
large_targets.append(
|
||||
self._filter_detections_by_size(targets, ObjectSizeCategory.LARGE)
|
||||
)
|
||||
result.large_objects = self._compute(large_predictions, large_targets)
|
||||
|
||||
return result
|
||||
|
||||
def _compute(
|
||||
self,
|
||||
predictions_list: List[Detections],
|
||||
targets_list: List[Detections],
|
||||
) -> MeanAveragePrecisionResult:
|
||||
iou_thresholds = np.linspace(0.5, 0.95, 10)
|
||||
stats = []
|
||||
|
||||
for predictions, targets in zip(predictions_list, targets_list):
|
||||
prediction_contents = self._detections_content(predictions)
|
||||
target_contents = self._detections_content(targets)
|
||||
|
||||
if len(targets) > 0:
|
||||
if len(predictions) == 0:
|
||||
stats.append(
|
||||
(
|
||||
np.zeros((0, iou_thresholds.size), dtype=bool),
|
||||
np.zeros((0,), dtype=np.float32),
|
||||
np.zeros((0,), dtype=int),
|
||||
targets.class_id,
|
||||
)
|
||||
)
|
||||
|
||||
else:
|
||||
if self._metric_target == MetricTarget.BOXES:
|
||||
iou = box_iou_batch(target_contents, prediction_contents)
|
||||
elif self._metric_target == MetricTarget.MASKS:
|
||||
iou = mask_iou_batch(target_contents, prediction_contents)
|
||||
else:
|
||||
raise NotImplementedError(
|
||||
"Unsupported metric target for IoU calculation"
|
||||
)
|
||||
|
||||
matches = self._match_detection_batch(
|
||||
predictions.class_id, targets.class_id, iou, iou_thresholds
|
||||
)
|
||||
stats.append(
|
||||
(
|
||||
matches,
|
||||
predictions.confidence,
|
||||
predictions.class_id,
|
||||
targets.class_id,
|
||||
)
|
||||
)
|
||||
|
||||
# Compute average precisions if any matches exist
|
||||
if stats:
|
||||
concatenated_stats = [np.concatenate(items, 0) for items in zip(*stats)]
|
||||
average_precisions = self._average_precisions_per_class(*concatenated_stats)
|
||||
map50 = average_precisions[:, 0].mean()
|
||||
map75 = average_precisions[:, 5].mean()
|
||||
map50_95 = average_precisions.mean()
|
||||
else:
|
||||
map50, map75, map50_95 = 0, 0, 0
|
||||
average_precisions = np.empty((0, len(iou_thresholds)), dtype=np.float32)
|
||||
|
||||
return MeanAveragePrecisionResult(
|
||||
iou_thresholds=iou_thresholds,
|
||||
map50_95=map50_95,
|
||||
map50=map50,
|
||||
map75=map75,
|
||||
per_class_ap50_95=average_precisions,
|
||||
metric_target=self._metric_target,
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
def _compute_average_precision(recall: np.ndarray, precision: np.ndarray) -> float:
|
||||
"""
|
||||
Compute the average precision using 101-point interpolation (COCO), given
|
||||
the recall and precision curves.
|
||||
|
||||
Args:
|
||||
recall (np.ndarray): The recall curve.
|
||||
precision (np.ndarray): The precision curve.
|
||||
|
||||
Returns:
|
||||
(float): Average precision.
|
||||
"""
|
||||
if len(recall) == 0 and len(precision) == 0:
|
||||
return 0.0
|
||||
|
||||
recall_levels = np.linspace(0, 1, 101)
|
||||
precision_levels = np.zeros_like(recall_levels)
|
||||
for r, p in zip(recall[::-1], precision[::-1]):
|
||||
precision_levels[recall_levels <= r] = p
|
||||
|
||||
average_precision = (1 / 100 * precision_levels).sum()
|
||||
return average_precision
|
||||
|
||||
@staticmethod
|
||||
def _match_detection_batch(
|
||||
predictions_classes: np.ndarray,
|
||||
target_classes: np.ndarray,
|
||||
iou: np.ndarray,
|
||||
iou_thresholds: np.ndarray,
|
||||
) -> np.ndarray:
|
||||
num_predictions, num_iou_levels = (
|
||||
predictions_classes.shape[0],
|
||||
iou_thresholds.shape[0],
|
||||
)
|
||||
correct = np.zeros((num_predictions, num_iou_levels), dtype=bool)
|
||||
correct_class = target_classes[:, None] == predictions_classes
|
||||
|
||||
for i, iou_level in enumerate(iou_thresholds):
|
||||
matched_indices = np.where((iou >= iou_level) & correct_class)
|
||||
|
||||
if matched_indices[0].shape[0]:
|
||||
combined_indices = np.stack(matched_indices, axis=1)
|
||||
iou_values = iou[matched_indices][:, None]
|
||||
matches = np.hstack([combined_indices, iou_values])
|
||||
|
||||
if matched_indices[0].shape[0] > 1:
|
||||
matches = matches[matches[:, 2].argsort()[::-1]]
|
||||
matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
|
||||
matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
|
||||
|
||||
correct[matches[:, 1].astype(int), i] = True
|
||||
|
||||
return correct
|
||||
|
||||
@staticmethod
|
||||
def _average_precisions_per_class(
|
||||
matches: np.ndarray,
|
||||
prediction_confidence: np.ndarray,
|
||||
prediction_class_ids: np.ndarray,
|
||||
true_class_ids: np.ndarray,
|
||||
) -> np.ndarray:
|
||||
"""
|
||||
Compute the average precision, given the recall and precision curves.
|
||||
Source: https://github.com/rafaelpadilla/Object-Detection-Metrics.
|
||||
|
||||
Args:
|
||||
matches (np.ndarray): True positives.
|
||||
prediction_confidence (np.ndarray): Objectness value from 0-1.
|
||||
prediction_class_ids (np.ndarray): Predicted object classes.
|
||||
true_class_ids (np.ndarray): True object classes.
|
||||
eps (float, optional): Small value to prevent division by zero.
|
||||
|
||||
Returns:
|
||||
(np.ndarray): Average precision for different IoU levels.
|
||||
"""
|
||||
eps = 1e-16
|
||||
|
||||
sorted_indices = np.argsort(-prediction_confidence)
|
||||
matches = matches[sorted_indices]
|
||||
prediction_class_ids = prediction_class_ids[sorted_indices]
|
||||
|
||||
unique_classes, class_counts = np.unique(true_class_ids, return_counts=True)
|
||||
num_classes = unique_classes.shape[0]
|
||||
|
||||
average_precisions = np.zeros((num_classes, matches.shape[1]))
|
||||
|
||||
for class_idx, class_id in enumerate(unique_classes):
|
||||
is_class = prediction_class_ids == class_id
|
||||
total_true = class_counts[class_idx]
|
||||
total_prediction = is_class.sum()
|
||||
|
||||
if total_prediction == 0 or total_true == 0:
|
||||
continue
|
||||
|
||||
false_positives = (1 - matches[is_class]).cumsum(0)
|
||||
true_positives = matches[is_class].cumsum(0)
|
||||
false_negatives = total_true - true_positives
|
||||
|
||||
recall = true_positives / (true_positives + false_negatives + eps)
|
||||
precision = true_positives / (true_positives + false_positives)
|
||||
|
||||
for iou_level_idx in range(matches.shape[1]):
|
||||
average_precisions[class_idx, iou_level_idx] = (
|
||||
MeanAveragePrecision._compute_average_precision(
|
||||
recall[:, iou_level_idx], precision[:, iou_level_idx]
|
||||
)
|
||||
)
|
||||
|
||||
return average_precisions
|
||||
|
||||
def _detections_content(self, detections: Detections) -> np.ndarray:
|
||||
"""Return boxes, masks or oriented bounding boxes from detections."""
|
||||
if self._metric_target == MetricTarget.BOXES:
|
||||
return detections.xyxy
|
||||
if self._metric_target == MetricTarget.MASKS:
|
||||
return (
|
||||
detections.mask
|
||||
if detections.mask is not None
|
||||
else self._make_empty_content()
|
||||
)
|
||||
if self._metric_target == MetricTarget.ORIENTED_BOUNDING_BOXES:
|
||||
if obb := detections.data.get(ORIENTED_BOX_COORDINATES):
|
||||
return np.ndarray(obb, dtype=np.float32)
|
||||
return self._make_empty_content()
|
||||
raise ValueError(f"Invalid metric target: {self._metric_target}")
|
||||
|
||||
def _make_empty_content(self) -> np.ndarray:
|
||||
if self._metric_target == MetricTarget.BOXES:
|
||||
return np.empty((0, 4), dtype=np.float32)
|
||||
if self._metric_target == MetricTarget.MASKS:
|
||||
return np.empty((0, 0, 0), dtype=bool)
|
||||
if self._metric_target == MetricTarget.ORIENTED_BOUNDING_BOXES:
|
||||
return np.empty((0, 8), dtype=np.float32)
|
||||
raise ValueError(f"Invalid metric target: {self._metric_target}")
|
||||
|
||||
def _filter_detections_by_size(
|
||||
self, detections: Detections, size_category: ObjectSizeCategory
|
||||
) -> Detections:
|
||||
"""Return a copy of detections with contents filtered by object size."""
|
||||
new_detections = deepcopy(detections)
|
||||
if detections.is_empty() or size_category == ObjectSizeCategory.ANY:
|
||||
return new_detections
|
||||
|
||||
sizes = get_detection_size_category(new_detections, self._metric_target)
|
||||
size_mask = sizes == size_category.value
|
||||
|
||||
new_detections.xyxy = new_detections.xyxy[size_mask]
|
||||
if new_detections.mask is not None:
|
||||
new_detections.mask = new_detections.mask[size_mask]
|
||||
if new_detections.class_id is not None:
|
||||
new_detections.class_id = new_detections.class_id[size_mask]
|
||||
if new_detections.confidence is not None:
|
||||
new_detections.confidence = new_detections.confidence[size_mask]
|
||||
if new_detections.tracker_id is not None:
|
||||
new_detections.tracker_id = new_detections.tracker_id[size_mask]
|
||||
if new_detections.data is not None:
|
||||
for key, value in new_detections.data.items():
|
||||
new_detections.data[key] = np.array(value)[size_mask]
|
||||
|
||||
return new_detections
|
||||
|
||||
|
||||
@dataclass
|
||||
class MeanAveragePrecisionResult:
|
||||
iou_thresholds: np.ndarray
|
||||
"""Array of IoU thresholds used in the calculations"""
|
||||
map50_95: float
|
||||
"""Mean Average Precision over IoU thresholds from 0.5 to 0.95"""
|
||||
|
||||
map50: float
|
||||
"""Mean Average Precision at IoU threshold of 0.5"""
|
||||
|
||||
map75: float
|
||||
"""Mean Average Precision at IoU threshold of 0.75"""
|
||||
|
||||
per_class_ap50_95: np.ndarray
|
||||
"""Average precision for each class at different IoU thresholds"""
|
||||
|
||||
metric_target: MetricTarget
|
||||
"""
|
||||
Defines the type of data used for the metric - boxes, masks or
|
||||
oriented bounding boxes.
