Merge pull request #337 from roboflow/develop

`supervision-0.14.0` release

.gitattributes

@@ -1 +1 @@
-*.ipynb linguist-vendored
+*.ipynb linguist-vendored

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -62,4 +62,4 @@ body:
       description: >
         (Optional) We encourage you to submit a [Pull Request](https://github.com/roboflow/supervision/pulls) (PR) to help improve Supervision for everyone, especially if you have a good understanding of how to implement a fix or feature.
       options:
-        - label: Yes I'd like to help by submitting a PR!
+        - label: Yes I'd like to help by submitting a PR!

.github/ISSUE_TEMPLATE/feature-request.yml

@@ -46,4 +46,4 @@ body:
       description: >
         (Optional) We encourage you to submit a [Pull Request](https://github.com/roboflow/supervision/pulls) (PR) to help improve Supervision for everyone, especially if you have a good understanding of how to implement a fix or feature.
       options:
-        - label: Yes I'd like to help by submitting a PR!
+        - label: Yes I'd like to help by submitting a PR!

.github/ISSUE_TEMPLATE/question.yml

@@ -30,4 +30,4 @@ body:
   - type: textarea
     attributes:
       label: Additional
-      description: Anything else you would like to share?
+      description: Anything else you would like to share?

.github/workflows/publish-test.yml

@@ -0,0 +1,41 @@
+name: Supervision Test Releases to PyPi
+on:
+  push:
+    tags:
+      - '[0-9]+.[0-9]+[0-9]+.[0-9]+a[0-9]'
+      - '[0-9]+.[0-9]+[0-9]+.[0-9]+b[0-9]'
+      - '[0-9]+.[0-9]+[0-9]+.[0-9]+rc[0-9]'
+
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+jobs:
+  build-n-publish:
+    name: Build and publish to PyPI
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout source
+        uses: actions/checkout@v3
+
+      - name: 🐍 Set up Python 3.8 environment for build
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
+
+      - name: 🏗️ Build source and wheel distributions
+        run: |
+          python -m pip install --upgrade build twine
+          python -m build
+          twine check --strict dist/*
+      - name: 🚀 Publish distribution to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          user: ${{ secrets.PYPI_USERNAME }}
+          password: ${{ secrets.PYPI_PASSWORD }}
+      - name: 🚀 Publish to Test-PyPi
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          repository-url: https://test.pypi.org/legacy/
+          user: ${{ secrets.PYPI_TEST_USERNAME }}
+          password: ${{ secrets.PYPI_TEST_PASSWORD }}

.github/workflows/publish.yml

@@ -1,8 +1,13 @@
-name: Publish WorkFlow
-
+name: Supervision Releases to PyPi
 on:
-  release:
-    types: [created]
+  push:
+    tags:
+      - '[0-9]+.[0-9]+[0-9]+.[0-9]'
+      - '[0-9]+.[0-9]+[0-9]+.[0-9]'
+      - '[0-9]+.[0-9]+[0-9]+.[0-9]'
+
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
 
 jobs:
   build:
@@ -19,15 +24,6 @@ jobs:
         uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
-      - name: 🦾 Install dependencies
-        run: |
-          python -m pip install --upgrade virtualenv
-          python -m pip install --upgrade pip
-          virtualenv venv
-          source venv/bin/activate
-          python -m pip install --upgrade pip
-          python -m pip install --upgrade poetry
-          poetry install
 
       - name:  🏗️ Build source and wheel distributions
         run: |
@@ -43,5 +39,5 @@ jobs:
         uses: pypa/gh-action-pypi-publish@release/v1
         with:
           repository-url: https://test.pypi.org/legacy/
-          user: ${{ secrets.PYPI_USERNAME }}
+          user: ${{ secrets.PYPI_TEST_USERNAME }}
           password: ${{ secrets.PYPI_TEST_PASSWORD }}

.github/workflows/test.yml

@@ -25,8 +25,5 @@ jobs:
           pip install isort
           pip install flake8
           pip install "black==22.3.0"
-      - name: 🧹 Lint with flake8
-        run: |
-          make check_code_quality
       - name: 🧪 Test
-        run: "python -m pytest ./test"
+        run: "python -m pytest ./test"

.github/workflows/welcome.yml

@@ -15,4 +15,4 @@ jobs:
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
           issue-message: "Hello there, thank you for opening an Issue ! 🙏🏻 The team was notified and they will get back to you asap."
-          pr-message:  "Hello there, thank you for opening an PR ! 🙏🏻 The team was notified and they will get back to you asap."
+          pr-message:  "Hello there, thank you for opening an PR ! 🙏🏻 The team was notified and they will get back to you asap."

.gitignore

@@ -54,6 +54,7 @@ coverage.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
+.ruff_cache/
 
 # Translations
 *.mo

.pre-commit-config.yaml

@@ -0,0 +1,80 @@
+
+ci:
+  autofix_prs: true
+  autoupdate_schedule: weekly
+  autofix_commit_msg: "fix(pre_commit): 🎨 auto format pre-commit hooks"
+  autoupdate_commit_msg: "chore(pre_commit): ⬆ pre_commit autoupdate"
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+      - id: check-yaml
+      - id: check-docstring-first
+      - id: check-executables-have-shebangs
+      - id: check-toml
+      - id: check-case-conflict
+      - id: check-added-large-files
+        args: ['--maxkb=2048']
+        exclude: ^logo/
+      - id: detect-private-key
+      - id: forbid-new-submodules
+      - id: pretty-format-json
+        args: ['--autofix', '--no-sort-keys', '--indent=4']
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+
+  # - repo: https://github.com/asottile/pyupgrade
+  #   rev: v3.9.0
+  #   hooks:
+  #     - id: pyupgrade
+  #       name: Upgrade code
+  #       args: [--py38-plus]
+
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.12.0
+    hooks:
+      - id: isort
+        name: Sort imports
+
+  - repo: https://github.com/PyCQA/flake8
+    rev: 6.1.0
+    hooks:
+      - id: flake8
+        name: Flake8 Checks
+        entry: flake8
+        additional_dependencies: [Flake8-pyproject]
+
+
+  -   repo: https://github.com/PyCQA/bandit
+      rev: '1.7.5'
+      hooks:
+      -   id: bandit
+          args: ["-c", "pyproject.toml"]
+          additional_dependencies: ["bandit[toml]"]
+
+  -   repo: https://github.com/pycqa/isort
+      rev: 5.12.0
+      hooks:
+      -   id: isort
+          name: isort (python)
+      -   id: isort
+          name: isort (cython)
+          types: [cython]
+      -   id: isort
+          name: isort (pyi)
+          types: [pyi]
+
+
+  -   repo: https://github.com/psf/black
+      rev: 23.7.0
+      hooks:
+      -   id: black
+
+  -   repo: https://github.com/astral-sh/ruff-pre-commit
+      rev: v0.0.286
+      hooks:
+      -   id: ruff
+          args: [--fix, --exit-non-zero-on-fix]

CITATION.cff

@@ -1,12 +1,23 @@
+# This CITATION.cff file was generated with cffinit.
+# Visit https://bit.ly/cffinit to generate yours today!
+
 cff-version: 1.2.0
-author: Roboflow
-message: If you use this software, please cite it as below.
-title: supervision
-version: 0.11.1
-date-released: 2023-01-19
-license: MIT
-repository-code: https://github.com/roboflow/supervision
+title: Supervision
+message: >-
+  If you use this software, please cite it using the
+  metadata from this file.
+type: software
+authors:
+  - given-names: Roboflow
+    email: support@roboflow.com
+repository-code: 'https://github.com/roboflow/supervision'
+url: 'https://roboflow.github.io/supervision/'
+abstract: >-
+  supervision features a range of utilities for use in
+  computer vision projects, from detections processing and
+  filtering to confusion matrix calcuation.
 keywords:
   - computer vision
   - image processing
-  - video processing
+  - video processing
+license: MIT

CONTRIBUTING.md

@@ -14,7 +14,7 @@ We welcome contributions to:
 4. Submit a request for a new feature.
 5. Improve our test coverage.
 
-### Contributing Features
+### Contributing Features ✨
 
 Supervision is designed to provide generic utilities to solve problems. Thus, we focus on contributions that can have an impact on a wide range of projects.
 
@@ -24,7 +24,72 @@ Before you contribute a new feature, consider submitting an Issue to discuss the
 
 ## How to Contribute Changes
 
-First, fork this repository to your own GitHub account. Create a new branch that describes your changes (i.e. `line-counter-docs`). Push your changes to the branch on your fork and then submit a pull request to `develop` branch of this repository.
+First, fork this repository to your own GitHub account. Click "fork" in the top corner of the `supervision` repository to get started:
+
+![Forking the repository](https://media.roboflow.com/fork.png)
+
+![Creating a repository fork](https://media.roboflow.com/create_fork.png)
+
+Then, run `git clone` to download the project code to your computer.
+
+Move to a new branch using the `git checkout` command:
+
+```bash
+git checkout -b <your_branch_name>
+```
+
+The name you choose for your branch should describe the change you want to make (i.e. `line-counter-docs`).
+
+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
+```
+
+## 🎨 Code quality
+
+### Pre-commit tool
+
+This project utilizes 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 execute `pre-commit install`. Every time you made `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).
+
+
+Then, go back to your fork of the `supervision` repository, click "Pull Requests", and click "New Pull Request".
+
+![Opening a pull request](https://media.roboflow.com/open_pr.png)
+
+Make sure the `base` branch is `develop` before submitting your PR.
+
+On the next page, review your changes then click "Create pull request":
+
+![Configuring a pull request](https://media.roboflow.com/create_pr_submit.png)
+
+Next, write a description for your pull request, and click "Create pull request" again to submit it for review:
+
+![Submitting a pull request](https://media.roboflow.com/write_pr.png)
 
 When creating new functions, please ensure you have the following:
 
@@ -32,21 +97,26 @@ When creating new functions, please ensure you have the following:
 2. Unit tests for the function.
 3. Examples in the documentation for the function.
 4. Created an entry in our docs to autogenerate the documentation for the function.
-5. Please share google colab with minimal code to test new feature or reproduce PR whenever it is possible. Please ensure that google colab can be accessed without any issue. 
+5. Please share a Google Colab with minimal code to test new feature or reproduce PR whenever it is possible. Please ensure that Google Colab can be accessed without any issue.
+
+When you submit your Pull Request, you will be asked to sign a Contributor License Agreement (CLA) by the `cla-assistant` GitHub bot. We can only respond to PRs from contributors who have signed the project CLA.
 
 All pull requests will be reviewed by the maintainers of the project. We will provide feedback and ask for changes if necessary.
 
 PRs must pass all tests and linting requirements before they can be merged.
 
-## 🧹 code quality 
+## 📝 documentation
 
-We provide two handy commands inside the `Makefile`, namely:
+The `supervision` documentation is stored in a folder called `docs`. The project documentation is built using `mkdocs`.
 
-- `make style` to format the code
-- `make check_code_quality` to check code quality (PEP8 basically)
+To run the documentation, install the project requirements with `poetry install dev`. Then, run `mkdocs serve` to start the documentation server.
 
-So far, **there is no types checking with mypy**. See [issue](https://github.com/roboflow-ai/template-python/issues/4). 
+You can learn more about mkdocs on the [mkdocs website](https://www.mkdocs.org/).
 
-## 🧪 tests 
+## 🧪 tests
 
 [`pytests`](https://docs.pytest.org/en/7.1.x/) is used to run our tests.
+
+## 📄 license
+
+By contributing, you agree that your contributions will be licensed under an [MIT license](https://github.com/roboflow/supervision/blob/develop/LICENSE.md).