|
||||
"""
|
||||
|
||||
small_objects: Optional[MeanAveragePrecisionResult] = None
|
||||
"""Mean Average Precision results for small objects"""
|
||||
|
||||
medium_objects: Optional[MeanAveragePrecisionResult] = None
|
||||
"""Mean Average Precision results for medium objects"""
|
||||
|
||||
large_objects: Optional[MeanAveragePrecisionResult] = None
|
||||
"""Mean Average Precision results for large objects"""
|
||||
|
||||
def __str__(self) -> str:
|
||||
"""
|
||||
Format the mAP results as a pretty string.
|
||||
|
||||
Example:
|
||||
```python
|
||||
print(map_result)
|
||||
```
|
||||
"""
|
||||
|
||||
out_str = (
|
||||
f"{self.__class__.__name__}:\n"
|
||||
f"iou_thresholds: {self.iou_thresholds}\n"
|
||||
f"map50_95: {self.map50_95:.4f}\n"
|
||||
f"map50: {self.map50:.4f}\n"
|
||||
f"map75: {self.map75:.4f}\n"
|
||||
f"per_class_ap50_95:"
|
||||
)
|
||||
|
||||
for class_id, ap in enumerate(self.per_class_ap50_95):
|
||||
out_str += f"\n {class_id}: {ap}"
|
||||
|
||||
indent = " "
|
||||
if self.small_objects is not None:
|
||||
indented_str = indent + str(self.small_objects).replace("\n", f"\n{indent}")
|
||||
out_str += f"\nSmall objects:\n{indented_str}"
|
||||
if self.medium_objects is not None:
|
||||
indented_str = indent + str(self.medium_objects).replace(
|
||||
"\n", f"\n{indent}"
|
||||
)
|
||||
out_str += f"\nMedium objects:\n{indented_str}"
|
||||
if self.large_objects is not None:
|
||||
indented_str = indent + str(self.large_objects).replace("\n", f"\n{indent}")
|
||||
out_str += f"\nLarge objects:\n{indented_str}"
|
||||
|
||||
return out_str
|
||||
|
||||
def to_pandas(self) -> "pd.DataFrame":
|
||||
"""
|
||||
Convert the result to a pandas DataFrame.
|
||||
|
||||
Returns:
|
||||
(pd.DataFrame): The result as a DataFrame.
|
||||
"""
|
||||
ensure_pandas_installed()
|
||||
import pandas as pd
|
||||
|
||||
pandas_data = {
|
||||
"mAP_50_95": self.map50_95,
|
||||
"mAP_50": self.map50,
|
||||
"mAP_75": self.map75,
|
||||
}
|
||||
if self.small_objects is not None:
|
||||
small_objects_df = self.small_objects.to_pandas()
|
||||
for key, value in small_objects_df.items():
|
||||
pandas_data[f"small_objects_{key}"] = value
|
||||
if self.medium_objects is not None:
|
||||
medium_objects_df = self.medium_objects.to_pandas()
|
||||
for key, value in medium_objects_df.items():
|
||||
pandas_data[f"medium_objects_{key}"] = value
|
||||
if self.large_objects is not None:
|
||||
large_objects_df = self.large_objects.to_pandas()
|
||||
for key, value in large_objects_df.items():
|
||||
pandas_data[f"large_objects_{key}"] = value
|
||||
|
||||
# Average precisions are currently not included in the DataFrame.
|
||||
|
||||
return pd.DataFrame(
|
||||
pandas_data,
|
||||
index=[0],
|
||||
)
|
||||
|
||||
def plot(self):
|
||||
"""
|
||||
Plot the mAP results.
|
||||
"""
|
||||
|
||||
labels = ["mAP_50_95", "mAP_50", "mAP_75"]
|
||||
values = [self.map50_95, self.map50, self.map75]
|
||||
colors = [LEGACY_COLOR_PALETTE[0]] * 3
|
||||
|
||||
if self.small_objects is not None:
|
||||
labels += [
|
||||
"small_objects_mAP_50_95",
|
||||
"small_objects_mAP_50",
|
||||
"small_objects_mAP_75",
|
||||
]
|
||||
values += [
|
||||
self.small_objects.map50_95,
|
||||
self.small_objects.map50,
|
||||
self.small_objects.map75,
|
||||
]
|
||||
colors += [LEGACY_COLOR_PALETTE[3]] * 3
|
||||
|
||||
if self.medium_objects is not None:
|
||||
labels += [
|
||||
"medium_objects_mAP_50_95",
|
||||
"medium_objects_mAP_50",
|
||||
"medium_objects_mAP_75",
|
||||
]
|
||||
values += [
|
||||
self.medium_objects.map50_95,
|
||||
self.medium_objects.map50,
|
||||
self.medium_objects.map75,
|
||||
]
|
||||
colors += [LEGACY_COLOR_PALETTE[2]] * 3
|
||||
|
||||
if self.large_objects is not None:
|
||||
labels += [
|
||||
"large_objects_mAP_50_95",
|
||||
"large_objects_mAP_50",
|
||||
"large_objects_mAP_75",
|
||||
]
|
||||
values += [
|
||||
self.large_objects.map50_95,
|
||||
self.large_objects.map50,
|
||||
self.large_objects.map75,
|
||||
]
|
||||
colors += [LEGACY_COLOR_PALETTE[4]] * 3
|
||||
|
||||
plt.rcParams["font.family"] = "monospace"
|
||||
|
||||
_, ax = plt.subplots(figsize=(10, 6))
|
||||
ax.set_ylim(0, 1)
|
||||
ax.set_ylabel("Value", fontweight="bold")
|
||||
ax.set_title("Mean Average Precision", fontweight="bold")
|
||||
|
||||
x_positions = range(len(labels))
|
||||
bars = ax.bar(x_positions, values, color=colors, align="center")
|
||||
|
||||
ax.set_xticks(x_positions)
|
||||
ax.set_xticklabels(labels, rotation=45, ha="right")
|
||||
|
||||
for bar in bars:
|
||||
y_value = bar.get_height()
|
||||
ax.text(
|
||||
bar.get_x() + bar.get_width() / 2,
|
||||
y_value + 0.02,
|
||||
f"{y_value:.2f}",
|
||||
ha="center",
|
||||
va="bottom",
|
||||
)
|
||||
|
||||
plt.rcParams["font.family"] = "sans-serif"
|
||||
|
||||
plt.tight_layout()
|
||||
plt.show()
|
||||
@@ -0,0 +1,300 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING, List, Optional, Set, Tuple
|
||||
|
||||
import numpy as np
|
||||
import numpy.typing as npt
|
||||
|
||||
from supervision.config import ORIENTED_BOX_COORDINATES
|
||||
from supervision.metrics.core import CLASS_ID_NONE, MetricTarget
|
||||
from supervision.metrics.utils.object_size import (
|
||||
ObjectSizeCategory,
|
||||
get_object_size_category,
|
||||
)
|
||||
from supervision.metrics.utils.utils import unify_pad_masks_shape
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from supervision.detection.core import Detections
|
||||
|
||||
|
||||
class MetricData:
|
||||
"""
|
||||
A container for detection contents, decouple from `Detections`.
|
||||
"""
|
||||
|
||||
def __init__(self, metric_target: MetricTarget, class_agnostic: bool = False):
|
||||
self._metric_target = metric_target
|
||||
self._class_agnostic = class_agnostic
|
||||
self._content_list: List[npt.NDArray] = []
|
||||
self._confidence_list: List[npt.NDArray[np.float32]] = []
|
||||
self._class_id_list: List[npt.NDArray[np.int_]] = []
|
||||
|
||||
def update(self, detections: Detections):
|
||||
"""Add new detections to the store."""
|
||||
if detections.is_empty() or len(detections) == 0:
|
||||
return
|
||||
|
||||
# Relies on Detections to ensure that member vars are equal in length
|
||||
# or None/empty.
|
||||
self._validate_new_entry(detections)
|
||||
|
||||
new_content = self._detections_content(detections)
|
||||
self._validate_shape(new_content)
|
||||
self._content_list.append(new_content)
|
||||
|
||||
if detections.confidence is not None:
|
||||
self._confidence_list.append(detections.confidence)
|
||||
|
||||
if detections.class_id is not None:
|
||||
if self._class_agnostic:
|
||||
self._class_id_list.append(
|
||||
np.full(len(detections.class_id), CLASS_ID_NONE, dtype=int)
|
||||
)
|
||||
else:
|
||||
self._class_id_list.append(detections.class_id)
|
||||
|
||||
def get_classes(self) -> Set[int]:
|
||||
"""Return all class IDs."""
|
||||
if self._class_agnostic:
|
||||
return {CLASS_ID_NONE}
|
||||
return set.union(*[set(class_id) for class_id in self._class_id_list])
|
||||
|
||||
def get(
|
||||
self, class_id: Optional[int] = None, size_category=ObjectSizeCategory.ANY
|
||||
) -> Tuple[npt.NDArray, npt.NDArray, npt.NDArray]:
|
||||
"""
|
||||
Get the contents, class_ids and confidences, optionally filtered by
|
||||
class_id and/or size.
|
||||
|
||||
Args:
|
||||
class_id (Optional[int]): The class ID for the data to retrieve
|
||||
size_category (ObjectSizeCategory): The size of the objects to retrieve.
|
||||
|
||||
Returns:
|
||||
(np.ndarray): Boxes, masks or obb, all stacked in a single array.
|
||||
"""
|
||||
if self._metric_target in [
|
||||
MetricTarget.BOXES,
|
||||
MetricTarget.ORIENTED_BOUNDING_BOXES,
|
||||
]:
|
||||
self._merge_boxes()
|
||||
if len(self._content_list) == 0:
|
||||
content = self._make_empty_content()
|
||||
else:
|
||||
content = self._content_list[0]
|
||||
|
||||
elif self._metric_target == MetricTarget.MASKS:
|
||||
self._merge_masks()
|
||||
if len(self._content_list) == 0:
|
||||
content = self._make_empty_content()
|
||||
else:
|
||||
content = self._content_list[0]
|
||||
|
||||
size_mask = np.full(len(content), True)
|
||||
if size_category != ObjectSizeCategory.ANY:
|
||||
sizes = get_object_size_category(content, self._metric_target)
|
||||
size_mask = sizes == size_category.value
|
||||
|
||||
class_mask = np.full(len(content), True)
|
||||
if class_id is not None:
|
||||
self._merge_class_id()
|
||||
class_ids = self._class_id_list[0]
|
||||
class_mask = class_ids == class_id
|
||||
|
||||
content = content[(size_mask & class_mask)]
|
||||
|
||||
self._merge_class_id()
|
||||
if len(self._class_id_list) == 0:
|
||||
class_ids = np.array([], dtype=int)
|
||||
else:
|
||||
class_ids = self._class_id_list[0]
|
||||
if len(class_ids) > 0:
|
||||
class_ids = class_ids[(size_mask & class_mask)]
|
||||
|
||||
self._merge_confidence()
|
||||
if len(self._confidence_list) == 0:
|
||||
confidences = np.array([], dtype=float)
|
||||
else:
|
||||
confidences = self._confidence_list[0]
|
||||
if len(confidences) > 0:
|
||||
confidences = confidences[(size_mask & class_mask)]
|
||||
|
||||
return content, class_ids, confidences
|
||||
|
||||
def get_class_id(self) -> npt.NDArray[np.int_]:
|
||||
self._merge_class_id()
|
||||
if len(self._class_id_list) == 0:
|
||||
return np.array([], dtype=int)
|
||||
return self._class_id_list[0]
|
||||
|
||||
def get_confidence(self) -> npt.NDArray[np.float32]:
|
||||
self._merge_confidence()
|
||||
if len(self._confidence_list) == 0:
|
||||
return np.array([], dtype=float)
|
||||
return self._confidence_list[0]
|
||||
|
||||
def _detections_content(self, detections: Detections) -> npt.NDArray:
|
||||
"""Return boxes, masks or oriented bounding boxes from detections."""
|
||||
if self._metric_target == MetricTarget.BOXES:
|
||||
return detections.xyxy
|
||||
if self._metric_target == MetricTarget.MASKS:
|
||||
return (
|
||||
detections.mask
|
||||
if detections.mask is not None
|
||||
else self._make_empty_content()
|
||||
)
|
||||
if self._metric_target == MetricTarget.ORIENTED_BOUNDING_BOXES:
|
||||
if obb := detections.data.get(ORIENTED_BOX_COORDINATES):
|
||||
return np.ndarray(obb, dtype=np.float32)
|
||||
return self._make_empty_content()
|
||||
raise ValueError(f"Invalid metric target: {self._metric_target}")
|
||||
|
||||
def _make_empty_content(self) -> npt.NDArray:
|
||||
if self._metric_target == MetricTarget.BOXES:
|
||||
return np.empty((0, 4), dtype=np.float32)
|
||||
if self._metric_target == MetricTarget.MASKS:
|
||||
return np.empty((0, 0, 0), dtype=bool)
|
||||
if self._metric_target == MetricTarget.ORIENTED_BOUNDING_BOXES:
|
||||
return np.empty((0, 8), dtype=np.float32)
|
||||
raise ValueError(f"Invalid metric target: {self._metric_target}")
|
||||
|
||||
def _validate_new_entry(self, detections: Detections) -> None:
|
||||
if (
|
||||
len(self._content_list) == 0
|
||||
or detections.is_empty()
|
||||
or len(detections) == 0
|
||||
):
|
||||
return
|
||||
|
||||
is_self_class_empty = len(self._class_id_list) == 0
|
||||
is_self_confidence_empty = len(self._confidence_list) == 0
|
||||
is_detection_class_empty = (
|
||||
detections.class_id is None or len(detections.class_id) == 0
|
||||
)
|
||||
is_detection_confidence_empty = (
|
||||
detections.confidence is None or len(detections.confidence) == 0
|
||||
)
|
||||
|
||||
if is_self_confidence_empty and not is_detection_confidence_empty:
|
||||
raise ValueError(
|
||||
"Previously stored detections without confidence,"
|
||||
" but new detections have it."
|
||||
)
|
||||
if is_self_class_empty and not is_detection_class_empty:
|
||||
raise ValueError(
|
||||
"Previously stored detections without class ID,"
|
||||
" but new detections have it."
|
||||
)
|
||||
if not is_self_class_empty and is_detection_class_empty:
|
||||
raise ValueError(
|
||||
"Started storing detections with class ID, but"
|
||||
" new detections do not have it."
|
||||
)
|
||||
if not is_self_confidence_empty and is_detection_confidence_empty:
|
||||
raise ValueError(
|
||||
"Started storing detections with confidence,"
|
||||
" but new detections do not have it."
|
||||
)
|
||||
|
||||
def _validate_shape(self, data: npt.NDArray) -> None:
|
||||
if self._metric_target == MetricTarget.BOXES:
|
||||
if len(data.shape) != 2 or data.shape[1] != 4:
|
||||
raise ValueError(f"Invalid xyxy shape: {data.shape}. Expected: (N, 4)")
|
||||
elif self._metric_target == MetricTarget.MASKS:
|
||||
if len(data.shape) != 3:
|
||||
raise ValueError(
|
||||
f"Invalid mask shape: {data.shape}. Expected: (N, H, W)"
|
||||
)
|
||||
elif self._metric_target == MetricTarget.ORIENTED_BOUNDING_BOXES:
|
||||
if len(data.shape) != 2 or data.shape[1] != 8:
|
||||
raise ValueError(f"Invalid obb shape: {data.shape}. Expected: (N, 8)")
|
||||
else:
|
||||
raise ValueError(f"Invalid metric target: {self._metric_target}")
|
||||
|
||||
def _merge_boxes(self):
|
||||
"""Merge all boxes into a single array."""
|
||||
if self._metric_target not in (
|
||||
MetricTarget.BOXES,
|
||||
MetricTarget.ORIENTED_BOUNDING_BOXES,
|
||||
):
|
||||
raise ValueError("Invalid metric target for merging boxes")
|
||||
if len(self._content_list) < 2:
|
||||
return
|
||||
self._content_list = [np.vstack(self._content_list)]
|
||||
|
||||
def _merge_masks(self):
|
||||
"""Merge all masks into a single array."""
|
||||
if self._metric_target != MetricTarget.MASKS:
|
||||
raise ValueError("Invalid metric target for merging masks")
|
||||
if len(self._content_list) < 2:
|
||||
return
|
||||
|
||||
mew_mask_list = unify_pad_masks_shape(*self._content_list)
|
||||
self._content_list = [np.vstack(mew_mask_list)]
|
||||
|
||||
def _merge_class_id(self):
|
||||
"""Merge all class IDs into a single array."""
|
||||
if len(self._class_id_list) < 2:
|
||||
return
|
||||
self._class_id_list = [np.hstack(self._class_id_list)]
|
||||
|
||||
def _merge_confidence(self):
|
||||
"""Merge all confidences into a single array."""
|
||||
if len(self._confidence_list) < 2:
|
||||
return
|
||||
self._confidence_list = [np.hstack(self._confidence_list)]
|
||||
|
||||
|
||||
class MetricDataStore:
|
||||
"""
|
||||
Stores internal data for metrics.
|
||||
|
||||
Provides a class-agnostic way to access it.
|
||||
"""
|
||||
|
||||
def __init__(self, metric_target: MetricTarget, class_agnostic: bool = False):
|
||||
self._metric_target = metric_target
|
||||
self._class_agnostic = class_agnostic
|
||||
self._data_1: MetricData
|
||||
self._data_2: MetricData
|
||||
self.reset()
|
||||
|
||||
def reset(self) -> None:
|
||||
self._data_1 = MetricData(self._metric_target, self._class_agnostic)
|
||||
self._data_2 = MetricData(self._metric_target, self._class_agnostic)
|
||||
|
||||
def update(self, data_1: Detections, data_2: Detections) -> None:
|
||||
"""
|
||||
Add new data to the store.
|
||||
|
||||
Use sv.Detections.empty() if only one set of data is available.
|
||||
"""
|
||||
self._data_1.update(data_1)
|
||||
self._data_2.update(data_2)
|
||||
|
||||
def get(
|
||||
self,
|
||||
class_id: Optional[int] = None,
|
||||
size_category: ObjectSizeCategory = ObjectSizeCategory.ANY,
|
||||
) -> Tuple[
|
||||
Tuple[npt.NDArray, npt.NDArray, npt.NDArray],
|
||||
Tuple[npt.NDArray, npt.NDArray, npt.NDArray],
|
||||
]:
|
||||
"""
|
||||
Get the data for both sets, optionally filtered by class_id and/or size.
|
||||
"""
|
||||
|
||||
data_1, class_id_1, confidence_1 = self._data_1.get(class_id, size_category)
|
||||
data_2, class_id_2, confidence_2 = self._data_2.get(class_id, size_category)
|
||||
|
||||
if self._metric_target == MetricTarget.MASKS:
|
||||
data_1, data_2 = unify_pad_masks_shape(data_1, data_2)
|
||||
|
||||
return (
|
||||
(data_1, class_id_1, confidence_1),
|
||||
(data_2, class_id_2, confidence_2),
|
||||
)
|
||||
|
||||
def get_classes(self) -> Set[int]:
|
||||
"""Return all class IDs."""