Makefile

@@ -12,11 +12,11 @@ check_code_quality:
 	isort --check-only --profile black $(check_dirs)
 	# stop the build if there are Python syntax errors or undefined names
 	flake8 $(check_dirs) --count --select=E9,F63,F7,F82 --show-source --statistics
-	# exit-zero treats all errors as warnings. E203 for black, E501 for docstring, W503 for line breaks before logical operators 
+	# exit-zero treats all errors as warnings. E203 for black, E501 for docstring, W503 for line breaks before logical operators
 	flake8 $(check_dirs) --count --max-line-length=88 --exit-zero  --ignore=D --extend-ignore=E203,E501,W503  --statistics
-	
+
 publish:
 	poetry build
-	twine upload -r testpypi dist/* -u ${PYPI_USERNAME} -p ${PYPI_TEST_PASSWORD} --verbose 
+	twine upload -r testpypi dist/* -u ${PYPI_USERNAME} -p ${PYPI_TEST_PASSWORD} --verbose
 	twine check dist/*
-	twine upload dist/* -u ${PYPI_USERNAME} -p ${PYPI_PASSWORD} --verbose 
+	twine upload dist/* -u ${PYPI_USERNAME} -p ${PYPI_PASSWORD} --verbose

README.md

@@ -10,11 +10,15 @@
 
   <br>
 
-[![version](https://badge.fury.io/py/supervision.svg)](https://badge.fury.io/py/supervision)
-[![downloads](https://img.shields.io/pypi/dm/supervision)](https://pypistats.org/packages/supervision)
-[![license](https://img.shields.io/pypi/l/supervision)](https://github.com/roboflow/supervision/blob/main/LICENSE.md)
-[![python-version](https://img.shields.io/pypi/pyversions/supervision)](https://badge.fury.io/py/supervision)
-[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/roboflow/supervision/blob/main/demo.ipynb)
+  [notebooks](https://github.com/roboflow/notebooks) | [inference](https://github.com/roboflow/inference) | [autodistill](https://github.com/autodistill/autodistill) | [collect](https://github.com/roboflow/roboflow-collect)
+
+  <br>
+
+  [![version](https://badge.fury.io/py/supervision.svg)](https://badge.fury.io/py/supervision)
+  [![downloads](https://img.shields.io/pypi/dm/supervision)](https://pypistats.org/packages/supervision)
+  [![license](https://img.shields.io/pypi/l/supervision)](https://github.com/roboflow/supervision/blob/main/LICENSE.md)
+  [![python-version](https://img.shields.io/pypi/pyversions/supervision)](https://badge.fury.io/py/supervision)
+  [![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/roboflow/supervision/blob/main/demo.ipynb)
 
 </div>
 
@@ -43,7 +47,7 @@ Read more about desktop, headless, and local installation in our [guide](https:/
 
 >>> model = YOLO('yolov8s.pt')
 >>> result = model(IMAGE)[0]
->>> detections = sv.Detections.from_yolov8(result)
+>>> detections = sv.Detections.from_ultralytics(result)
 
 >>> len(detections)
 5
@@ -51,9 +55,9 @@ Read more about desktop, headless, and local installation in our [guide](https:/
 
 <details close>
 <summary>👉 more detections utils</summary>
-  
+
 - Easily switch inference pipeline between supported object detection/instance segmentation models
-  
+
     ```python
     >>> import supervision as sv
     >>> from segment_anything import sam_model_registry, SamAutomaticMaskGenerator
@@ -63,17 +67,17 @@ Read more about desktop, headless, and local installation in our [guide](https:/
     >>> sam_result = mask_generator.generate(IMAGE)
     >>> detections = sv.Detections.from_sam(sam_result=sam_result)
     ```
- 
+
 - [Advanced filtering](https://roboflow.github.io/supervision/quickstart/detections/)
-  
+
     ```python
     >>> detections = detections[detections.class_id == 0]
     >>> detections = detections[detections.confidence > 0.5]
     >>> detections = detections[detections.area > 1000]
     ```
-  
+
 - Image annotation
-  
+
     ```python
     >>> import supervision as sv
 
@@ -83,7 +87,7 @@ Read more about desktop, headless, and local installation in our [guide](https:/
     ...     detections=detections
     ... )
     ```
-  
+
 </details>
 
 ### [datasets processing](https://roboflow.github.io/supervision/dataset/core/)
@@ -126,7 +130,7 @@ Read more about desktop, headless, and local installation in our [guide](https:/
     ...     annotations_path='...'
     ... )
     ```
-  
+
 - Loop over dataset entries
 
     ```python
@@ -137,17 +141,17 @@ Read more about desktop, headless, and local installation in our [guide](https:/
            [155.      , 497.      , 404.      , 833.5     ],
            [ 20.154999, 347.825   , 416.125   , 915.895   ]], dtype=float32)
     ```
-  
+
 - Split dataset for training, testing, and validation
-  
+
     ```python
     >>> train_dataset, test_dataset = dataset.split(split_ratio=0.7)
     >>> test_dataset, valid_dataset = test_dataset.split(split_ratio=0.5)
-  
+
     >>> len(train_dataset), len(test_dataset), len(valid_dataset)
     (700, 150, 150)
     ```
-  
+
 - Merge multiple datasets
 
     ```python
@@ -156,22 +160,22 @@ Read more about desktop, headless, and local installation in our [guide](https:/
     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']
     ```
-  
+
 - Save object detection/instance segmentation datasets in one of the supported formats
-  
+
     ```python
     >>> dataset.as_yolo(
     ...     images_directory_path='...',
@@ -189,9 +193,9 @@ Read more about desktop, headless, and local installation in our [guide](https:/
     ...     annotations_path='...'
     ... )
     ```
-  
+
 - Convert labels between supported formats
-  
+
     ```python
     >>> sv.DetectionDataset.from_yolo(
     ...     images_directory_path='...',
@@ -202,7 +206,7 @@ Read more about desktop, headless, and local installation in our [guide](https:/
     ...     annotations_directory_path='...'
     ... )
     ```
-  
+
 - Load classification datasets in one of the supported formats
 
     ```python
@@ -252,42 +256,48 @@ array([
 
     ```python
     >>> import supervision as sv
-    
+
     >>> dataset = sv.DetectionDataset.from_yolo(...)
-    
+
     >>> def callback(image: np.ndarray) -> sv.Detections:
     ...     ...
-    
+
     >>> mean_average_precision = sv.MeanAveragePrecision.benchmark(
     ...     dataset = dataset,
     ...     callback = callback
     ... )
-    
+
     >>> mean_average_precision.map50_95
-    0.433 
+    0.433
     ```
-  
+
 </details>
 
+## 🛠️ built with supervision
+
+Did you build something cool using supervision? [Let us know!](https://github.com/roboflow/supervision/discussions/categories/built-with-supervision)
+
+https://user-images.githubusercontent.com/26109316/207858600-ee862b22-0353-440b-ad85-caa0c4777904.mp4
+
 ## 🎬 tutorials
 
 <p align="left">
 <a href="https://youtu.be/oEQYStnF2l8" title="Accelerate Image Annotation with SAM and Grounding DINO"><img src="https://github.com/SkalskiP/SkalskiP/assets/26109316/ae1ca38e-40b7-4b35-8582-e8ea5de3806e" alt="Accelerate Image Annotation with SAM and Grounding DINO" width="300px" align="left" /></a>
 <a href="https://youtu.be/oEQYStnF2l8" title="Accelerate Image Annotation with SAM and Grounding DINO"><strong>Accelerate Image Annotation with SAM and Grounding DINO</strong></a>
 <div><strong>Created: 20 Apr 2023</strong> | <strong>Updated: 20 Apr 2023</strong></div>
-<br/> Discover how to speed up your image annotation process using Grounding DINO and Segment Anything Model (SAM). Learn how to convert object detection datasets into instance segmentation datasets, and see the potential of using these models to automatically annotate your datasets for real-time detectors like YOLOv8... </p> 
+<br/> Discover how to speed up your image annotation process using Grounding DINO and Segment Anything Model (SAM). Learn how to convert object detection datasets into instance segmentation datasets, and see the potential of using these models to automatically annotate your datasets for real-time detectors like YOLOv8... </p>
 
-<br/> 
+<br/>
 
 <p align="left">
-<a href="https://youtu.be/oEQYStnF2l8" title="SAM - Segment Anything Model by Meta AI: Complete Guide"><img src="https://github.com/SkalskiP/SkalskiP/assets/26109316/6913ff11-53c6-4341-8d90-eaff3023c3fd" alt="SAM - Segment Anything Model by Meta AI: Complete Guide" width="300px" align="left" /></a>
-<a href="https://youtu.be/oEQYStnF2l8" title="SAM - Segment Anything Model by Meta AI: Complete Guide"><strong>SAM - Segment Anything Model by Meta AI: Complete Guide</strong></a>
+<a href="https://youtu.be/D-D6ZmadzPE" title="SAM - Segment Anything Model by Meta AI: Complete Guide"><img src="https://github.com/SkalskiP/SkalskiP/assets/26109316/6913ff11-53c6-4341-8d90-eaff3023c3fd" alt="SAM - Segment Anything Model by Meta AI: Complete Guide" width="300px" align="left" /></a>
+<a href="https://youtu.be/D-D6ZmadzPE" title="SAM - Segment Anything Model by Meta AI: Complete Guide"><strong>SAM - Segment Anything Model by Meta AI: Complete Guide</strong></a>
 <div><strong>Created: 11 Apr 2023</strong> | <strong>Updated: 11 Apr 2023</strong></div>
 <br/> Discover the incredible potential of Meta AI's Segment Anything Model (SAM)! We dive into SAM, an efficient and promptable model for image segmentation, which has revolutionized computer vision tasks. With over 1 billion masks on 11M licensed and privacy-respecting images, SAM's zero-shot performance is often competitive with or even superior to prior fully supervised results... </p>
 
 ## 📚 documentation
 
-Visit our [documentation](https://roboflow.github.io/supervision) page to learn how supervision can help you build computer vision applications faster and more reliably. 
+Visit our [documentation](https://roboflow.github.io/supervision) page to learn how supervision can help you build computer vision applications faster and more reliably.
 
 ## 🏆 contribution
 

docs/CNAME

@@ -0,0 +1 @@
+supervision.roboflow.com

docs/changelog.md

@@ -1,6 +1,41 @@
+### 0.14.0 <small>August 31, 2023</small>
+
+- Added [#282](https://github.com/roboflow/supervision/pull/282): support for SAHI inference technique with [`sv.InferenceSlicer`](https://supervision.roboflow.com/detection/tools/inference_slicer).
+
+```python
+>>> import cv2
+>>> import supervision as sv
+>>> from ultralytics import YOLO
+
+>>> image = cv2.imread(SOURCE_IMAGE_PATH)
+>>> model = YOLO(...)
+
+>>> def callback(image_slice: np.ndarray) -> sv.Detections:
+...     result = model(image_slice)[0]
+...     return sv.Detections.from_ultralytics(result)
+
+>>> slicer = sv.InferenceSlicer(callback = callback)
+
+>>> detections = slicer(image)
+```
+
+- Added [#297](https://github.com/roboflow/supervision/pull/297): [`Detections.from_deepsparse`](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.from_deepsparse) to enable seamless integration with [DeepSparse](https://github.com/neuralmagic/deepsparse) framework.
+
+- Added [#281](https://github.com/roboflow/supervision/pull/281): [`sv.Classifications.from_ultralytics`](https://supervision.roboflow.com/classification/core/#supervision.classification.core.Classifications.from_ultralytics) to enable seamless integration with [Ultralytics](https://github.com/ultralytics/ultralytics) framework. This will enable you to use supervision with all [models](https://docs.ultralytics.com/models/) that Ultralytics supports.
+
+!!! warning
+
+    [sv.Detections.from_yolov8](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.from_yolov8) and [sv.Classifications.from_yolov8](https://supervision.roboflow.com/classification/core/#supervision.classification.core.Classifications.from_yolov8) are now deprecated and will be removed with supervision-0.16.0 release.
+
+- Added [#341](https://github.com/roboflow/supervision/pull/341): First supervision usage example script showing how to detect and track objects on video using YOLOv8 + Supervision.
+
+- Changed [#296](https://github.com/roboflow/supervision/pull/296): [`sv.ClassificationDataset`](https://supervision.roboflow.com/dataset/core/#supervision.dataset.core.ClassificationDataset) and [`sv.DetectionDataset`](https://supervision.roboflow.com/dataset/core/#supervision.dataset.core.DetectionDataset) now use image path (not image name) as dataset keys.
+
+- Fixed [#300](https://github.com/roboflow/supervision/pull/300): [`Detections.from_roboflow`](https://supervision.roboflow.com/detection/core/#supervision.detection.core.Detections.from_roboflow) to filter out polygons with less than 3 points.
+
 ### 0.13.0 <small>August 8, 2023</small>
 
-- Added [#236](https://github.com/roboflow/supervision/pull/236): support for mean average precision (mAP) for object detection models with [`sv.MeanAveragePrecision`](https://roboflow.github.io/supervision/metrics/detection/#meanaverageprecision). 
+- Added [#236](https://github.com/roboflow/supervision/pull/236): support for mean average precision (mAP) for object detection models with [`sv.MeanAveragePrecision`](https://roboflow.github.io/supervision/metrics/detection/#meanaverageprecision).
 
 ```python
 >>> import supervision as sv
@@ -83,7 +118,7 @@ array([
 
 ### 0.11.0 <small>June 28, 2023</small>
 
-- Added [#150](https://github.com/roboflow/supervision/pull/150): ability to load and save [`sv.DetectionDataset`](https://roboflow.github.io/supervision/dataset/core/#detectiondataset) in COCO format using [`as_coco`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.as_coco) and [`from_coco`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.from_coco) methods. 
+- Added [#150](https://github.com/roboflow/supervision/pull/150): ability to load and save [`sv.DetectionDataset`](https://roboflow.github.io/supervision/dataset/core/#detectiondataset) in COCO format using [`as_coco`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.as_coco) and [`from_coco`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.from_coco) methods.
 