|
||||
return self._data_1.get_classes() | self._data_2.get_classes()
|
||||
@@ -0,0 +1,155 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from enum import Enum
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import numpy as np
|
||||
import numpy.typing as npt
|
||||
|
||||
from supervision.config import ORIENTED_BOX_COORDINATES
|
||||
from supervision.metrics.core import MetricTarget
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from supervision.detection.core import Detections
|
||||
|
||||
SIZE_THRESHOLDS = (32**2, 96**2)
|
||||
|
||||
|
||||
class ObjectSizeCategory(Enum):
|
||||
ANY = -1
|
||||
SMALL = 1
|
||||
MEDIUM = 2
|
||||
LARGE = 3
|
||||
|
||||
|
||||
def get_object_size_category(
|
||||
data: npt.NDArray, metric_target: MetricTarget
|
||||
) -> npt.NDArray[np.int_]:
|
||||
"""
|
||||
Get the size category of an object. Distinguish based on the metric target.
|
||||
|
||||
Args:
|
||||
data (np.ndarray): The object data, shaped (N, ...).
|
||||
metric_target (MetricTarget): Determines whether boxes, masks or
|
||||
oriented bounding boxes are used.
|
||||
|
||||
Returns:
|
||||
(np.ndarray) The size category of each object, matching
|
||||
the enum values of ObjectSizeCategory. Shaped (N,).
|
||||
"""
|
||||
if metric_target == MetricTarget.BOXES:
|
||||
return get_bbox_size_category(data)
|
||||
if metric_target == MetricTarget.MASKS:
|
||||
return get_mask_size_category(data)
|
||||
if metric_target == MetricTarget.ORIENTED_BOUNDING_BOXES:
|
||||
return get_obb_size_category(data)
|
||||
raise ValueError("Invalid metric type")
|
||||
|
||||
|
||||
def get_bbox_size_category(xyxy: npt.NDArray[np.float32]) -> npt.NDArray[np.int_]:
|
||||
"""
|
||||
Get the size category of a bounding boxes array.
|
||||
|
||||
Args:
|
||||
xyxy (np.ndarray): The bounding boxes array shaped (N, 4).
|
||||
|
||||
Returns:
|
||||
(np.ndarray) The size category of each bounding box, matching
|
||||
the enum values of ObjectSizeCategory. Shaped (N,).
|
||||
"""
|
||||
if len(xyxy.shape) != 2 or xyxy.shape[1] != 4:
|
||||
raise ValueError("Bounding boxes must be shaped (N, 4)")
|
||||
|
||||
width = xyxy[:, 2] - xyxy[:, 0]
|
||||
height = xyxy[:, 3] - xyxy[:, 1]
|
||||
areas = width * height
|
||||
|
||||
result = np.full(areas.shape, ObjectSizeCategory.ANY.value)
|
||||
SM, LG = SIZE_THRESHOLDS
|
||||
result[areas < SM] = ObjectSizeCategory.SMALL.value
|
||||
result[(areas >= SM) & (areas < LG)] = ObjectSizeCategory.MEDIUM.value
|
||||
result[areas >= LG] = ObjectSizeCategory.LARGE.value
|
||||
return result
|
||||
|
||||
|
||||
def get_mask_size_category(mask: npt.NDArray[np.bool_]) -> npt.NDArray[np.int_]:
|
||||
"""
|
||||
Get the size category of detection masks.
|
||||
|
||||
Args:
|
||||
mask (np.ndarray): The mask array shaped (N, H, W).
|
||||
|
||||
Returns:
|
||||
(np.ndarray) The size category of each mask, matching
|
||||
the enum values of ObjectSizeCategory. Shaped (N,).
|
||||
"""
|
||||
if len(mask.shape) != 3:
|
||||
raise ValueError("Masks must be shaped (N, H, W)")
|
||||
|
||||
areas = np.sum(mask, axis=(1, 2))
|
||||
|
||||
result = np.full(areas.shape, ObjectSizeCategory.ANY.value)
|
||||
SM, LG = SIZE_THRESHOLDS
|
||||
result[areas < SM] = ObjectSizeCategory.SMALL.value
|
||||
result[(areas >= SM) & (areas < LG)] = ObjectSizeCategory.MEDIUM.value
|
||||
result[areas >= LG] = ObjectSizeCategory.LARGE.value
|
||||
return result
|
||||
|
||||
|
||||
def get_obb_size_category(xyxyxyxy: npt.NDArray[np.float32]) -> npt.NDArray[np.int_]:
|
||||
"""
|
||||
Get the size category of a oriented bounding boxes array.
|
||||
|
||||
Args:
|
||||
xyxyxyxy (np.ndarray): The bounding boxes array shaped (N, 8).
|
||||
|
||||
Returns:
|
||||
(np.ndarray) The size category of each bounding box, matching
|
||||
the enum values of ObjectSizeCategory. Shaped (N,).
|
||||
"""
|
||||
if len(xyxyxyxy.shape) != 2 or xyxyxyxy.shape[1] != 8:
|
||||
raise ValueError("Oriented bounding boxes must be shaped (N, 8)")
|
||||
|
||||
# Shoelace formula
|
||||
x1, y1, x2, y2, x3, y3, x4, y4 = xyxyxyxy.T
|
||||
areas = 0.5 * np.abs(
|
||||
(x1 * y2 + x2 * y3 + x3 * y4 + x4 * y1)
|
||||
- (x2 * y1 + x3 * y2 + x4 * y3 + x1 * y4)
|
||||
)
|
||||
|
||||
result = np.full(areas.shape, ObjectSizeCategory.ANY.value)
|
||||
SM, LG = SIZE_THRESHOLDS
|
||||
result[areas < SM] = ObjectSizeCategory.SMALL.value
|
||||
result[(areas >= SM) & (areas < LG)] = ObjectSizeCategory.MEDIUM.value
|
||||
result[areas >= LG] = ObjectSizeCategory.LARGE.value
|
||||
return result
|
||||
|
||||
|
||||
def get_detection_size_category(
|
||||
detections: Detections, metric_target: MetricTarget = MetricTarget.BOXES
|
||||
) -> npt.NDArray[np.int_]:
|
||||
"""
|
||||
Get the size category of a detections object.
|
||||
|
||||
Args:
|
||||
xyxyxyxy (np.ndarray): The bounding boxes array shaped (N, 8).
|
||||
metric_target (MetricTarget): Determines whether boxes, masks or
|
||||
oriented bounding boxes are used.
|
||||
|
||||
Returns:
|
||||
(np.ndarray) The size category of each bounding box, matching
|
||||
the enum values of ObjectSizeCategory. Shaped (N,).
|
||||
"""
|
||||
if metric_target == MetricTarget.BOXES:
|
||||
return get_bbox_size_category(detections.xyxy)
|
||||
if metric_target == MetricTarget.MASKS:
|
||||
if detections.mask is None:
|
||||
raise ValueError("Detections mask is not available")
|
||||
return get_mask_size_category(detections.mask)
|
||||
if metric_target == MetricTarget.ORIENTED_BOUNDING_BOXES:
|
||||
if detections.data.get(ORIENTED_BOX_COORDINATES) is None:
|
||||
raise ValueError("Detections oriented bounding boxes are not available")
|
||||
return get_obb_size_category(
|
||||
np.array(detections.data[ORIENTED_BOX_COORDINATES])
|
||||
)
|
||||
raise ValueError("Invalid metric type")
|
||||
@@ -0,0 +1,70 @@
|
||||
from typing import List, Tuple
|
||||
|
||||
import numpy as np
|
||||
import numpy.typing as npt
|
||||
|
||||
|
||||
def ensure_pandas_installed():
|
||||
try:
|
||||
import pandas # noqa
|
||||
except ImportError:
|
||||
raise ImportError(
|
||||
"`metrics` extra is required to run the function."
|
||||
" Run `pip install 'supervision[metrics]'` or"
|
||||
" `poetry add supervision -E metrics`"
|
||||
)
|
||||
|
||||
|
||||
def pad_mask(mask: npt.NDArray, new_shape: Tuple[int, int]) -> npt.NDArray:
|
||||
"""Pad a mask to a new shape, inserting zeros on the right and bottom."""
|
||||
if len(mask.shape) != 3:
|
||||
raise ValueError(f"Invalid mask shape: {mask.shape}. Expected: (N, H, W)")
|
||||
|
||||
new_mask = np.pad(
|
||||
mask,
|
||||
(
|
||||
(0, 0),
|
||||
(0, new_shape[0] - mask.shape[1]),
|
||||
(0, new_shape[1] - mask.shape[2]),
|
||||
),
|
||||
mode="constant",
|
||||
constant_values=0,
|
||||
)
|
||||
|
||||
return new_mask
|
||||
|
||||
|
||||
def unify_pad_masks_shape(
|
||||
*masks: npt.NDArray[np.bool_],
|
||||
) -> List[npt.NDArray[np.bool_]]:
|
||||
"""
|
||||
Given any number of (N, H, W) mask objects, return copies of the
|
||||
same (H, W), padded to the largest dimensions.
|
||||
|
||||
Args:
|
||||
*masks (np.ndarray): The mask arrays to unify. Each shaped (_, H, W),
|
||||
|
||||
Returns:
|
||||
List[np.ndarray]: The masks, padded to the largest dimensions.
|
||||
Each list element shaped (_, H_max, W_max)
|
||||
"""
|
||||
new_h = 0
|
||||
new_w = 0
|
||||
for mask in masks:
|
||||
if len(mask.shape) != 3:
|
||||
raise ValueError(f"Invalid mask shape: {mask.shape}. Expected: (N, H, W)")
|
||||
|
||||
_, h, w = mask.shape
|
||||
new_h = max(new_h, h)
|
||||
new_w = max(new_w, w)
|
||||
|
||||
results = []
|
||||
for mask in masks:
|
||||
results.append(pad_mask(mask, (new_h, new_w)))
|
||||
|
||||
return results
|
||||
|
||||
|
||||
def len0_like(data: npt.NDArray) -> npt.NDArray:
|
||||
"""Create an empty array with the same shape as input, but with 0 rows."""
|
||||
return np.empty((0, *data.shape[1:]), dtype=data.dtype)
|
||||
@@ -7,7 +7,6 @@ from supervision.detection.utils import box_iou_batch
|
||||
from supervision.tracker.byte_tracker import matching
|
||||
from supervision.tracker.byte_tracker.basetrack import BaseTrack, TrackState
|
||||
from supervision.tracker.byte_tracker.kalman_filter import KalmanFilter
|
||||
from supervision.utils.internal import deprecated_parameter
|
||||
|
||||
|
||||
class STrack(BaseTrack):
|
||||
@@ -197,48 +196,24 @@ class ByteTrack:
|
||||
</video>
|
||||
|
||||
Parameters:
|
||||
track_activation_threshold (float, optional): Detection confidence threshold
|
||||
track_activation_threshold (float): Detection confidence threshold
|
||||
for track activation. Increasing track_activation_threshold improves accuracy
|
||||
and stability but might miss true detections. Decreasing it increases
|
||||
completeness but risks introducing noise and instability.
|
||||
lost_track_buffer (int, optional): Number of frames to buffer when a track is lost.
|
||||
lost_track_buffer (int): Number of frames to buffer when a track is lost.
|
||||
Increasing lost_track_buffer enhances occlusion handling, significantly
|
||||
reducing the likelihood of track fragmentation or disappearance caused
|
||||
by brief detection gaps.
|
||||
minimum_matching_threshold (float, optional): Threshold for matching tracks with detections.
|
||||
minimum_matching_threshold (float): Threshold for matching tracks with detections.
|
||||
Increasing minimum_matching_threshold improves accuracy but risks fragmentation.
|
||||
Decreasing it improves completeness but risks false positives and drift.
|
||||
frame_rate (int, optional): The frame rate of the video.
|
||||
minimum_consecutive_frames (int, optional): Number of consecutive frames that an object must
|
||||
frame_rate (int): The frame rate of the video.
|
||||
minimum_consecutive_frames (int): Number of consecutive frames that an object must
|
||||
be tracked before it is considered a 'valid' track.
|
||||
Increasing minimum_consecutive_frames prevents the creation of accidental tracks from
|
||||
false detection or double detection, but risks missing shorter tracks.
|
||||
""" # noqa: E501 // docs
|
||||
|
||||
@deprecated_parameter(
|
||||
old_parameter="track_buffer",
|
||||
new_parameter="lost_track_buffer",
|
||||
map_function=lambda x: x,
|
||||
warning_message="`{old_parameter}` in `{function_name}` is deprecated and will "
|
||||
"be remove in `supervision-0.23.0`. Use '{new_parameter}' "
|
||||
"instead.",
|
||||
)
|
||||
@deprecated_parameter(
|
||||
old_parameter="track_thresh",
|
||||
new_parameter="track_activation_threshold",
|
||||
map_function=lambda x: x,
|
||||
warning_message="`{old_parameter}` in `{function_name}` is deprecated and will "
|
||||
"be remove in `supervision-0.23.0`. Use '{new_parameter}' "
|
||||
"instead.",
|
||||
)
|
||||
@deprecated_parameter(
|
||||
old_parameter="match_thresh",
|
||||
new_parameter="minimum_matching_threshold",
|
||||
map_function=lambda x: x,
|
||||
warning_message="`{old_parameter}` in `{function_name}` is deprecated and will "
|
||||
"be remove in `supervision-0.23.0`. Use '{new_parameter}' "
|
||||
"instead.",
|
||||
)
|
||||
def __init__(
|
||||
self,
|
||||
track_activation_threshold: float = 0.25,
|
||||
@@ -276,7 +251,7 @@ class ByteTrack:
|
||||
model = YOLO(<MODEL_PATH>)
|
||||
tracker = sv.ByteTrack()
|
||||
|
||||
bounding_box_annotator = sv.BoundingBoxAnnotator()
|
||||
box_annotator = sv.BoxAnnotator()
|
||||
label_annotator = sv.LabelAnnotator()
|
||||
|
||||
def callback(frame: np.ndarray, index: int) -> np.ndarray:
|
||||
@@ -286,7 +261,7 @@ class ByteTrack:
|
||||
|
||||
labels = [f"#{tracker_id}" for tracker_id in detections.tracker_id]
|
||||
|
||||
annotated_frame = bounding_box_annotator.annotate(
|
||||
annotated_frame = box_annotator.annotate(
|
||||
scene=frame.copy(), detections=detections)
|
||||
annotated_frame = label_annotator.annotate(
|
||||
scene=annotated_frame, detections=detections, labels=labels)
|
||||
|
||||
@@ -158,7 +158,7 @@ def resize_image(
|
||||
accepting either `numpy.ndarray` or `PIL.Image.Image`.
|
||||
resolution_wh (Tuple[int, int]): The target resolution as
|
||||
`(width, height)`.
|
||||
keep_aspect_ratio (bool, optional): Flag to maintain the image's original
|
||||
keep_aspect_ratio (bool): Flag to maintain the image's original
|
||||
aspect ratio. Defaults to `False`.
|
||||
|
||||
Returns:
|
||||
@@ -270,6 +270,7 @@ def letterbox_image(
|
||||
|
||||
{ align=center width="800" }
|
||||
""" # noqa E501 // docs
|
||||
assert isinstance(image, np.ndarray)
|
||||
color = unify_to_bgr(color=color)
|
||||
resized_image = resize_image(
|
||||
image=image, resolution_wh=resolution_wh, keep_aspect_ratio=True
|
||||
@@ -279,7 +280,7 @@ def letterbox_image(
|
||||
padding_bottom = resolution_wh[1] - height_new - padding_top
|
||||
padding_left = (resolution_wh[0] - width_new) // 2
|
||||
padding_right = resolution_wh[0] - width_new - padding_left
|
||||
return cv2.copyMakeBorder(
|
||||
image_with_borders = cv2.copyMakeBorder(
|
||||
resized_image,
|
||||
padding_top,
|
||||
padding_bottom,
|
||||
@@ -289,6 +290,14 @@ def letterbox_image(
|
||||
value=color,
|
||||
)
|
||||
|
||||
if image.shape[2] == 4:
|
||||
image[:padding_top, :, 3] = 0
|
||||
image[height_new - padding_bottom :, :, 3] = 0
|
||||
image[:, :padding_left, 3] = 0
|
||||
image[:, width_new - padding_right :, 3] = 0
|
||||
|
||||
return image_with_borders
|
||||
|
||||
|
||||
def overlay_image(
|
||||
image: npt.NDArray[np.uint8],
|
||||
@@ -341,9 +350,20 @@ def overlay_image(
|
||||
crop_x_max = image_width - max((anchor_x + image_width) - scene_width, 0)
|
||||
crop_y_max = image_height - max((anchor_y + image_height) - scene_height, 0)
|
||||
|
||||
image[y_min:y_max, x_min:x_max] = overlay[
|
||||
crop_y_min:crop_y_max, crop_x_min:crop_x_max
|
||||
]
|
||||
if overlay.shape[2] == 4:
|
||||
b, g, r, alpha = cv2.split(
|
||||
overlay[crop_y_min:crop_y_max, crop_x_min:crop_x_max]
|
||||
)
|
||||
alpha = alpha[:, :, None] / 255.0
|
||||
overlay_color = cv2.merge((b, g, r))
|
||||
|
||||
roi = image[y_min:y_max, x_min:x_max]
|
||||
roi[:] = roi * (1 - alpha) + overlay_color * alpha
|
||||
image[y_min:y_max, x_min:x_max] = roi
|
||||
else:
|
||||
image[y_min:y_max, x_min:x_max] = overlay[
|
||||
crop_y_min:crop_y_max, crop_x_min:crop_x_max
|
||||
]
|
||||
|
||||
return image
|
||||
|
||||
@@ -360,9 +380,9 @@ class ImageSink:
|
||||
|
||||
Args:
|
||||
target_dir_path (str): The target directory where images will be saved.
|
||||
overwrite (bool, optional): Whether to overwrite the existing directory.
|
||||
overwrite (bool): Whether to overwrite the existing directory.
|
||||
Defaults to False.
|
||||
image_name_pattern (str, optional): The image file name pattern.
|
||||
image_name_pattern (str): The image file name pattern.
|
||||
Defaults to "image_{:05d}.png".
|
||||
|
||||
Examples:
|
||||
@@ -399,7 +419,7 @@ class ImageSink:
|
||||
Args:
|
||||
image (np.ndarray): The image to be saved. The image must be in BGR color
|
||||
format.
|
||||
image_name (str, optional): The name to use for the saved image.
|
||||
image_name (Optional[str]): The name to use for the saved image.
|
||||
If not provided, a name will be
|
||||
generated using the `image_name_pattern`.
|
||||
"""
|
||||
|
||||
@@ -2,7 +2,7 @@ import functools
|
||||
import inspect
|
||||
import os
|
||||
import warnings
|
||||
from typing import Any, Callable, Set
|
||||
from typing import Any, Callable, Generic, Optional, Set, TypeVar
|
||||
|
||||
|
||||
class SupervisionWarnings(Warning):
|
||||
@@ -31,6 +31,16 @@ else:
|
||||
warnings.simplefilter("always", SupervisionWarnings)
|
||||
|
||||
|
||||
def warn_deprecated(message: str):
|
||||
"""
|
||||
Issue a warning that a function is deprecated.
|
||||
|
||||
Args:
|
||||
message (str): The message to display when the function is called.
|
||||
"""
|
||||
warnings.warn(message, category=SupervisionWarnings, stacklevel=2)
|
||||
|
||||
|
||||
def deprecated_parameter(
|
||||
old_parameter: str,
|
||||
new_parameter: str,
|
||||
@@ -46,9 +56,9 @@ def deprecated_parameter(
|
||||
Parameters:
|
||||
old_parameter (str): The name of the deprecated parameter.
|
||||
new_parameter (str): The name of the parameter that should be used instead.
|
||||
map_function (Callable, optional): A function used to map the value of the old
|
||||
map_function (Callable): A function used to map the value of the old
|
||||
parameter to the new parameter. Defaults to the identity function.
|
||||
warning_message (str, optional): The warning message to be displayed when the
|
||||
warning_message (str): The warning message to be displayed when the
|
||||
deprecated parameter is used. Defaults to a generic warning message with
|
||||
placeholders for the old parameter, new parameter, and function name.