 ```python
 >>> import supervision as sv
@@ -99,7 +134,7 @@ array([
 ... )
 ```
 
-- Added [#158](https://github.com/roboflow/supervision/pull/158): ability to marge multiple [`sv.DetectionDataset`](https://roboflow.github.io/supervision/dataset/core/#detectiondataset) together using [`merge`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.merge) method. 
+- Added [#158](https://github.com/roboflow/supervision/pull/158): ability to marge multiple [`sv.DetectionDataset`](https://roboflow.github.io/supervision/dataset/core/#detectiondataset) together using [`merge`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.merge) method.
 
 ```python
 >>> import supervision as sv
@@ -145,11 +180,11 @@ array([
 
 - Added [#125](https://github.com/roboflow/supervision/pull/125): support for [`sv.ClassificationDataset.split`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.ClassificationDataset.split) allowing to divide `sv.ClassificationDataset` into two parts.
 
-- Added [#110](https://github.com/roboflow/supervision/pull/110): ability to extract masks from Roboflow API results using [`sv.Detections.from_roboflow`](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.from_roboflow). 
+- Added [#110](https://github.com/roboflow/supervision/pull/110): ability to extract masks from Roboflow API results using [`sv.Detections.from_roboflow`](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.from_roboflow).
 
 - Added [commit hash](https://github.com/roboflow/supervision/commit/d000292eb2f2342544e0947b65528082e60fb8d6): Supervision Quickstart [notebook](https://colab.research.google.com/github/roboflow/supervision/blob/main/demo.ipynb) where you can learn more about Detection, Dataset and Video APIs.
 
-- Changed [#135](https://github.com/roboflow/supervision/pull/135): `sv.get_video_frames_generator` documentation to better describe actual behavior.  
+- Changed [#135](https://github.com/roboflow/supervision/pull/135): `sv.get_video_frames_generator` documentation to better describe actual behavior.
 
 ### 0.9.0 <small>June 7, 2023</small>
 
@@ -168,7 +203,7 @@ array([
 ```
 
 - Added [#101](https://github.com/roboflow/supervision/pull/101): ability to extract masks from YOLOv8 result using [`sv.Detections.from_yolov8`](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.from_yolov8). Here is an example illustrating how to extract boolean masks from the result of the YOLOv8 model inference.
- 
+
 - Added [#122](https://github.com/roboflow/supervision/pull/122): ability to crop image using [`sv.crop`](https://roboflow.github.io/supervision/utils/image/#crop). Here is an example showing how to get a separate crop for each detection in `sv.Detections`.
 
 - Added [#120](https://github.com/roboflow/supervision/pull/120): ability to conveniently save multiple images into directory using [`sv.ImageSink`](https://roboflow.github.io/supervision/utils/image/#imagesink). Here is an example showing how to save every tenth video frame as a separate image.
@@ -186,7 +221,7 @@ array([
 ### 0.8.0 <small>May 17, 2023</small>
 
 - Added [#100](https://github.com/roboflow/supervision/pull/100): support for dataset inheritance. The current `Dataset` got renamed to `DetectionDataset`. Now [`DetectionDataset`](https://roboflow.github.io/supervision/dataset/core/#detectiondataset) inherits from `BaseDataset`. This change was made to enforce the future consistency of APIs of different types of computer vision datasets.
-- Added [#100](https://github.com/roboflow/supervision/pull/100): ability to save datasets in YOLO format using [`DetectionDataset.as_yolo`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.as_yolo). 
+- Added [#100](https://github.com/roboflow/supervision/pull/100): ability to save datasets in YOLO format using [`DetectionDataset.as_yolo`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.as_yolo).
 
 ```python
 >>> import roboflow
@@ -210,7 +245,7 @@ array([
 ['dog', 'person']
 ```
 
-- Added [#102](https://github.com/roboflow/supervision/pull/103): support for [`DetectionDataset.split`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.split) allowing to divide `DetectionDataset` into two parts. 
+- Added [#102](https://github.com/roboflow/supervision/pull/103): support for [`DetectionDataset.split`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.split) allowing to divide `DetectionDataset` into two parts.
 
 ```python
 >>> import supervision as sv
@@ -227,14 +262,14 @@ array([
 ### 0.7.0 <small>May 11, 2023</small>
 
 - Added [#91](https://github.com/roboflow/supervision/pull/91): `Detections.from_yolo_nas` to enable seamless integration with [YOLO-NAS](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md) model.
-- Added [#86](https://github.com/roboflow/supervision/pull/86): ability to load datasets in YOLO format using `Dataset.from_yolo`. 
+- Added [#86](https://github.com/roboflow/supervision/pull/86): ability to load datasets in YOLO format using `Dataset.from_yolo`.
 - Added [#84](https://github.com/roboflow/supervision/pull/84): `Detections.merge` to merge multiple `Detections` objects together.
 - Fixed [#81](https://github.com/roboflow/supervision/pull/81): `LineZoneAnnotator.annotate` does not return annotated frame.
 - Changed [#44](https://github.com/roboflow/supervision/pull/44): `LineZoneAnnotator.annotate` to allow for custom text for the in and out tags.
 
 ### 0.6.0 <small>April 19, 2023</small>
 
-- Added [#71](https://github.com/roboflow/supervision/pull/71): initial `Dataset` support and ability to save `Detections` in Pascal VOC XML format. 
+- Added [#71](https://github.com/roboflow/supervision/pull/71): initial `Dataset` support and ability to save `Detections` in Pascal VOC XML format.
 - Added [#71](https://github.com/roboflow/supervision/pull/71): new `mask_to_polygons`, `filter_polygons_by_area`, `polygon_to_xyxy` and `approximate_polygon` utilities.
 - Added [#72](https://github.com/roboflow/supervision/pull/72): ability to load Pascal VOC XML **object detections** dataset as `Dataset`.
 - Changed [#70](https://github.com/roboflow/supervision/pull/70): order of `Detections` attributes to make it consistent with order of objects in `__iter__` tuple.
@@ -256,7 +291,7 @@ array([
 - Added [#58](https://github.com/roboflow/supervision/pull/58): `Detections.from_sam` to enable native Segment Anything Model (SAM) support.
 - Changed [#58](https://github.com/roboflow/supervision/pull/58): `Detections.area` behaviour to work not only with boxes but also with masks.
 
-### 0.4.0 <small>April 5, 2023</small> 
+### 0.4.0 <small>April 5, 2023</small>
 
 - Added [#46](https://github.com/roboflow/supervision/discussions/48): `Detections.empty` to allow easy creation of empty `Detections` objects.
 - Added [#56](https://github.com/roboflow/supervision/pull/56): `Detections.from_roboflow` to allow easy creation of `Detections` objects from Roboflow API inference results.
@@ -264,28 +299,28 @@ array([
 - Added [#56](https://github.com/roboflow/supervision/pull/56): initial support for Pascal VOC XML format with `detections_to_voc_xml` method.
 - Changed [#56](https://github.com/roboflow/supervision/pull/56): `show_frame_in_notebook` refactored and renamed to `plot_image`.
 
-### 0.3.2 <small>March 23, 2023</small> 
+### 0.3.2 <small>March 23, 2023</small>
 
-- Changed [#50](https://github.com/roboflow/supervision/issues/50): Allow `Detections.class_id` to be `None`. 
+- Changed [#50](https://github.com/roboflow/supervision/issues/50): Allow `Detections.class_id` to be `None`.
 
-### 0.3.1 <small>March 6, 2023</small> 
+### 0.3.1 <small>March 6, 2023</small>
 
 - Fixed [#41](https://github.com/roboflow/supervision/issues/41): `PolygonZone` throws an exception when the object touches the bottom edge of the image.
 - Fixed [#42](https://github.com/roboflow/supervision/issues/42): `Detections.wth_nms` method throws an exception when `Detections` is empty.
 - Changed [#36](https://github.com/roboflow/supervision/pull/36): `Detections.wth_nms` support class agnostic and non-class agnostic case.
 
-### 0.3.0 <small>March 6, 2023</small> 
+### 0.3.0 <small>March 6, 2023</small>
 
 - Changed: Allow `Detections.confidence` to be `None`.
-- Added: `Detections.from_transformers` and `Detections.from_detectron2` to enable seamless integration with Transformers and Detectron2 models. 
+- Added: `Detections.from_transformers` and `Detections.from_detectron2` to enable seamless integration with Transformers and Detectron2 models.
 - Added: `Detections.area` to dynamically calculate bounding box area.
-- Added: `Detections.wth_nms` to filter out double detections with NMS. Initial - only class agnostic - implementation. 
+- Added: `Detections.wth_nms` to filter out double detections with NMS. Initial - only class agnostic - implementation.
 
-### 0.2.0 <small>February 2, 2023</small> 
+### 0.2.0 <small>February 2, 2023</small>
 
 - Added: Advanced `Detections` filtering with pandas-like API.
 - Added: `Detections.from_yolov5` and `Detections.from_yolov8` to enable seamless integration with YOLOv5 and YOLOv8 models.
 
-### 0.1.0 <small>January 19, 2023</small> 
+### 0.1.0 <small>January 19, 2023</small>
 
 Say hello to Supervision 👋

docs/dataset/core.md

@@ -1,6 +1,6 @@
 !!! warning
 
-    Dataset API is still fluid and may change. If you use Dataset API in your project until further notice, freeze the 
+    Dataset API is still fluid and may change. If you use Dataset API in your project until further notice, freeze the
     `supervision` version in your `requirements.txt` or `setup.py`.
 
 ## DetectionDataset
@@ -9,4 +9,4 @@
 
 ## ClassificationDataset
 
-:::supervision.dataset.core.ClassificationDataset
+:::supervision.dataset.core.ClassificationDataset

docs/detection/annotate.md

@@ -4,4 +4,4 @@
 
 ## MaskAnnotator
 
-:::supervision.detection.annotate.MaskAnnotator
+:::supervision.detection.annotate.MaskAnnotator

docs/detection/tools/inference_slicer.md

@@ -0,0 +1,3 @@
+## InferenceSlicer
+
+:::supervision.detection.tools.inference_slicer.InferenceSlicer

docs/detection/tools/polygon_zone.md

@@ -4,4 +4,4 @@
 
 ## PolygonZoneAnnotator
 
-:::supervision.detection.tools.polygon_zone.PolygonZoneAnnotator
+:::supervision.detection.tools.polygon_zone.PolygonZoneAnnotator

docs/detection/utils.md

@@ -24,4 +24,4 @@
 
 ## filter_polygons_by_area
 
-:::supervision.detection.utils.filter_polygons_by_area
+:::supervision.detection.utils.filter_polygons_by_area

docs/draw/utils.md

@@ -16,4 +16,4 @@
 
 ## draw_text
 
-:::supervision.draw.utils.draw_text
+:::supervision.draw.utils.draw_text

docs/index.md

@@ -11,22 +11,22 @@
 
 ## 👋 Hello
 
-We write your reusable computer vision tools. Whether you need to load your dataset from your hard drive, draw detections on an image or video, or count how many detections are in a zone. You can count on us! 
+We write your reusable computer vision tools. Whether you need to load your dataset from your hard drive, draw detections on an image or video, or count how many detections are in a zone. You can count on us!
 
 ## 💻 Install
 
-You can install `supervision` with pip in a 
+You can install `supervision` with pip in a
 [**3.11>=Python>=3.8**](https://www.python.org/) environment.
 
 !!! example "pip install (recommended)"
 
     === "headless"
-        The headless installation of `supervision` is designed for environments where graphical user interfaces (GUI) are not needed, making it more lightweight and suitable for server-side applications. 
+        The headless installation of `supervision` is designed for environments where graphical user interfaces (GUI) are not needed, making it more lightweight and suitable for server-side applications.
 
         ```bash
         pip install supervision
         ```
-    
+
     === "desktop"
         If you require the full version of `supervision` with GUI support you can install the desktop version. This version includes the GUI components of OpenCV, allowing you to display images and videos on the screen.
 
@@ -42,32 +42,32 @@ You can install `supervision` with pip in a
         # clone repository and navigate to root directory
         git clone https://github.com/roboflow/supervision.git
         cd supervision
-        
+
         # setup python environment and activate it
         python3 -m venv venv
         source venv/bin/activate
-        
+
         # headless install
         pip install -e "."
-        
+
         # desktop install
         pip install -e ".[desktop]"
         ```
-    
+
     === "poetry"
 
         ```bash
         # clone repository and navigate to root directory
         git clone https://github.com/roboflow/supervision.git
         cd supervision
- 
+
         # setup python environment and activate it
         poetry env use python 3.10
         poetry shell
 
         # headless install
         poetry install
-        
+
         # desktop install
         poetry install --extras "desktop"
-        ```
+        ```

docs/metrics/detection.md

@@ -1,6 +1,6 @@
 !!! warning
 
-    Evaluation API is still fluid and may change. If you use Evaluation API in your project until further notice, freeze the 
+    Evaluation API is still fluid and may change. If you use Evaluation API in your project until further notice, freeze the
     `supervision` version in your `requirements.txt` or `setup.py`.
 
 ## ConfusionMatrix

docs/quickstart/detections.md

@@ -1,10 +1,10 @@
 ## advanced filtering
 
 
-The advanced filtering capabilities of the `Detections` class offer users a versatile and efficient way to narrow down 
-and refine object detections. This section outlines various filtering methods, including filtering by specific class 
-or a set of classes, confidence, object area, bounding box area, relative area, box dimensions, and designated zones. 
-Each method is demonstrated with concise code examples to provide users with a clear understanding of how to implement 
+The advanced filtering capabilities of the `Detections` class offer users a versatile and efficient way to narrow down
+and refine object detections. This section outlines various filtering methods, including filtering by specific class
+or a set of classes, confidence, object area, bounding box area, relative area, box dimensions, and designated zones.
+Each method is demonstrated with concise code examples to provide users with a clear understanding of how to implement
 the filters in their applications.
 
 ### by specific class
@@ -44,14 +44,14 @@ Allows you to select detections that belong only to one selected class.
 
 ### by set of classes
 
-Allows you to select detections that belong only to selected set of classes. 
+Allows you to select detections that belong only to selected set of classes.
 
 === "After"
 
     ```python
     import numpy as np
     import supervision as sv
-    
+
     selected_classes = [0, 2, 3]
     detections = sv.Detections(...)
     detections = detections[np.isin(detections.class_id, selected_classes)]
@@ -68,7 +68,7 @@ Allows you to select detections that belong only to selected set of classes.
     ```python
     import numpy as np
     import supervision as sv
-    
+
     class_id = [0, 2, 3]
     detections = sv.Detections(...)
     detections = detections[np.isin(detections.class_id, class_id)]
@@ -116,8 +116,8 @@ Allows you to select detections with specific confidence value, for example high
 
 ### by area
 
-Allows you to select detections based on their size. We define the area as the number of pixels occupied by the 
-detection in the image. In the example below, we have sifted out the detections that are too small. 
+Allows you to select detections based on their size. We define the area as the number of pixels occupied by the
+detection in the image. In the example below, we have sifted out the detections that are too small.
 
 === "After"
 
@@ -151,9 +151,9 @@ detection in the image. In the example below, we have sifted out the detections
 
 ### by relative area
 
-Allows you to select detections based on their size in relation to the size of whole image. Sometimes the concept of 
-detection size changes depending on the image. Detection occupying 10000 square px can be large on a 1280x720 image 
-but small on a 3840x2160 image. In such cases, we can filter out detections based on the percentage of the image area 
+Allows you to select detections based on their size in relation to the size of whole image. Sometimes the concept of
+detection size changes depending on the image. Detection occupying 10000 square px can be large on a 1280x720 image
+but small on a 3840x2160 image. In such cases, we can filter out detections based on the percentage of the image area
 occupied by them. In the example below, we remove too large detections.
 
 === "After"
@@ -164,7 +164,7 @@ occupied by them. In the example below, we remove too large detections.
     image = ...
     height, width, channels = image.shape
     image_area = height * width
-    
+
     detections = sv.Detections(...)
     detections = detections[(detections.area / image_area) < 0.8]
     ```
@@ -183,7 +183,7 @@ occupied by them. In the example below, we remove too large detections.
     image = ...
     height, width, channels = image.shape
     image_area = height * width
-    
+
     detections = sv.Detections(...)
     detections = detections[(detections.area / image_area) < 0.8]
     ```
@@ -196,8 +196,8 @@ occupied by them. In the example below, we remove too large detections.
 
 ### by box dimensions
 
-Allows you to select detections based on their dimensions. The size of the bounding box, as well as its coordinates, 
-can be criteria for rejecting detection. Implementing such filtering requires a bit of custom code but is relatively 
+Allows you to select detections based on their dimensions. The size of the bounding box, as well as its coordinates,
+can be criteria for rejecting detection. Implementing such filtering requires a bit of custom code but is relatively
 simple and fast.
 
 === "After"
@@ -236,7 +236,7 @@ simple and fast.
 
 ### by `PolygonZone`
 
-Allows you to use `Detections` in combination with `PolygonZone` to weed out bounding boxes that are in and out of the 
+Allows you to use `Detections` in combination with `PolygonZone` to weed out bounding boxes that are in and out of the
 zone. In the example below you can see how to filter out all detections located in the lower part of the image.
 
 === "After"
@@ -309,4 +309,4 @@ zone. In the example below you can see how to filter out all detections located
 
     ![original](https://media.roboflow.com/open-source/supervision/supervision-detection-original.png){ align=center width="800" }
 
-    </div>
+    </div>

docs/stylesheets/extra.css

@@ -1,4 +1,4 @@
 :root {
   --md-primary-fg-color:        #8315F9;
   --md-accent-fg-color:         #00FFCE;
-}
+}

docs/tracker/core.md

@@ -1,4 +1,3 @@
 ## ByteTrack
 
 :::supervision.tracker.byte_tracker.core.ByteTrack
-

docs/utils/image.md

@@ -4,4 +4,4 @@
 
 ## crop
 
-:::supervision.utils.image.crop
+:::supervision.utils.image.crop_image

docs/utils/notebook.md

@@ -4,4 +4,4 @@
 
 ## plot_images_grid
 
-:::supervision.utils.notebook.plot_images_grid
+:::supervision.utils.notebook.plot_images_grid

docs/utils/video.md

@@ -12,4 +12,4 @@
 
 ## process_video
 
-:::supervision.utils.video.process_video
+:::supervision.utils.video.process_video

examples/tracking/README.md

@@ -0,0 +1,20 @@
+## 👋 hello
+
+This script provides functionality for processing videos using YOLOv8 for object
+detection and Supervision for tracking and annotation.
+
+## 💻 install
+
+```bash
+pip install -r requirements.txt
+```
+
+## ⚙️ parameters
+
+| parameter                | required | description                                                                       |
+|:-------------------------|:--------:|:----------------------------------------------------------------------------------|
+| `--source_weights_path`  |    ✓     | Path to the source weights file for YOLOv8.                                       |
+| `--source_video_path`    |    ✓     | Path to the source video file to be processed.                                    |
+| `--target_video_path`    |    ✓     | Path to the target video file (output).                                           |
+| `--confidence_threshold` |    ✗     | Confidence threshold for YOLO model detection. Default is 0.3.                    |
+| `--iou_threshold`        |    ✗     | IOU (Intersection over Union) threshold for YOLO model detection. Default is 0.7. |

examples/tracking/requirements.txt

@@ -0,0 +1,3 @@
+supervision
+tqdm
+ultralytics

examples/tracking/script.py

@@ -0,0 +1,83 @@
+import argparse
+
+from tqdm import tqdm
+from ultralytics import YOLO
+
+import supervision as sv
+
+
+def process_video(
+    source_weights_path: str,
+    source_video_path: str,
+    target_video_path: str,
+    confidence_threshold: float = 0.3,
+    iou_threshold: float = 0.7,
+) -> None:
+    model = YOLO(source_weights_path)
+
+    tracker = sv.ByteTrack()
+    box_annotator = sv.BoxAnnotator()
+    frame_generator = sv.get_video_frames_generator(source_path=source_video_path)
+    video_info = sv.VideoInfo.from_video_path(video_path=source_video_path)
+
+    with sv.VideoSink(target_path=target_video_path, video_info=video_info) as sink:
+        for frame in tqdm(frame_generator, total=video_info.total_frames):
+            results = model(
+                frame, verbose=False, conf=confidence_threshold, iou=iou_threshold
+            )[0]
+            detections = sv.Detections.from_ultralytics(results)
+            detections = tracker.update_with_detections(detections)
+
+            labels = [
+                f"#{tracker_id} {model.model.names[class_id]}"
+                for _, _, _, class_id, tracker_id in detections
+            ]
+
+            annotated_frame = box_annotator.annotate(
+                scene=frame.copy(), detections=detections, labels=labels
+            )
+
+            sink.write_frame(frame=annotated_frame)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="Video Processing with YOLO and ByteTrack"
+    )
+    parser.add_argument(
+        "--source_weights_path",
+        required=True,
+        help="Path to the source weights file",
+        type=str,
+    )
+    parser.add_argument(
+        "--source_video_path",
+        required=True,
+        help="Path to the source video file",
+        type=str,
+    )
+    parser.add_argument(
+        "--target_video_path",
+        required=True,
+        help="Path to the target video file (output)",
+        type=str,
+    )
+    parser.add_argument(
+        "--confidence_threshold",
+        default=0.3,
+        help="Confidence threshold for the model",
+        type=float,
+    )
+    parser.add_argument(
+        "--iou_threshold", default=0.7, help="IOU threshold for the model", type=float
+    )
+
+    args = parser.parse_args()
+
+    process_video(
+        source_weights_path=args.source_weights_path,
+        source_video_path=args.source_video_path,
+        target_video_path=args.target_video_path,
+        confidence_threshold=args.confidence_threshold,
+        iou_threshold=args.iou_threshold,
+    )

mkdocs.yml

@@ -37,6 +37,7 @@ nav:
         - Utils: detection/utils.md
         - Tools:
             - Polygon Zone: detection/tools/polygon_zone.md
+            - Inference Slicer: detection/tools/inference_slicer.md
     - Trackers:
         - Core: tracker/core.md
     - Dataset:
@@ -87,4 +88,4 @@ markdown_extensions:
   - pymdownx.tabbed:
       alternate_style: true
   - toc:
-      permalink: true
+      permalink: true

poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.5.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.6.1 and should not be changed by hand.
 
 [[package]]
 name = "anyio"
@@ -255,13 +255,13 @@ virtualenv = ["virtualenv (>=20.0.35)"]
 
 [[package]]
 name = "certifi"
-version = "2023.5.7"
+version = "2023.7.22"
 description = "Python package for providing Mozilla's CA Bundle."
 optional = false
 python-versions = ">=3.6"
 files = [
-    {file = "certifi-2023.5.7-py3-none-any.whl", hash = "sha256:c6c2e98f5c7869efca1f8916fed228dd91539f9f1b444c314c06eef02980c716"},
-    {file = "certifi-2023.5.7.tar.gz", hash = "sha256:0f0d56dc5a6ad56fd4ba36484d6cc34451e1c6548c61daad8c320169f91eddc7"},
+    {file = "certifi-2023.7.22-py3-none-any.whl", hash = "sha256:92d6037539857d8206b8f6ae472e8b77db8058fec5937a1ef3f54304089edbb9"},
+    {file = "certifi-2023.7.22.tar.gz", hash = "sha256:539cc1d13202e33ca466e88b2807e29f4c13049d6d87031a3c110744495cb082"},
 ]
 
 [[package]]
@@ -1218,13 +1218,13 @@ test = ["click", "coverage", "pre-commit", "pytest (>=7.0)", "pytest-asyncio (>=
 
 [[package]]
 name = "jupyter-server"
-version = "2.7.0"
+version = "2.7.2"
 description = "The backend—i.e. core services, APIs, and REST endpoints—to Jupyter web applications."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "jupyter_server-2.7.0-py3-none-any.whl", hash = "sha256:6a77912aff643e53fa14bdb2634884b52b784a4be77ce8e93f7283faed0f0849"},
-    {file = "jupyter_server-2.7.0.tar.gz", hash = "sha256:36da0a266d31a41ac335a366c88933c17dfa5bb817a48f5c02c16d303bc9477f"},
+    {file = "jupyter_server-2.7.2-py3-none-any.whl", hash = "sha256:98a375347b580e837e7016007c24680a4261ed8ad7cd35196ac087d229f48e5a"},
+    {file = "jupyter_server-2.7.2.tar.gz", hash = "sha256:d64fb4e593907290e5df916e3c9399c15ab2cd7bdb71cbcd1d36452dbfb30523"},
 ]
 