|
||||
**message_kwargs: Additional keyword arguments that can be used to customize
|
||||
@@ -82,15 +92,13 @@ def deprecated_parameter(
|
||||
else:
|
||||
function_name = func.__name__
|
||||
|
||||
warnings.warn(
|
||||
warn_deprecated(
|
||||
message=warning_message.format(
|
||||
function_name=function_name,
|
||||
old_parameter=old_parameter,
|
||||
new_parameter=new_parameter,
|
||||
**message_kwargs,
|
||||
),
|
||||
category=SupervisionWarnings,
|
||||
stacklevel=2,
|
||||
)
|
||||
)
|
||||
|
||||
kwargs[new_parameter] = map_function(kwargs.pop(old_parameter))
|
||||
@@ -106,11 +114,7 @@ def deprecated(reason: str):
|
||||
def decorator(func):
|
||||
@functools.wraps(func)
|
||||
def wrapper(*args, **kwargs):
|
||||
warnings.warn(
|
||||
f"{func.__name__} is deprecated: {reason}",
|
||||
category=SupervisionWarnings,
|
||||
stacklevel=2,
|
||||
)
|
||||
warn_deprecated(f"{func.__name__} is deprecated: {reason}")
|
||||
return func(*args, **kwargs)
|
||||
|
||||
return wrapper
|
||||
@@ -118,7 +122,10 @@ def deprecated(reason: str):
|
||||
return decorator
|
||||
|
||||
|
||||
class classproperty(property):
|
||||
T = TypeVar("T")
|
||||
|
||||
|
||||
class classproperty(Generic[T]):
|
||||
"""
|
||||
A decorator that combines @classmethod and @property.
|
||||
It allows a method to be accessed as a property of the class,
|
||||
@@ -130,17 +137,27 @@ class classproperty(property):
|
||||
...
|
||||
"""
|
||||
|
||||
def __get__(self, owner_self: object, owner_cls: type) -> object:
|
||||
def __init__(self, fget: Callable[..., T]):
|
||||
"""
|
||||
Args:
|
||||
The function that is called when the property is accessed.
|
||||
"""
|
||||
self.fget = fget
|
||||
|
||||
def __get__(self, owner_self: Any, owner_cls: Optional[type] = None) -> T:
|
||||
"""
|
||||
Override the __get__ method to return the result of the function call.
|
||||
|
||||
Args:
|
||||
owner_self: The instance through which the attribute was accessed, or None.
|
||||
owner_cls: The class through which the attribute was accessed.
|
||||
owner_self: The instance through which the attribute was accessed, or None.
|
||||
Irrelevant for class properties.
|
||||
owner_cls: The class through which the attribute was accessed.
|
||||
|
||||
Returns:
|
||||
The result of calling the function stored in 'fget' with 'owner_cls'.
|
||||
The result of calling the function stored in 'fget' with 'owner_cls'.
|
||||
"""
|
||||
if self.fget is None:
|
||||
raise AttributeError("unreadable attribute")
|
||||
return self.fget(owner_cls)
|
||||
|
||||
|
||||
|
||||
@@ -68,3 +68,17 @@ def fill(sequence: List[V], desired_size: int, content: V) -> List[V]:
|
||||
missing_size = max(0, desired_size - len(sequence))
|
||||
sequence.extend([content] * missing_size)
|
||||
return sequence
|
||||
|
||||
|
||||
def find_duplicates(sequence: List) -> List:
|
||||
"""
|
||||
Find all duplicate elements in the input sequence.
|
||||
"""
|
||||
seen = set()
|
||||
duplicates = set()
|
||||
for element in sequence:
|
||||
if element in seen:
|
||||
duplicates.add(element)
|
||||
else:
|
||||
seen.add(element)
|
||||
return list(duplicates)
|
||||
|
||||
@@ -17,7 +17,7 @@ def plot_image(
|
||||
Args:
|
||||
image (ImageType): The frame to be displayed ImageType
|
||||
is a flexible type, accepting either `numpy.ndarray` or `PIL.Image.Image`.
|
||||
size (Tuple[int, int]): The size of the plot.
|
||||
size (Tuple[int, int]): The size of the plot in inches.
|
||||
cmap (str): the colormap to use for single channel images.
|
||||
|
||||
Examples:
|
||||
|
||||
+25
-25
@@ -8,8 +8,6 @@ from typing import Callable, Generator, Optional, Tuple
|
||||
import cv2
|
||||
import numpy as np
|
||||
|
||||
from supervision.utils.internal import deprecated
|
||||
|
||||
|
||||
@dataclass
|
||||
class VideoInfo:
|
||||
@@ -21,7 +19,7 @@ class VideoInfo:
|
||||
width (int): width of the video in pixels
|
||||
height (int): height of the video in pixels
|
||||
fps (int): frames per second of the video
|
||||
total_frames (int, optional): total number of frames in the video,
|
||||
total_frames (Optional[int]): total number of frames in the video,
|
||||
default is None
|
||||
|
||||
Examples:
|
||||
@@ -118,7 +116,9 @@ class VideoSink:
|
||||
self.__writer.release()
|
||||
|
||||
|
||||
def _validate_and_setup_video(source_path: str, start: int, end: Optional[int]):
|
||||
def _validate_and_setup_video(
|
||||
source_path: str, start: int, end: Optional[int], iterative_seek: bool = False
|
||||
):
|
||||
video = cv2.VideoCapture(source_path)
|
||||
if not video.isOpened():
|
||||
raise Exception(f"Could not open video at {source_path}")
|
||||
@@ -127,12 +127,25 @@ def _validate_and_setup_video(source_path: str, start: int, end: Optional[int]):
|
||||
raise Exception("Requested frames are outbound")
|
||||
start = max(start, 0)
|
||||
end = min(end, total_frames) if end is not None else total_frames
|
||||
video.set(cv2.CAP_PROP_POS_FRAMES, start)
|
||||
|
||||
if iterative_seek:
|
||||
while start > 0:
|
||||
success = video.grab()
|
||||
if not success:
|
||||
break
|
||||
start -= 1
|
||||
elif start > 0:
|
||||
video.set(cv2.CAP_PROP_POS_FRAMES, start)
|
||||
|
||||
return video, start, end
|
||||
|
||||
|
||||
def get_video_frames_generator(
|
||||
source_path: str, stride: int = 1, start: int = 0, end: Optional[int] = None
|
||||
source_path: str,
|
||||
stride: int = 1,
|
||||
start: int = 0,
|
||||
end: Optional[int] = None,
|
||||
iterative_seek: bool = False,
|
||||
) -> Generator[np.ndarray, None, None]:
|
||||
"""
|
||||
Get a generator that yields the frames of the video.
|
||||
@@ -145,6 +158,9 @@ def get_video_frames_generator(
|
||||
video should generate frames
|
||||
end (Optional[int]): Indicates the ending position at which video
|
||||
should stop generating frames. If None, video will be read to the end.
|
||||
iterative_seek (bool): If True, the generator will seek to the
|
||||
`start` frame by grabbing each frame, which is much slower. This is a
|
||||
workaround for videos that don't open at all when you set the `start` value.
|
||||
|
||||
Returns:
|
||||
(Generator[np.ndarray, None, None]): A generator that yields the
|
||||
@@ -158,7 +174,9 @@ def get_video_frames_generator(
|
||||
...
|
||||
```
|
||||
"""
|
||||
video, start, end = _validate_and_setup_video(source_path, start, end)
|
||||
video, start, end = _validate_and_setup_video(
|
||||
source_path, start, end, iterative_seek
|
||||
)
|
||||
frame_position = start
|
||||
while True:
|
||||
success, frame = video.read()
|
||||
@@ -239,24 +257,6 @@ class FPSMonitor:
|
||||
""" # noqa: E501 // docs
|
||||
self.all_timestamps = deque(maxlen=sample_size)
|
||||
|
||||
@deprecated(
|
||||
"`FPSMonitor.__call__` is deprecated and will be removed in "
|
||||
"`supervision-0.22.0`. Use `FPSMonitor.fps` instead."
|
||||
)
|
||||
def __call__(self) -> float:
|
||||
"""
|
||||
!!! failure "Deprecated"
|
||||
|
||||
`FPSMonitor.__call__` is deprecated and will be removed in
|
||||
`supervision-0.22.0`. Use `FPSMonitor.fps` instead.
|
||||
|
||||
Computes and returns the average FPS based on the stored time stamps.
|
||||
|
||||
Returns:
|
||||
float: The average FPS. Returns 0.0 if no time stamps are stored.