 [package.dependencies]
@@ -1242,7 +1242,7 @@ packaging = "*"
 prometheus-client = "*"
 pywinpty = {version = "*", markers = "os_name == \"nt\""}
 pyzmq = ">=24"
-send2trash = "*"
+send2trash = ">=1.8.2"
 terminado = ">=0.8.3"
 tornado = ">=6.2.0"
 traitlets = ">=5.6.0"
@@ -2034,13 +2034,12 @@ files = [
 
 [package.dependencies]
 numpy = [
-    {version = ">=1.21.0", markers = "python_version <= \"3.9\" and platform_system == \"Darwin\" and platform_machine == \"arm64\""},
-    {version = ">=1.19.3", markers = "python_version >= \"3.6\" and platform_system == \"Linux\" and platform_machine == \"aarch64\" or python_version >= \"3.9\""},
-    {version = ">=1.17.0", markers = "python_version >= \"3.7\""},
-    {version = ">=1.17.3", markers = "python_version >= \"3.8\""},
-    {version = ">=1.21.2", markers = "python_version >= \"3.10\""},
-    {version = ">=1.21.4", markers = "python_version >= \"3.10\" and platform_system == \"Darwin\""},
+    {version = ">=1.21.0", markers = "python_version <= \"3.9\" and platform_system == \"Darwin\" and platform_machine == \"arm64\" and python_version >= \"3.8\""},
     {version = ">=1.23.5", markers = "python_version >= \"3.11\""},
+    {version = ">=1.21.4", markers = "python_version >= \"3.10\" and platform_system == \"Darwin\" and python_version < \"3.11\""},
+    {version = ">=1.21.2", markers = "platform_system != \"Darwin\" and python_version >= \"3.10\" and python_version < \"3.11\""},
+    {version = ">=1.19.3", markers = "platform_system == \"Linux\" and platform_machine == \"aarch64\" and python_version >= \"3.8\" and python_version < \"3.10\" or python_version > \"3.9\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_system != \"Darwin\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_machine != \"arm64\" and python_version < \"3.10\""},
+    {version = ">=1.17.3", markers = "(platform_system != \"Darwin\" and platform_system != \"Linux\") and python_version >= \"3.8\" and python_version < \"3.9\" or platform_system != \"Darwin\" and python_version >= \"3.8\" and python_version < \"3.9\" and platform_machine != \"aarch64\" or platform_machine != \"arm64\" and python_version >= \"3.8\" and python_version < \"3.9\" and platform_system != \"Linux\" or (platform_machine != \"arm64\" and platform_machine != \"aarch64\") and python_version >= \"3.8\" and python_version < \"3.9\""},
 ]
 
 [[package]]
@@ -2061,13 +2060,12 @@ files = [
 
 [package.dependencies]
 numpy = [
-    {version = ">=1.21.0", markers = "python_version <= \"3.9\" and platform_system == \"Darwin\" and platform_machine == \"arm64\""},
-    {version = ">=1.21.2", markers = "python_version >= \"3.10\""},
-    {version = ">=1.21.4", markers = "python_version >= \"3.10\" and platform_system == \"Darwin\""},
+    {version = ">=1.21.0", markers = "python_version <= \"3.9\" and platform_system == \"Darwin\" and platform_machine == \"arm64\" and python_version >= \"3.8\""},
     {version = ">=1.23.5", markers = "python_version >= \"3.11\""},
-    {version = ">=1.19.3", markers = "python_version >= \"3.6\" and platform_system == \"Linux\" and platform_machine == \"aarch64\" or python_version >= \"3.9\""},
-    {version = ">=1.17.0", markers = "python_version >= \"3.7\""},
-    {version = ">=1.17.3", markers = "python_version >= \"3.8\""},
+    {version = ">=1.21.4", markers = "python_version >= \"3.10\" and platform_system == \"Darwin\" and python_version < \"3.11\""},
+    {version = ">=1.21.2", markers = "platform_system != \"Darwin\" and python_version >= \"3.10\" and python_version < \"3.11\""},
+    {version = ">=1.19.3", markers = "platform_system == \"Linux\" and platform_machine == \"aarch64\" and python_version >= \"3.8\" and python_version < \"3.10\" or python_version > \"3.9\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_system != \"Darwin\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_machine != \"arm64\" and python_version < \"3.10\""},
+    {version = ">=1.17.3", markers = "(platform_system != \"Darwin\" and platform_system != \"Linux\") and python_version >= \"3.8\" and python_version < \"3.9\" or platform_system != \"Darwin\" and python_version >= \"3.8\" and python_version < \"3.9\" and platform_machine != \"aarch64\" or platform_machine != \"arm64\" and python_version >= \"3.8\" and python_version < \"3.9\" and platform_system != \"Linux\" or (platform_machine != \"arm64\" and platform_machine != \"aarch64\") and python_version >= \"3.8\" and python_version < \"3.9\""},
 ]
 
 [[package]]
@@ -2582,6 +2580,7 @@ files = [
     {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"},
     {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"},
     {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"},
+    {file = "PyYAML-6.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:326c013efe8048858a6d312ddd31d56e468118ad4cdeda36c719bf5bb6192290"},
     {file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"},
     {file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"},
     {file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"},
@@ -2589,8 +2588,15 @@ files = [
     {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"},
     {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"},
     {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"},
+    {file = "PyYAML-6.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7d73685e87afe9f3b36c799222440d6cf362062f78be1013661b00c5c6f678b"},
     {file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"},
     {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
+    {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
+    {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
+    {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
+    {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
+    {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
+    {file = "PyYAML-6.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:0d3304d8c0adc42be59c5f8a4d9e3d7379e6955ad754aa9d6ab7a398b59dd1df"},
     {file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"},
     {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"},
     {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"},
@@ -2607,6 +2613,7 @@ files = [
     {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"},
     {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"},
     {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"},
+    {file = "PyYAML-6.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:49a183be227561de579b4a36efbb21b3eab9651dd81b1858589f796549873dd6"},
     {file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"},
     {file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"},
     {file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"},
@@ -2614,6 +2621,7 @@ files = [
     {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"},
     {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"},
     {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"},
+    {file = "PyYAML-6.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:04ac92ad1925b2cff1db0cfebffb6ffc43457495c9b3c39d3fcae417d7125dc5"},
     {file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"},
     {file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"},
     {file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"},
@@ -3266,22 +3274,22 @@ files = [
 
 [[package]]
 name = "tornado"
-version = "6.3.2"
+version = "6.3.3"
 description = "Tornado is a Python web framework and asynchronous networking library, originally developed at FriendFeed."
 optional = false
 python-versions = ">= 3.8"
 files = [
-    {file = "tornado-6.3.2-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:c367ab6c0393d71171123ca5515c61ff62fe09024fa6bf299cd1339dc9456829"},
-    {file = "tornado-6.3.2-cp38-abi3-macosx_10_9_x86_64.whl", hash = "sha256:b46a6ab20f5c7c1cb949c72c1994a4585d2eaa0be4853f50a03b5031e964fc7c"},
-    {file = "tornado-6.3.2-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c2de14066c4a38b4ecbbcd55c5cc4b5340eb04f1c5e81da7451ef555859c833f"},
-    {file = "tornado-6.3.2-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:05615096845cf50a895026f749195bf0b10b8909f9be672f50b0fe69cba368e4"},
-    {file = "tornado-6.3.2-cp38-abi3-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5b17b1cf5f8354efa3d37c6e28fdfd9c1c1e5122f2cb56dac121ac61baa47cbe"},
-    {file = "tornado-6.3.2-cp38-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:29e71c847a35f6e10ca3b5c2990a52ce38b233019d8e858b755ea6ce4dcdd19d"},
-    {file = "tornado-6.3.2-cp38-abi3-musllinux_1_1_i686.whl", hash = "sha256:834ae7540ad3a83199a8da8f9f2d383e3c3d5130a328889e4cc991acc81e87a0"},
-    {file = "tornado-6.3.2-cp38-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:6a0848f1aea0d196a7c4f6772197cbe2abc4266f836b0aac76947872cd29b411"},
-    {file = "tornado-6.3.2-cp38-abi3-win32.whl", hash = "sha256:7efcbcc30b7c654eb6a8c9c9da787a851c18f8ccd4a5a3a95b05c7accfa068d2"},
-    {file = "tornado-6.3.2-cp38-abi3-win_amd64.whl", hash = "sha256:0c325e66c8123c606eea33084976c832aa4e766b7dff8aedd7587ea44a604cdf"},
-    {file = "tornado-6.3.2.tar.gz", hash = "sha256:4b927c4f19b71e627b13f3db2324e4ae660527143f9e1f2e2fb404f3a187e2ba"},
+    {file = "tornado-6.3.3-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:502fba735c84450974fec147340016ad928d29f1e91f49be168c0a4c18181e1d"},
+    {file = "tornado-6.3.3-cp38-abi3-macosx_10_9_x86_64.whl", hash = "sha256:805d507b1f588320c26f7f097108eb4023bbaa984d63176d1652e184ba24270a"},
+    {file = "tornado-6.3.3-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1bd19ca6c16882e4d37368e0152f99c099bad93e0950ce55e71daed74045908f"},
+    {file = "tornado-6.3.3-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7ac51f42808cca9b3613f51ffe2a965c8525cb1b00b7b2d56828b8045354f76a"},
+    {file = "tornado-6.3.3-cp38-abi3-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:71a8db65160a3c55d61839b7302a9a400074c9c753040455494e2af74e2501f2"},
+    {file = "tornado-6.3.3-cp38-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:ceb917a50cd35882b57600709dd5421a418c29ddc852da8bcdab1f0db33406b0"},
+    {file = "tornado-6.3.3-cp38-abi3-musllinux_1_1_i686.whl", hash = "sha256:7d01abc57ea0dbb51ddfed477dfe22719d376119844e33c661d873bf9c0e4a16"},
+    {file = "tornado-6.3.3-cp38-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:9dc4444c0defcd3929d5c1eb5706cbe1b116e762ff3e0deca8b715d14bf6ec17"},
+    {file = "tornado-6.3.3-cp38-abi3-win32.whl", hash = "sha256:65ceca9500383fbdf33a98c0087cb975b2ef3bfb874cb35b8de8740cf7f41bd3"},
+    {file = "tornado-6.3.3-cp38-abi3-win_amd64.whl", hash = "sha256:22d3c2fa10b5793da13c807e6fc38ff49a4f6e1e3868b0a6f4164768bb8e20f5"},
+    {file = "tornado-6.3.3.tar.gz", hash = "sha256:e7d8db41c0181c80d76c982aacc442c0783a2c54d6400fe028954201a2e032fe"},
 ]
 
 [[package]]

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "supervision"
-version = "0.13.0"
+version = "0.14.0"
 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>"]
@@ -66,6 +66,111 @@ flake8 = { version = "*", python = ">=3.8.1,<3.12.0" }
 mkdocs-material = "^9.1.4"
 mkdocstrings = {extras = ["python"], version = "^0.20.0"}
 
+[tool.flake8]
+exclude = ".venv"
+max-complexity = 10
+max-line-length = 88
+extend-ignore = """
+    W503,
+    E203,
+    E701,
+    C901,
+"""
+per-file-ignores = """
+    __init__.py: F401
+"""
+
+[tool.isort]
+line_length = 88
+profile = "black"
+
+[tool.bandit]
+target = ["test", "supervision"]
+tests = ["B201", "B301"]
+
+[tool.autoflake]
+check = true
+imports = ["cv2", "supervision"]
+
+
+[tool.black]
+target-version = ["py38"]
+line-length = 88
+include = '\.pyi?$'
+exclude = '''
+/(
+    \.git
+  | \.hg
+  | \.mypy_cache
+  | \.tox
+  | \.venv
+  | _build
+  | buck-out
+  | build
+  | dist
+  | docs
+)/
+'''
+
+[tool.ruff]
+target-version = "py38"
+# Enable pycodestyle (`E`) and Pyflakes (`F`) codes by default.
+select = ["E", "F"]
+ignore = []
+
+# Allow autofix for all enabled rules (when `--fix`) is provided.
+fixable = ["A", "B", "C", "D", "E", "F", "G", "I", "N", "Q", "S", "T", "W", "ANN", "ARG", "BLE", "COM", "DJ", "DTZ", "EM", "ERA", "EXE", "FBT", "ICN", "INP", "ISC", "NPY", "PD", "PGH", "PIE", "PL", "PT", "PTH", "PYI", "RET", "RSE", "RUF", "SIM", "SLF", "TCH", "TID", "TRY", "UP", "YTT"]
+unfixable = []
+
+# Exclude a variety of commonly ignored directories.
+exclude = [
+    ".bzr",
+    ".direnv",
+    ".eggs",
+    ".git",
+    ".git-rewrite",
+    ".hg",
+    ".mypy_cache",
+    ".nox",
+    ".pants.d",
+    ".pytype",
+    ".ruff_cache",
+    ".svn",
+    ".tox",
+    ".venv",
+    "__pypackages__",
+    "_build",
+    "buck-out",
+    "build",
+    "dist",
+    "node_modules",
+    "venv",
+    "yarn-error.log",
+    "yarn.lock",
+    "docs",
+]
+
+# Same as Black.
+line-length = 88
+
+# Allow unused variables when underscore-prefixed.
+dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
+
+[tool.ruff.flake8-quotes]
+inline-quotes = "double"
+multiline-quotes = "double"
+docstring-quotes = "double"
+
+[tool.ruff.pydocstyle]
+convention = "google"
+
+[tool.ruff.per-file-ignores]
+"__init__.py" = ["E402","F401"]
+
+[tool.ruff.pylint]
+max-args = 20
+
+
 [tool.setuptools]
 include-package-data = false
 

supervision/__init__.py

@@ -16,6 +16,7 @@ from supervision.dataset.core import (
 from supervision.detection.annotate import BoxAnnotator, MaskAnnotator
 from supervision.detection.core import Detections
 from supervision.detection.line_counter import LineZone, LineZoneAnnotator
+from supervision.detection.tools.inference_slicer import InferenceSlicer
 from supervision.detection.tools.polygon_zone import PolygonZone, PolygonZoneAnnotator
 from supervision.detection.utils import (
     box_iou_batch,
@@ -33,7 +34,7 @@ from supervision.geometry.utils import get_polygon_center
 from supervision.metrics.detection import ConfusionMatrix, MeanAveragePrecision
 from supervision.tracker.byte_tracker.core import ByteTrack
 from supervision.utils.file import list_files_with_extensions
-from supervision.utils.image import ImageSink, crop
+from supervision.utils.image import ImageSink, crop_image
 from supervision.utils.notebook import plot_image, plot_images_grid
 from supervision.utils.video import (
     VideoInfo,

supervision/classification/core.py

@@ -5,6 +5,8 @@ from typing import Any, Optional, Tuple
 
 import numpy as np
 
+from supervision.utils.internal import deprecated
+
 
 def _validate_class_ids(class_id: Any, n: int) -> None:
     """
@@ -40,15 +42,24 @@ class Classifications:
         _validate_confidence(self.confidence, n)
 
     @classmethod
+    @deprecated(
+        """
+        This method is deprecated and removed in 0.16.0 release.
+        Use sv.Classifications.from_ultralytics() instead as it is more generic and
+        can be used for detections from any ultralytics.engine.results.Results Object
+        """
+    )
     def from_yolov8(cls, yolov8_results) -> Classifications:
         """
-        Creates a Classifications instance from a [YOLOv8](https://github.com/ultralytics/ultralytics) inference result.
+        Creates a Classifications instance from a
+        [YOLOv8](https://github.com/ultralytics/ultralytics) inference result.
 
         Args:
-            yolov8_results (ultralytics.yolo.engine.results.Results): The output Results instance from YOLOv8
+            yolov8_results (ultralytics.yolo.engine.results.Results):
+                The output Results instance from YOLOv8
 
         Returns:
-            Detections: A new Classifications object.
+            Classifications: A new Classifications object.
 
         Example:
             ```python
@@ -65,15 +76,47 @@ class Classifications:
         confidence = yolov8_results.probs.data.cpu().numpy()
         return cls(class_id=np.arange(confidence.shape[0]), confidence=confidence)
 
+    @classmethod
+    def from_ultralytics(cls, ultralytics_results) -> Classifications:
+        """
+        Creates a Classifications instance from a
+        (https://github.com/ultralytics/ultralytics) inference result.
+
+        Args:
+            ultralytics_results (ultralytics.engine.results.Results):
+            The output Results instance from ultralytics model
+
+        Returns:
+            Classifications: A new Classifications object.
+
+        Example:
+            ```python
+            >>> import cv2
+            >>> from ultralytics import YOLO
+            >>> import supervision as sv
+
+            >>> image = cv2.imread(SOURCE_IMAGE_PATH)
+            >>> model = YOLO('yolov8n-cls.pt')
+            >>> model = YOLO('yolov8s-cls.pt')
+
+            >>> result = model(image)[0]
+            >>> classifications = sv.Classifications.from_ultralytics(result)
+            ```
+        """
+        confidence = ultralytics_results.probs.data.cpu().numpy()
+        return cls(class_id=np.arange(confidence.shape[0]), confidence=confidence)
+
     def get_top_k(self, k: int) -> Tuple[np.ndarray, np.ndarray]:
         """
-        Retrieve the top k class IDs and confidences, ordered in descending order by confidence.
+        Retrieve the top k class IDs and confidences,
+            ordered in descending order by confidence.
 
         Args:
             k (int): The number of top class IDs and confidences to retrieve.
 
         Returns:
-            Tuple[np.ndarray, np.ndarray]: A tuple containing the top k class IDs and confidences.
+            Tuple[np.ndarray, np.ndarray]: A tuple containing
+                the top k class IDs and confidences.
 
         Example:
             ```python

supervision/dataset/core.py

@@ -54,7 +54,8 @@ class DetectionDataset(BaseDataset):
     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 image name to annotations.
+        annotations (Dict[str, Detections]): Dictionary mapping
+            image name to annotations.
     """
 
     classes: List[str]
@@ -75,8 +76,9 @@ class DetectionDataset(BaseDataset):
         Iterate over the images and annotations in the dataset.
 
         Yields:
-            Iterator[Tuple[str, np.ndarray, Detections]]: An iterator that yields tuples containing the image name,
-                                                          the image data, and its corresponding annotation.
+            Iterator[Tuple[str, np.ndarray, Detections]]:
+                An iterator that yields tuples containing the image name,
+                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)
@@ -100,22 +102,27 @@ class DetectionDataset(BaseDataset):
         self, split_ratio=0.8, random_state=None, shuffle: bool = True
     ) -> Tuple[DetectionDataset, DetectionDataset]:
         """
-        Splits the dataset into two parts (training and testing) using the provided split_ratio.
+        Splits the dataset into two parts (training and testing)
+            using the provided split_ratio.
 
         Args:
-            split_ratio (float, optional): The ratio of the training set to the entire dataset.
-            random_state (int, optional): The seed for the random number generator. This is used for reproducibility.
+            split_ratio (float, optional): The ratio of the training
+                set to the entire dataset.
+            random_state (int, optional): The seed for the random number generator.
+                This is used for reproducibility.
             shuffle (bool, optional): Whether to shuffle the data before splitting.
 
         Returns:
-            Tuple[DetectionDataset, DetectionDataset]: A tuple containing the training and testing datasets.
+            Tuple[DetectionDataset, DetectionDataset]: A tuple containing
+                the training and testing datasets.
 
         Example:
             ```python
             >>> import supervision as sv
 
             >>> ds = sv.DetectionDataset(...)
-            >>> train_ds, test_ds = ds.split(split_ratio=0.7, random_state=42, shuffle=True)
+            >>> train_ds, test_ds = ds.split(split_ratio=0.7,
+            ...                              random_state=42, shuffle=True)
             >>> len(train_ds), len(test_ds)
             (700, 300)
             ```
@@ -150,37 +157,45 @@ class DetectionDataset(BaseDataset):
         approximation_percentage: float = 0.0,
     ) -> None:
         """
-        Exports the dataset to PASCAL VOC format. This method saves the images and their corresponding annotations in
-        PASCAL VOC format.
+        Exports the dataset to PASCAL VOC format. This method saves the images
+        and their corresponding annotations in PASCAL VOC format.
 
         Args:
-            images_directory_path (Optional[str]): The path to the directory where the images should be saved.
+            images_directory_path (Optional[str]): The path to the directory
+                where the images should be saved.
                 If not provided, images will not be saved.
-            annotations_directory_path (Optional[str]): The path to the directory where the annotations in
-                PASCAL VOC format should be saved. If not provided, annotations will not be saved.
-            min_image_area_percentage (float): The minimum percentage of detection area relative to
-                the image area for a detection to be included. Argument is used only for segmentation datasets.
-            max_image_area_percentage (float): The maximum percentage of detection area relative to
-                the image area for a detection to be included. Argument is used only for segmentation datasets.
-            approximation_percentage (float): The percentage of polygon points to be removed from the input polygon,
+            annotations_directory_path (Optional[str]): The path to
+            the directory where the annotations in
+                PASCAL VOC format should be saved. If not provided,
+                annotations will not be saved.
+            min_image_area_percentage (float): The minimum percentage of
+                detection area relative to
+                the image area for a detection to be included.
+                Argument is used only for segmentation datasets.
+            max_image_area_percentage (float): The maximum percentage
+                of detection area relative to
+                the image area for a detection to be included.
+                Argument is used only for segmentation datasets.
+            approximation_percentage (float): The percentage of
+                polygon points to be removed from the input polygon,
             in the range [0, 1). Argument is used only for segmentation datasets.
         """
         if images_directory_path:
-            images_path = Path(images_directory_path)
-            images_path.mkdir(parents=True, exist_ok=True)
-
+            save_dataset_images(
+                images_directory_path=images_directory_path, images=self.images
+            )
         if annotations_directory_path:
-            annotations_path = Path(annotations_directory_path)
-            annotations_path.mkdir(parents=True, exist_ok=True)
+            Path(annotations_directory_path).mkdir(parents=True, exist_ok=True)
 
-        for image_name, image in self.images.items():
-            detections = self.annotations[image_name]
-
-            if images_directory_path:
-                cv2.imwrite(str(images_path / image_name), image)
+        for image_path, image in self.images.items():
+            detections = self.annotations[image_path]
 
             if annotations_directory_path:
-                annotation_name = Path(image_name).stem
+                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,
                     classes=self.classes,
@@ -191,7 +206,7 @@ class DetectionDataset(BaseDataset):
                     approximation_percentage=approximation_percentage,
                 )
 
-                with open(annotations_path / f"{annotation_name}.xml", "w") as f:
+                with open(annotations_path, "w") as f:
                     f.write(pascal_voc_xml)
 
     @classmethod
@@ -205,12 +220,15 @@ class DetectionDataset(BaseDataset):
         Creates a Dataset instance from PASCAL VOC formatted data.
 
         Args:
-            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 XML annotations.
-            force_masks (bool, optional): If True, forces masks to be loaded for all annotations, regardless of whether they are present.
+            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
+                be loaded for all annotations, regardless of whether they are present.
 
         Returns:
-            DetectionDataset: A DetectionDataset instance containing the loaded images and annotations.
+            DetectionDataset: A DetectionDataset instance containing
+                the loaded images and annotations.
 
         Example:
             ```python
@@ -255,13 +273,19 @@ class DetectionDataset(BaseDataset):
         Creates a Dataset instance from YOLO formatted data.
 
         Args:
-            images_directory_path (str): The path to the directory containing the images.
-            annotations_directory_path (str): The path to the directory 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 for all annotations, regardless of whether they are present.
+            images_directory_path (str): The path to the
+                directory containing the images.
+            annotations_directory_path (str): The path to the directory
+                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 for all annotations,
+                regardless of whether they are present.
 
         Returns:
-            DetectionDataset: A DetectionDataset instance containing the loaded images and annotations.
+            DetectionDataset: A DetectionDataset instance
+                containing the loaded images and annotations.
 
         Example:
             ```python
@@ -304,23 +328,32 @@ class DetectionDataset(BaseDataset):
         approximation_percentage: float = 0.0,
     ) -> None:
         """
-        Exports the dataset to YOLO format. This method saves the images and their corresponding
-        annotations in YOLO format.
+        Exports the dataset to YOLO format. This method saves the
+        images and their corresponding annotations in YOLO format.
 
         Args:
-            images_directory_path (Optional[str]): The path to the directory where the images should be saved.
+            images_directory_path (Optional[str]): The path to the
+                directory where the images should be saved.
                 If not provided, images will not be saved.
-            annotations_directory_path (Optional[str]): The path to the directory where the annotations in
-                YOLO format should be saved. If not provided, annotations will not be saved.
-            data_yaml_path (Optional[str]): The path where the data.yaml file should be saved.
+            annotations_directory_path (Optional[str]): The path to the
+                directory where the annotations in
+                YOLO format should be saved. If not provided,
+                annotations will not be saved.
+            data_yaml_path (Optional[str]): The path where the data.yaml
+                file should be saved.
                 If not provided, the file will not be saved.
-            min_image_area_percentage (float): The minimum percentage of detection area relative to
-                the image area for a detection to be included. Argument is used only for segmentation datasets.
-            max_image_area_percentage (float): The maximum percentage of detection area relative to
-                the image area for a detection to be included. Argument is used only for segmentation datasets.
-            approximation_percentage (float): The percentage of polygon points to be removed from the input polygon,
-                in the range [0, 1). This is useful for simplifying the annotations. Argument is used only for
-                segmentation datasets.
+            min_image_area_percentage (float): The minimum percentage of
+                detection area relative to
+                the image area for a detection to be included.
+                Argument is used only for segmentation datasets.
+            max_image_area_percentage (float): The maximum percentage
+                of detection area relative to
+                the image area for a detection to be included.
+                Argument is used only for segmentation datasets.
+            approximation_percentage (float): The percentage of polygon points to
+                be removed from the input polygon, in the range [0, 1).
+                This is useful for simplifying the annotations.
+                Argument is used only for segmentation datasets.
         """
         if images_directory_path is not None:
             save_dataset_images(
@@ -349,12 +382,16 @@ class DetectionDataset(BaseDataset):
         Creates a Dataset instance from COCO formatted data.
 