|
||||
"""
|
||||
return self.fps
|
||||
|
||||
@property
|
||||
def fps(self) -> float:
|
||||
"""
|
||||
|
||||
@@ -62,8 +62,7 @@ def validate_keypoint_confidence(confidence: Any, n: int, m: int) -> None:
|
||||
if not is_valid:
|
||||
raise ValueError(
|
||||
f"confidence must be a 1D np.ndarray with shape {expected_shape}, but "
|
||||
"got"
|
||||
f"shape {actual_shape}"
|
||||
f"got shape {actual_shape}"
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
from contextlib import ExitStack as DoesNotRaise
|
||||
from test.test_utils import mock_detections
|
||||
from typing import Optional
|
||||
|
||||
import numpy as np
|
||||
@@ -7,6 +6,7 @@ import pytest
|
||||
|
||||
from supervision.annotators.utils import ColorLookup, resolve_color_idx
|
||||
from supervision.detection.core import Detections
|
||||
from test.test_utils import mock_detections
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
|
||||
@@ -1,16 +1,16 @@
|
||||
from contextlib import ExitStack as DoesNotRaise
|
||||
from test.test_utils import mock_detections
|
||||
from typing import List, Optional
|
||||
|
||||
import defusedxml.ElementTree as ET
|
||||
import numpy as np
|
||||
import pytest
|
||||
from defusedxml import ElementTree
|
||||
|
||||
from supervision.dataset.formats.pascal_voc import (
|
||||
detections_from_xml_obj,
|
||||
object_to_pascal_voc,
|
||||
parse_polygon_points,
|
||||
)
|
||||
from test.test_utils import mock_detections
|
||||
|
||||
|
||||
def are_xml_elements_equal(elem1, elem2):
|
||||
@@ -36,7 +36,7 @@ def are_xml_elements_equal(elem1, elem2):
|
||||
np.array([0, 0, 10, 10]),
|
||||
"test",
|
||||
None,
|
||||
ET.fromstring(
|
||||
ElementTree.fromstring(
|
||||
"""<object><name>test</name><bndbox><xmin>1</xmin><ymin>1</ymin>
|
||||
<xmax>11</xmax><ymax>11</ymax></bndbox></object>"""
|
||||
),
|
||||
@@ -46,7 +46,7 @@ def are_xml_elements_equal(elem1, elem2):
|
||||
np.array([0, 0, 10, 10]),
|
||||
"test",
|
||||
np.array([[0, 0], [10, 0], [10, 10], [0, 10]]),
|
||||
ET.fromstring(
|
||||
ElementTree.fromstring(
|
||||
"""<object><name>test</name><bndbox><xmin>1</xmin><ymin>1</ymin>
|
||||
<xmax>11</xmax><ymax>11</ymax>
|
||||
</bndbox><polygon><x1>1</x1><y1>1</y1><x2>11</x2>
|
||||
@@ -73,7 +73,7 @@ def test_object_to_pascal_voc(
|
||||
"polygon_element, expected_result, exception",
|
||||
[
|
||||
(
|
||||
ET.fromstring(
|
||||
ElementTree.fromstring(
|
||||
"""<polygon><x1>0</x1><y1>0</y1><x2>10</x2><y2>0</y2><x3>10</x3>
|
||||
<y3>10</y3><x4>0</x4><y4>10</y4></polygon>"""
|
||||
),
|
||||
@@ -160,6 +160,6 @@ def test_detections_from_xml_obj(
|
||||
xml_string, classes, resolution_wh, force_masks, expected_result, exception
|
||||
):
|
||||
with exception:
|
||||
root = ET.fromstring(xml_string)
|
||||
root = ElementTree.fromstring(xml_string)
|
||||
result, _ = detections_from_xml_obj(root, classes, resolution_wh, force_masks)
|
||||
assert result == expected_result
|
||||
|
||||
@@ -13,7 +13,7 @@ from supervision.dataset.formats.yolo import (
|
||||
from supervision.detection.core import Detections
|
||||
|
||||
|
||||
def _mock_simple_mask(resolution_wh: Tuple[int, int], box: List[int]) -> np.array:
|
||||
def _mock_simple_mask(resolution_wh: Tuple[int, int], box: List[int]) -> np.ndarray:
|
||||
x_min, y_min, x_max, y_max = box
|
||||
mask = np.full(resolution_wh, False, dtype=bool)
|
||||
mask[y_min:y_max, x_min:x_max] = True
|
||||
|
||||
+21
-49
@@ -1,11 +1,10 @@
|
||||
from contextlib import ExitStack as DoesNotRaise
|
||||
from test.test_utils import mock_detections
|
||||
from typing import List, Optional
|
||||
|
||||
import numpy as np
|
||||
import pytest
|
||||
|
||||
from supervision import DetectionDataset
|
||||
from test.test_utils import mock_detections
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
@@ -13,29 +12,29 @@ from supervision import DetectionDataset
|
||||
[
|
||||
(
|
||||
[],
|
||||
DetectionDataset(classes=[], images={}, annotations={}),
|
||||
DetectionDataset(classes=[], images=[], annotations={}),
|
||||
DoesNotRaise(),
|
||||
), # empty dataset list
|
||||
(
|
||||
[DetectionDataset(classes=[], images={}, annotations={})],
|
||||
DetectionDataset(classes=[], images={}, annotations={}),
|
||||
[DetectionDataset(classes=[], images=[], annotations={})],
|
||||
DetectionDataset(classes=[], images=[], annotations={}),
|
||||
DoesNotRaise(),
|
||||
), # single empty dataset
|
||||
(
|
||||
[
|
||||
DetectionDataset(classes=["dog", "person"], images={}, annotations={}),
|
||||
DetectionDataset(classes=["dog", "person"], images={}, annotations={}),
|
||||
DetectionDataset(classes=["dog", "person"], images=[], annotations={}),
|
||||
DetectionDataset(classes=["dog", "person"], images=[], annotations={}),
|
||||
],
|
||||
DetectionDataset(classes=["dog", "person"], images={}, annotations={}),
|
||||
DetectionDataset(classes=["dog", "person"], images=[], annotations={}),
|
||||
DoesNotRaise(),
|
||||
), # two datasets; no images and annotations, the same classes
|
||||
(
|
||||
[
|
||||
DetectionDataset(classes=["dog", "person"], images={}, annotations={}),
|
||||
DetectionDataset(classes=["cat"], images={}, annotations={}),
|
||||
DetectionDataset(classes=["dog", "person"], images=[], annotations={}),
|
||||
DetectionDataset(classes=["cat"], images=[], annotations={}),
|
||||
],
|
||||
DetectionDataset(
|
||||
classes=["cat", "dog", "person"], images={}, annotations={}
|
||||
classes=["cat", "dog", "person"], images=[], annotations={}
|
||||
),
|
||||
DoesNotRaise(),
|
||||
), # two datasets; no images and annotations, different classes
|
||||
@@ -43,10 +42,7 @@ from supervision import DetectionDataset
|
||||
[
|
||||
DetectionDataset(
|
||||
classes=["dog", "person"],
|
||||
images={
|
||||
"image-1.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
"image-2.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
},
|
||||
images=["image-1.png", "image-2.png"],
|
||||
annotations={
|
||||
"image-1.png": mock_detections(
|
||||
xyxy=[[0, 0, 10, 10]], class_id=[0]
|
||||
@@ -56,14 +52,11 @@ from supervision import DetectionDataset
|
||||
),
|
||||
},
|
||||
),
|
||||
DetectionDataset(classes=[], images={}, annotations={}),
|
||||
DetectionDataset(classes=[], images=[], annotations={}),
|
||||
],
|
||||
DetectionDataset(
|
||||
classes=["dog", "person"],
|
||||
images={
|
||||
"image-1.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
"image-2.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
},
|
||||
images=["image-1.png", "image-2.png"],
|
||||
annotations={
|
||||
"image-1.png": mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[0]),
|
||||
"image-2.png": mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[1]),
|
||||
@@ -75,10 +68,7 @@ from supervision import DetectionDataset
|
||||
[
|
||||
DetectionDataset(
|
||||
classes=["dog", "person"],
|
||||
images={
|
||||
"image-1.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
"image-2.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
},
|
||||
images=["image-1.png", "image-2.png"],
|
||||
annotations={
|
||||
"image-1.png": mock_detections(
|
||||
xyxy=[[0, 0, 10, 10]], class_id=[0]
|
||||
@@ -88,14 +78,11 @@ from supervision import DetectionDataset
|
||||
),
|
||||
},
|
||||
),
|
||||
DetectionDataset(classes=["cat"], images={}, annotations={}),
|
||||
DetectionDataset(classes=["cat"], images=[], annotations={}),
|
||||
],
|
||||
DetectionDataset(
|
||||
classes=["cat", "dog", "person"],
|
||||
images={
|
||||
"image-1.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
"image-2.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
},
|
||||
images=["image-1.png", "image-2.png"],
|
||||
annotations={
|
||||
"image-1.png": mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[1]),
|
||||
"image-2.png": mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[2]),
|
||||
@@ -107,10 +94,7 @@ from supervision import DetectionDataset
|
||||
[
|
||||
DetectionDataset(
|
||||
classes=["dog", "person"],
|
||||
images={
|
||||
"image-1.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
"image-2.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
},
|
||||
images=["image-1.png", "image-2.png"],
|
||||
annotations={
|
||||
"image-1.png": mock_detections(
|
||||
xyxy=[[0, 0, 10, 10]], class_id=[0]
|
||||
@@ -122,9 +106,7 @@ from supervision import DetectionDataset
|
||||
),
|
||||
DetectionDataset(
|
||||
classes=["cat"],
|
||||
images={
|
||||
"image-3.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
},
|
||||
images=["image-3.png"],
|
||||
annotations={
|
||||
"image-3.png": mock_detections(
|
||||
xyxy=[[0, 0, 10, 10]], class_id=[0]
|
||||
@@ -134,11 +116,7 @@ from supervision import DetectionDataset
|
||||
],
|
||||
DetectionDataset(
|
||||
classes=["cat", "dog", "person"],
|
||||
images={
|
||||
"image-1.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
"image-2.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
"image-3.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
},
|
||||
images=["image-1.png", "image-2.png", "image-3.png"],
|
||||
annotations={
|
||||
"image-1.png": mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[1]),
|
||||
"image-2.png": mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[2]),
|
||||
@@ -151,10 +129,7 @@ from supervision import DetectionDataset
|
||||
[
|
||||
DetectionDataset(
|
||||
classes=["dog", "person"],
|
||||
images={
|
||||
"image-1.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
"image-2.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
},
|
||||
images=["image-1.png", "image-2.png"],
|
||||
annotations={
|
||||
"image-1.png": mock_detections(
|
||||
xyxy=[[0, 0, 10, 10]], class_id=[0]
|
||||
@@ -166,10 +141,7 @@ from supervision import DetectionDataset
|
||||
),
|
||||
DetectionDataset(
|
||||