         Args:
-            images_directory_path (str): The path to the directory containing the images.
+            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, forces masks to be loaded for all annotations, regardless of whether they are present.
+            force_masks (bool, optional): If True,
+                forces masks to be loaded for all annotations,
+                regardless of whether they are present.
 
         Returns:
-            DetectionDataset: A DetectionDataset instance containing the loaded images and annotations.
+            DetectionDataset: A DetectionDataset instance containing
+                the loaded images and annotations.
 
         Example:
             ```python
@@ -394,20 +431,26 @@ class DetectionDataset(BaseDataset):
         approximation_percentage: float = 0.0,
     ) -> None:
         """
-        Exports the dataset to COCO format. This method saves the images and their corresponding
-        annotations in COCO format.
+        Exports the dataset to COCO format. This method saves the
+        images and their corresponding annotations in COCO format.
 
         Args:
-            images_directory_path (Optional[str]): The path to the directory where the images should be saved.
+            images_directory_path (Optional[str]): The path to the directory
+                where the images should be saved.
                 If not provided, images will not be saved.
             annotations_path (Optional[str]): The path to COCO annotation file.
-            min_image_area_percentage (float): The minimum percentage of detection area relative to
-                the image area for a detection to be included. Argument is used only for segmentation datasets.
-            max_image_area_percentage (float): The maximum percentage of detection area relative to
-                the image area for a detection to be included. Argument is used only for segmentation datasets.
-            approximation_percentage (float): The percentage of polygon points to be removed from the input polygon,
-                in the range [0, 1). This is useful for simplifying the annotations. Argument is used only for
-                segmentation datasets.
+            min_image_area_percentage (float): The minimum percentage of
+                detection area relative to
+                the image area for a detection to be included.
+                Argument is used only for segmentation datasets.
+            max_image_area_percentage (float): The maximum percentage of
+                detection area relative to
+                the image area for a detection to be included.
+                Argument is used only for segmentation datasets.
+            approximation_percentage (float): The percentage of polygon points
+                to be removed from the input polygon,
+                in the range [0, 1). This is useful for simplifying the annotations.
+                Argument is used only for segmentation datasets.
         """
         if images_directory_path is not None:
             save_dataset_images(
@@ -427,16 +470,20 @@ class DetectionDataset(BaseDataset):
     @classmethod
     def merge(cls, dataset_list: List[DetectionDataset]) -> DetectionDataset:
         """
-        Merge a list of `DetectionDataset` objects into a single `DetectionDataset` object.
+        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`,
+        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.
+            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.
+            (DetectionDataset): A single `DetectionDataset` object containing
+            the merged data from the input list.
 
         Example:
             ```python
@@ -494,7 +541,8 @@ class ClassificationDataset(BaseDataset):
     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 image name to annotations.
+        annotations (Dict[str, Detections]): Dictionary mapping
+            image name to annotations.
     """
 
     classes: List[str]
@@ -508,22 +556,28 @@ class ClassificationDataset(BaseDataset):
         self, split_ratio=0.8, random_state=None, shuffle: bool = True
     ) -> Tuple[ClassificationDataset, ClassificationDataset]:
         """
-        Splits the dataset into two parts (training and testing) using the provided split_ratio.
+        Splits the dataset into two parts (training and testing)
+            using the provided split_ratio.
 
         Args:
-            split_ratio (float, optional): The ratio of the training set to the entire dataset.
-            random_state (int, optional): The seed for the random number generator. This is used for reproducibility.
+            split_ratio (float, optional): The ratio of the training
+                set to the entire dataset.
+            random_state (int, optional): The seed for the
+                random number generator.
+            This is used for reproducibility.
             shuffle (bool, optional): Whether to shuffle the data before splitting.
 
         Returns:
-            Tuple[ClassificationDataset, ClassificationDataset]: A tuple containing the training and testing datasets.
+            Tuple[ClassificationDataset, ClassificationDataset]: A tuple containing
+            the training and testing datasets.
 
         Example:
             ```python
             >>> import supervision as sv
 
             >>> cd = sv.ClassificationDataset(...)
-            >>> train_cd, test_cd = cd.split(split_ratio=0.7, random_state=42, shuffle=True)
+            >>> train_cd,test_cd = cd.split(split_ratio=0.7,
+            ...                             random_state=42,shuffle=True)
             >>> len(train_cd), len(test_cd)
             (700, 300)
             ```
@@ -553,16 +607,18 @@ class ClassificationDataset(BaseDataset):
         Saves the dataset as a multi-class folder structure.
 
         Args:
-            root_directory_path (str): The path to the directory where the dataset will be saved.
+            root_directory_path (str): The path to the directory
+                where the dataset will be saved.
         """
         os.makedirs(root_directory_path, exist_ok=True)
 
         for class_name in self.classes:
             os.makedirs(os.path.join(root_directory_path, class_name), exist_ok=True)
 
-        for image_name in self.images:
-            classification = self.annotations[image_name]
-            image = self.images[image_name]
+        for image_path in self.images:
+            classification = self.annotations[image_path]
+            image = self.images[image_path]
+            image_name = Path(image_path).name
             class_id = (
                 classification.class_id[0]
                 if classification.confidence is None
@@ -611,9 +667,9 @@ class ClassificationDataset(BaseDataset):
             class_id = classes.index(class_name)
 
             for image in os.listdir(os.path.join(root_directory_path, class_name)):
-                image_dir = os.path.join(root_directory_path, class_name, image)
-                images[image] = cv2.imread(image_dir)
-                annotations[image] = Classifications(
+                image_path = str(os.path.join(root_directory_path, class_name, image))
+                images[image_path] = cv2.imread(image_path)
+                annotations[image_path] = Classifications(
                     class_id=np.array([class_id]),
                 )
 

supervision/dataset/formats/coco.py

@@ -159,7 +159,7 @@ 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(str(image_path))
+        image = cv2.imread(image_path)
         annotation = coco_annotations_to_detections(
             image_annotations=image_annotations,
             resolution_wh=(image_width, image_height),
@@ -170,8 +170,8 @@ def load_coco_annotations(
             detections=annotation,
         )
 
-        images[image_name] = image
-        annotations[image_name] = annotation
+        images[image_path] = image
+        annotations[image_path] = annotation
 
     return classes, images, annotations
 
@@ -200,9 +200,9 @@ def save_coco_annotations(
     coco_categories = classes_to_coco_categories(classes=classes)
 
     image_id, annotation_id = 1, 1
-    for image_name, image in images.items():
+    for image_path, image in images.items():
         image_height, image_width, _ = image.shape
-
+        image_name = f"{Path(image_path).stem}{Path(image_path).suffix}"
         coco_image = {
             "id": image_id,
             "license": 1,
@@ -213,9 +213,9 @@ def save_coco_annotations(
         }
 
         coco_images.append(coco_image)
-        detections = annotations[image_name]
+        detections = annotations[image_path]
 
-        coco_annotation, label_id = detections_to_coco_annotations(
+        coco_annotation, annotation_id = detections_to_coco_annotations(
             detections=detections,
             image_id=image_id,
             annotation_id=annotation_id,

supervision/dataset/formats/pascal_voc.py

@@ -21,6 +21,9 @@ def object_to_pascal_voc(
     object_name = SubElement(root, "name")
     object_name.text = name
 
+    # https://github.com/roboflow/supervision/issues/144
+    xyxy += 1
+
     bndbox = SubElement(root, "bndbox")
     xmin = SubElement(bndbox, "xmin")
     xmin.text = str(int(xyxy[0]))
@@ -32,6 +35,8 @@ def object_to_pascal_voc(
     ymax.text = str(int(xyxy[3]))
 
     if polygon is not None:
+        # https://github.com/roboflow/supervision/issues/144
+        polygon += 1
         object_polygon = SubElement(root, "polygon")
         for index, point in enumerate(polygon, start=1):
             x_coordinate, y_coordinate = point
@@ -56,13 +61,19 @@ def detections_to_pascal_voc(
     Converts Detections object to Pascal VOC XML format.
 
     Args:
-        detections (Detections): A Detections object containing bounding boxes, class ids, and other relevant information.
-        classes (List[str]): A list of class names corresponding to the class ids in the Detections object.
+        detections (Detections): A Detections object containing bounding boxes,
+            class ids, and other relevant information.
+        classes (List[str]): A list of class names corresponding to the
+            class ids in the Detections object.
         filename (str): The name of the image file associated with the detections.
-        image_shape (Tuple[int, int, int]): The shape of the image file associated with the detections.
-        min_image_area_percentage (float): Minimum detection area relative to area of image associated with it.
-        max_image_area_percentage (float): Maximum detection area relative to area of image associated with it.
-        approximation_percentage (float): The percentage of polygon points to be removed from the input polygon, in the range [0, 1).
+        image_shape (Tuple[int, int, int]): The shape of the image
+            file associated with the detections.
+        min_image_area_percentage (float): Minimum detection area
+            relative to area of image associated with it.
+        max_image_area_percentage (float): Maximum detection area
+            relative to area of image associated with it.
+        approximation_percentage (float): The percentage of
+            polygon points to be removed from the input polygon, in the range [0, 1).
     Returns:
         str: An XML string in Pascal VOC format representing the detections.
     """
@@ -129,15 +140,22 @@ def load_pascal_voc_annotations(
     force_masks: bool = False,
 ) -> Tuple[List[str], Dict[str, np.ndarray], Dict[str, Detections]]:
     """
-    Loads PASCAL VOC annotations and returns class names, images, and their corresponding detections.
+    Loads PASCAL VOC XML annotations and returns the image name,
+        a Detections instance, and a list of class names.
 
     Args:
         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 annotations, regardless of whether they are present.
+        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
+            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], 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.
     """
 
     image_paths = list_files_with_extensions(
@@ -150,12 +168,13 @@ def load_pascal_voc_annotations(
 
     for image_path in image_paths:
         image_name = Path(image_path).stem
-        image = cv2.imread(str(image_path))
+        image_path = str(image_path)
+        image = cv2.imread(image_path)
 
         annotation_path = os.path.join(annotations_directory_path, f"{image_name}.xml")
         if not os.path.exists(annotation_path):
-            images[image_path.name] = image
-            annotations[image_path.name] = Detections.empty()
+            images[image_path] = image
+            annotations[image_path] = Detections.empty()
             continue
 
         tree = parse(annotation_path)
@@ -166,8 +185,8 @@ def load_pascal_voc_annotations(
             root, classes, resolution_wh, force_masks
         )
 
-        images[image_path.name] = image
-        annotations[image_path.name] = annotation
+        images[image_path] = image
+        annotations[image_path] = annotation
 
     return classes, images, annotations
 
@@ -202,7 +221,9 @@ def detections_from_xml_obj(
     </annotation>
 
     Returns:
-        Tuple[Detections, List[str]]: A tuple containing a Detections object and an updated list of class names, extended with the class names from the XML object.
+        Tuple[Detections, List[str]]: A tuple containing a Detections object and an
+            updated list of class names, extended with the class names
+            from the XML object.
     """
     xyxy = []
     class_names = []
@@ -225,15 +246,21 @@ def detections_from_xml_obj(
         with_masks = force_masks if force_masks else with_masks
 
         for polygon in obj.findall("polygon"):
-            polygon_points = parse_polygon_points(polygon)
+            polygon = parse_polygon_points(polygon)
+            # https://github.com/roboflow/supervision/issues/144
+            polygon -= 1
 
             mask_from_polygon = polygon_to_mask(
-                polygon=np.array(polygon_points),
+                polygon=polygon,
                 resolution_wh=resolution_wh,
             )
             masks.append(mask_from_polygon)
 
     xyxy = np.array(xyxy) if len(xyxy) > 0 else np.empty((0, 4))
+
+    # https://github.com/roboflow/supervision/issues/144
+    xyxy -= 1
+
     for k in set(class_names):
         if k not in extended_classes:
             extended_classes.append(k)
@@ -250,11 +277,8 @@ def detections_from_xml_obj(
     return annotation, extended_classes
 
 
-def parse_polygon_points(polygon: Element) -> List[List[int]]:
-    polygon_points = []
-    coords = polygon.findall(".//*")
-    for i in range(0, len(coords), 2):
-        x = int(coords[i].text)
-        y = int(coords[i + 1].text)
-        polygon_points.append([x, y])
-    return polygon_points
+def parse_polygon_points(polygon: Element) -> np.ndarray:
+    coordinates = [int(coord.text) for coord in polygon.findall(".//*")]
+    return np.array(
+        [(coordinates[i], coordinates[i + 1]) for i in range(0, len(coordinates), 2)]
+    )

supervision/dataset/formats/yolo.py

@@ -1,6 +1,6 @@
 import os
 from pathlib import Path
-from typing import Dict, List, Optional, Tuple, Union
+from typing import Dict, List, Optional, Tuple
 
 import cv2
 import numpy as np
@@ -112,16 +112,23 @@ def load_yolo_annotations(
     force_masks: bool = False,
 ) -> Tuple[List[str], Dict[str, np.ndarray], Dict[str, Detections]]:
     """
-    Loads YOLO annotations and returns class names, images, and their corresponding detections.
+    Loads YOLO annotations and returns class names, images,
+        and their corresponding detections.
 