classes=["dog", "person"],
|
||||
images={
|
||||
"image-2.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
"image-3.png": np.zeros((100, 100, 3), dtype=np.uint8),
|
||||
},
|
||||
images=["image-2.png", "image-3.png"],
|
||||
annotations={
|
||||
"image-2.png": mock_detections(
|
||||
xyxy=[[0, 0, 10, 10]], class_id=[0]
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
from contextlib import ExitStack as DoesNotRaise
|
||||
from test.test_utils import mock_detections
|
||||
from typing import Dict, List, Optional, Tuple, TypeVar
|
||||
|
||||
import numpy as np
|
||||
@@ -15,6 +14,7 @@ from supervision.dataset.utils import (
|
||||
rle_to_mask,
|
||||
train_test_split,
|
||||
)
|
||||
from test.test_utils import mock_detections
|
||||
|
||||
T = TypeVar("T")
|
||||
|
||||
@@ -278,7 +278,7 @@ def test_map_detections_class_id(
|
||||
np.array([[[]]]).astype(bool),
|
||||
None,
|
||||
pytest.raises(AssertionError),
|
||||
), # raises AssertionError because mask dimentionality is not 2D
|
||||
), # raises AssertionError because mask dimensionality is not 2D
|
||||
(
|
||||
np.array([[]]).astype(bool),
|
||||
None,
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
from contextlib import ExitStack as DoesNotRaise
|
||||
from test.test_utils import mock_detections
|
||||
from typing import List, Optional, Union
|
||||
|
||||
import numpy as np
|
||||
@@ -7,6 +6,7 @@ import pytest
|
||||
|
||||
from supervision.detection.core import Detections, merge_inner_detection_object_pair
|
||||
from supervision.geometry.core import Position
|
||||
from test.test_utils import mock_detections
|
||||
|
||||
PREDICTIONS = np.array(
|
||||
[
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
import csv
|
||||
import os
|
||||
from test.test_utils import mock_detections
|
||||
from typing import Any, Dict, List
|
||||
|
||||
import pytest
|
||||
|
||||
import supervision as sv
|
||||
from test.test_utils import mock_detections
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
import json
|
||||
import os
|
||||
from test.test_utils import mock_detections
|
||||
from typing import Any, Dict, List
|
||||
|
||||
import pytest
|
||||
|
||||
import supervision as sv
|
||||
from test.test_utils import mock_detections
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
from contextlib import ExitStack as DoesNotRaise
|
||||
from test.test_utils import mock_detections
|
||||
from typing import List, Optional, Tuple
|
||||
|
||||
import pytest
|
||||
|
||||
from supervision import LineZone
|
||||
from supervision.geometry.core import Point, Position, Vector
|
||||
from test.test_utils import mock_detections
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
|
||||
@@ -237,7 +237,7 @@ from supervision.detection.lmm import from_florence_2
|
||||
DoesNotRaise(),
|
||||
),
|
||||
( # Region to Category: detected
|
||||
{"<REGION_TO_CATEGORY>": "some object<loc_3><loc_4><loc_5><loc_6>"},
|
||||
{"<REGION_TO_CATEGORY>": "some object<loc_300><loc_400><loc_500><loc_600>"},
|
||||
(10, 10),
|
||||
(
|
||||
np.array([[3, 4, 5, 6]], dtype=np.float32),
|
||||
@@ -254,11 +254,11 @@ from supervision.detection.lmm import from_florence_2
|
||||
DoesNotRaise(),
|
||||
),
|
||||
( # Region to Description: detected
|
||||
{"<REGION_TO_DESCRIPTION>": "some description<loc_3><loc_4><loc_5><loc_6>"},
|
||||
{"<REGION_TO_DESCRIPTION>": "descr<loc_300><loc_400><loc_500><loc_600>"},
|
||||
(10, 10),
|
||||
(
|
||||
np.array([[3, 4, 5, 6]], dtype=np.float32),
|
||||
np.array(["some description"]),
|
||||
np.array(["descr"]),
|
||||
None,
|
||||
None,
|
||||
),
|
||||
|
||||
@@ -1,10 +1,10 @@
|
||||
from contextlib import ExitStack as DoesNotRaise
|
||||
from test.test_utils import mock_detections
|
||||
|
||||
import numpy as np
|
||||
import pytest
|
||||
|
||||
import supervision as sv
|
||||
from test.test_utils import mock_detections
|
||||
|
||||
DETECTION_BOXES = np.array(
|
||||
[
|
||||
@@ -26,7 +26,6 @@ DETECTIONS = mock_detections(
|
||||
)
|
||||
|
||||
POLYGON = np.array([[100, 100], [200, 100], [200, 200], [100, 200]])
|
||||
FRAME_RESOLUTION = (300, 300)
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
@@ -36,7 +35,6 @@ FRAME_RESOLUTION = (300, 300)
|
||||
DETECTIONS,
|
||||
sv.PolygonZone(
|
||||
POLYGON,
|
||||
FRAME_RESOLUTION,
|
||||
triggering_anchors=(
|
||||
sv.Position.TOP_LEFT,
|
||||
sv.Position.TOP_RIGHT,
|
||||
@@ -53,7 +51,6 @@ FRAME_RESOLUTION = (300, 300)
|
||||
DETECTIONS,
|
||||
sv.PolygonZone(
|
||||
POLYGON,
|
||||
FRAME_RESOLUTION,
|
||||
),
|
||||
np.array(
|
||||
[False, False, True, True, True, True, False, False, False], dtype=bool
|
||||
@@ -64,7 +61,6 @@ FRAME_RESOLUTION = (300, 300)
|
||||
DETECTIONS,
|
||||
sv.PolygonZone(
|
||||
POLYGON,
|
||||
FRAME_RESOLUTION,
|
||||
triggering_anchors=[sv.Position.BOTTOM_CENTER],
|
||||
),
|
||||
np.array(
|
||||
@@ -76,7 +72,6 @@ FRAME_RESOLUTION = (300, 300)
|
||||
sv.Detections.empty(),
|
||||
sv.PolygonZone(
|
||||
POLYGON,
|
||||
FRAME_RESOLUTION,
|
||||
),
|
||||
np.array([], dtype=bool),
|
||||
DoesNotRaise(),
|
||||
@@ -107,4 +102,4 @@ def test_polygon_zone_trigger(
|
||||
)
|
||||
def test_polygon_zone_initialization(polygon, triggering_anchors, exception):
|
||||
with exception:
|
||||
sv.PolygonZone(polygon, FRAME_RESOLUTION, triggering_anchors=triggering_anchors)
|
||||
sv.PolygonZone(polygon, triggering_anchors=triggering_anchors)
|
||||
|
||||
@@ -17,6 +17,8 @@ from supervision.detection.utils import (
|
||||
move_boxes,
|
||||
process_roboflow_result,
|
||||
scale_boxes,
|
||||
xcycwh_to_xyxy,
|
||||
xywh_to_xyxy,
|
||||
)
|
||||
|
||||
TEST_MASK = np.zeros((1, 1000, 1000), dtype=bool)
|
||||
@@ -973,7 +975,7 @@ def test_get_data_item(
|
||||
),
|
||||
False,
|
||||
DoesNotRaise(),
|
||||
), # foreground object in 2 seperate elements
|
||||
), # foreground object in 2 separate elements
|
||||
(
|
||||
np.array([[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0]]).astype(
|
||||
bool
|
||||
@@ -1030,7 +1032,7 @@ def test_contains_holes(
|
||||
4,
|
||||
True,
|
||||
DoesNotRaise(),
|
||||
), # foreground object in 2 seperate elements
|
||||
), # foreground object in 2 separate elements
|
||||
(
|
||||
np.array([[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0]]).astype(
|
||||
bool
|
||||
@@ -1090,3 +1092,49 @@ def test_contains_multiple_segments(
|
||||
with exception:
|
||||
result = contains_multiple_segments(mask=mask, connectivity=connectivity)
|
||||
assert result == expected_result
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"xywh, expected_result",
|
||||
[
|
||||
(np.array([[10, 20, 30, 40]]), np.array([[10, 20, 40, 60]])), # standard case
|
||||
(np.array([[0, 0, 0, 0]]), np.array([[0, 0, 0, 0]])), # zero size bounding box
|
||||
(
|
||||
np.array([[50, 50, 100, 100]]),
|
||||
np.array([[50, 50, 150, 150]]),
|
||||
), # large bounding box
|
||||
(
|
||||
np.array([[-10, -20, 30, 40]]),
|
||||
np.array([[-10, -20, 20, 20]]),
|
||||
), # negative coordinates
|
||||
(np.array([[50, 50, 0, 30]]), np.array([[50, 50, 50, 80]])), # zero width
|
||||
(np.array([[50, 50, 20, 0]]), np.array([[50, 50, 70, 50]])), # zero height
|
||||
(np.array([]).reshape(0, 4), np.array([]).reshape(0, 4)), # empty array
|
||||
],
|
||||
)
|
||||
def test_xywh_to_xyxy(xywh: np.ndarray, expected_result: np.ndarray) -> None:
|
||||
result = xywh_to_xyxy(xywh)
|
||||
np.testing.assert_array_equal(result, expected_result)
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"xcycwh, expected_result",
|
||||
[
|
||||
(np.array([[50, 50, 20, 30]]), np.array([[40, 35, 60, 65]])), # standard case
|
||||
(np.array([[0, 0, 0, 0]]), np.array([[0, 0, 0, 0]])), # zero size bounding box
|
||||
(
|
||||
np.array([[50, 50, 100, 100]]),
|
||||
np.array([[0, 0, 100, 100]]),
|
||||
), # large bounding box centered at (50, 50)
|
||||
(
|
||||
np.array([[-10, -10, 20, 30]]),
|
||||
np.array([[-20, -25, 0, 5]]),
|
||||
), # negative coordinates
|
||||
(np.array([[50, 50, 0, 30]]), np.array([[50, 35, 50, 65]])), # zero width
|
||||
(np.array([[50, 50, 20, 0]]), np.array([[40, 50, 60, 50]])), # zero height
|
||||
(np.array([]).reshape(0, 4), np.array([]).reshape(0, 4)), # empty array
|
||||
],
|
||||
)
|
||||
def test_xcycwh_to_xyxy(xcycwh: np.ndarray, expected_result: np.ndarray) -> None:
|
||||
result = xcycwh_to_xyxy(xcycwh)
|
||||
np.testing.assert_array_equal(result, expected_result)
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
from contextlib import ExitStack as DoesNotRaise
|
||||
from test.test_utils import assert_almost_equal, mock_detections
|
||||
from typing import Optional, Union
|
||||
|
||||
import numpy as np
|
||||
@@ -11,6 +10,7 @@ from supervision.metrics.detection import (
|
||||
MeanAveragePrecision,
|
||||
detections_to_tensor,
|
||||
)
|
||||
from test.test_utils import assert_almost_equal, mock_detections
|
||||
|
||||
CLASSES = np.arange(80)
|
||||
NUM_CLASSES = len(CLASSES)
|
||||
|
||||
+3
-2
@@ -1,13 +1,14 @@
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
import numpy as np
|
||||
import numpy.typing as npt
|
||||
|
||||
from supervision.detection.core import Detections
|
||||
from supervision.keypoint.core import KeyPoints
|
||||
|
||||
|
||||
def mock_detections(
|
||||
xyxy: List[List[float]],
|
||||
xyxy: npt.NDArray[np.float32],
|
||||
mask: Optional[List[np.ndarray]] = None,
|
||||
confidence: Optional[List[float]] = None,
|
||||
class_id: Optional[List[int]] = None,
|
||||
@@ -32,7 +33,7 @@ def mock_detections(
|
||||
|
||||
|
||||
def mock_keypoints(
|
||||
xy: List[List[float]],
|
||||
xy: npt.NDArray[np.float32],
|
||||
confidence: Optional[List[float]] = None,
|
||||
class_id: Optional[List[int]] = None,
|
||||
data: Optional[Dict[str, List[Any]]] = None,
|
||||
|
||||
Reference in New Issue
Block a user