     Args:
         images_directory_path (str): The path to the directory containing the images.
-        annotations_directory_path (str): The path to the directory 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 for all annotations, regardless of whether they are present.
+        annotations_directory_path (str): The path to the directory
+            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
+            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], 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.
     """
     image_paths = list_files_with_extensions(
         directory=images_directory_path, extensions=["jpg", "jpeg", "png"]
@@ -132,13 +139,14 @@ def load_yolo_annotations(
     annotations = {}
 
     for image_path in image_paths:
-        image_name = Path(image_path).stem
-        image = cv2.imread(str(image_path))
+        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_name}.txt")
+        annotation_path = os.path.join(annotations_directory_path, f"{image_stem}.txt")
         if not os.path.exists(annotation_path):
-            images[image_path.name] = image
-            annotations[image_path.name] = Detections.empty()
+            images[image_path] = image
+            annotations[image_path] = Detections.empty()
             continue
 
         lines = read_txt_file(str(annotation_path))
@@ -151,8 +159,8 @@ def load_yolo_annotations(
             lines=lines, resolution_wh=resolution_wh, with_masks=with_masks
         )
 
-        images[image_path.name] = image
-        annotations[image_path.name] = annotation
+        images[image_path] = image
+        annotations[image_path] = annotation
     return classes, images, annotations
 
 
@@ -220,8 +228,9 @@ def save_yolo_annotations(
     approximation_percentage: float = 0.75,
 ) -> None:
     Path(annotations_directory_path).mkdir(parents=True, exist_ok=True)
-    for image_name, image in images.items():
-        detections = annotations[image_name]
+    for image_path, image in images.items():
+        detections = annotations[image_path]
+        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

supervision/dataset/utils.py

@@ -64,7 +64,7 @@ def build_class_index_mapping(
         if class_name not in target_classes:
             raise ValueError(
                 f"Class {class_name} not found in target classes. "
-                f"source_classes must be a subset of target_classes."
+                "source_classes must be a subset of target_classes."
             )
         corresponding_index = target_classes.index(class_name)
         index_mapping[i] = corresponding_index
@@ -97,7 +97,8 @@ def save_dataset_images(
 ) -> None:
     Path(images_directory_path).mkdir(parents=True, exist_ok=True)
 
-    for image_name, image in images.items():
+    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)
 

supervision/detection/annotate.py

@@ -12,12 +12,15 @@ 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
+        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
+        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
 
     """
 
@@ -49,8 +52,11 @@ class BoxAnnotator:
 
         Args:
             scene (np.ndarray): The image on which the bounding boxes will be drawn
-            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.
+            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:
             np.ndarray: The image with the bounding boxes drawn on it
@@ -145,7 +151,8 @@ class MaskAnnotator:
     A class for overlaying masks on an image using detections provided.
 
     Attributes:
-        color (Union[Color, ColorPalette]): The color to fill the mask, can be a single color or a color palette
+        color (Union[Color, ColorPalette]): The color to fill the mask,
+            can be a single color or a color palette
     """
 
     def __init__(
@@ -158,11 +165,13 @@ class MaskAnnotator:
         self, scene: np.ndarray, detections: Detections, opacity: float = 0.5
     ) -> np.ndarray:
         """
-        Overlays the masks on the given image based on the provided detections, with a specified opacity.
+        Overlays the masks on the given image based on the provided detections,
+            with a specified opacity.
 
         Args:
             scene (np.ndarray): The image on which the masks will be overlaid
-            detections (Detections): The detections for which the masks will be overlaid
+            detections (Detections): The detections for which the
+                masks will be overlaid
             opacity (float): The opacity of the masks, between 0 and 1, default is 0.5
 
         Returns:

supervision/detection/core.py

@@ -3,7 +3,6 @@ from __future__ import annotations
 from dataclasses import astuple, dataclass
 from typing import Any, Iterator, List, Optional, Tuple, Union
 
-import cv2
 import numpy as np
 
 from supervision.detection.utils import (
@@ -30,6 +29,13 @@ def _validate_mask(mask: Any, n: int) -> None:
         raise ValueError("mask must be 3d np.ndarray with (n, H, W) shape")
 
 
+def validate_inference_callback(callback) -> None:
+    tmp_img = np.zeros((256, 256, 3), dtype=np.uint8)
+    res = callback(tmp_img)
+    if not isinstance(res, Detections):
+        raise ValueError("Callback function must return sv.Detection type")
+
+
 def _validate_class_id(class_id: Any, n: int) -> None:
     is_valid = class_id is None or (
         isinstance(class_id, np.ndarray) and class_id.shape == (n,)
@@ -59,11 +65,16 @@ class Detections:
     """
     Data class containing information about the detections in a video frame.
     Attributes:
-        xyxy (np.ndarray): An array of shape `(n, 4)` containing the bounding boxes coordinates in format `[x1, y1, x2, y2]`
-        mask: (Optional[np.ndarray]): An array of shape `(n, H, W)` containing the segmentation masks.
-        confidence (Optional[np.ndarray]): An array of shape `(n,)` containing the confidence scores of the detections.
-        class_id (Optional[np.ndarray]): An array of shape `(n,)` containing the class ids of the detections.
-        tracker_id (Optional[np.ndarray]): An array of shape `(n,)` containing the tracker ids of the detections.
+        xyxy (np.ndarray): An array of shape `(n, 4)` containing
+            the bounding boxes coordinates in format `[x1, y1, x2, y2]`
+        mask: (Optional[np.ndarray]): An array of shape
+            `(n, H, W)` containing the segmentation masks.
+        confidence (Optional[np.ndarray]): An array of shape
+            `(n,)` containing the confidence scores of the detections.
+        class_id (Optional[np.ndarray]): An array of shape
+            `(n,)` containing the class ids of the detections.
+        tracker_id (Optional[np.ndarray]): An array of shape
+            `(n,)` containing the tracker ids of the detections.
     """
 
     xyxy: np.ndarray
@@ -98,7 +109,8 @@ class Detections:
         ]
     ]:
         """
-        Iterates over the Detections object and yield a tuple of `(xyxy, mask, confidence, class_id, tracker_id)` for each detection.
+        Iterates over the Detections object and yield a tuple of
+        `(xyxy, mask, confidence, class_id, tracker_id)` for each detection.
         """
         for i in range(len(self.xyxy)):
             yield (
@@ -143,10 +155,12 @@ class Detections:
     @classmethod
     def from_yolov5(cls, yolov5_results) -> Detections:
         """
-        Creates a Detections instance from a [YOLOv5](https://github.com/ultralytics/yolov5) inference result.
+        Creates a Detections instance from a
+        [YOLOv5](https://github.com/ultralytics/yolov5) inference result.
 
         Args:
-            yolov5_results (yolov5.models.common.Detections): The output Detections instance from YOLOv5
+            yolov5_results (yolov5.models.common.Detections):
+                The output Detections instance from YOLOv5
 
         Returns:
             Detections: A new Detections object.
@@ -172,14 +186,20 @@ class Detections:
 
     @classmethod
     @deprecated(
-        "This method is deprecated and removed in 0.15.0 release. Use sv.Detections.from_ultralytics() instead."
+        """
+        This method is deprecated and removed in 0.15.0 release.
+        Use sv.Detections.from_ultralytics() instead as it is more generic and
+        can be used for detections from any ultralytics.engine.results.Results Object
+        """
     )
     def from_yolov8(cls, yolov8_results) -> Detections:
         """
-        Creates a Detections instance from a [YOLOv8](https://github.com/ultralytics/ultralytics) inference result.
+        Creates a Detections instance from a
+        [YOLOv8](https://github.com/ultralytics/ultralytics) inference result.
 
         Args:
-            yolov8_results (ultralytics.yolo.engine.results.Results): The output Results instance from YOLOv8
+            yolov8_results (ultralytics.yolo.engine.results.Results):
+                The output Results instance from YOLOv8
 
         Returns:
             Detections: A new Detections object.
@@ -206,10 +226,12 @@ class Detections:
     @classmethod
     def from_ultralytics(cls, ultralytics_results) -> Detections:
         """
-        Creates a Detections instance from a [YOLOv8](https://github.com/ultralytics/ultralytics) inference result.
+        Creates a Detections instance from a
+            [YOLOv8](https://github.com/ultralytics/ultralytics) inference result.
 
         Args:
-            ultralytics_results (ultralytics.yolo.engine.results.Results): The output Results instance from YOLOv8
+            ultralytics_results (ultralytics.yolo.engine.results.Results):
+                The output Results instance from YOLOv8
 
         Returns:
             Detections: A new Detections object.
@@ -246,10 +268,15 @@ class Detections:
     @classmethod
     def from_yolo_nas(cls, yolo_nas_results) -> Detections:
         """
-        Creates a Detections instance from a [YOLO-NAS](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md) inference result.
+        Creates a Detections instance from a
+        [YOLO-NAS](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md)
+        inference result.
 
         Args:
-            yolo_nas_results (super_gradients.training.models.prediction_results.ImageDetectionPrediction): The output Results instance from YOLO-NAS
+            yolo_nas_results (ImageDetectionPrediction):
+                The output Results instance from YOLO-NAS
+                ImageDetectionPrediction is coming from
+                'super_gradients.training.models.prediction_results'
 
         Returns:
             Detections: A new Detections object.
@@ -272,14 +299,51 @@ class Detections:
             class_id=yolo_nas_results.prediction.labels.astype(int),
         )
 
+    @classmethod
+    def from_deepsparse(cls, deepsparse_results) -> Detections:
+        """
+        Creates a Detections instance from a
+        [DeepSparse](https://github.com/neuralmagic/deepsparse)
+        inference result.
+
+        Args:
+            deepsparse_results (deepsparse.yolo.schemas.YOLOOutput):
+                The output Results instance from DeepSparse.
+
+        Returns:
+            Detections: A new Detections object.
+
+        Example:
+            ```python
+            >>> from deepsparse import Pipeline
+            >>> import supervision as sv
+
+            >>> yolo_pipeline = Pipeline.create(
+            ...     task="yolo",
+            ...     model_stub = "zoo:cv/detection/yolov5-l/pytorch/" \
+            ...                  "ultralytics/coco/pruned80_quant-none"
+            >>> pipeline_outputs = yolo_pipeline(SOURCE_IMAGE_PATH,
+            ...                         iou_thres=0.6, conf_thres=0.001)
+            >>> result = list(pipeline_outputs.boxes[0])
+            >>> detections = sv.Detections.from_yolo_nas(result)
+            ```
+        """
+        return cls(
+            xyxy=np.array(deepsparse_results.boxes[0]),
+            confidence=np.array(deepsparse_results.scores[0]),
+            class_id=np.array(deepsparse_results.labels[0]).astype(float).astype(int),
+        )
+
     @classmethod
     def from_mmdetection(cls, mmdet_results) -> Detections:
         """
-        Creates a Detections instance from a [mmdetection](https://github.com/open-mmlab/mmdetection) inference result.
+        Creates a Detections instance from
+        a [mmdetection](https://github.com/open-mmlab/mmdetection) inference result.
         Also supported for [mmyolo](https://github.com/open-mmlab/mmyolo)
 
         Args:
-            mmdet_results (mmdet.structures.DetDataSample): The output Results instance from MMDetection
+            mmdet_results (mmdet.structures.DetDataSample):
+                The output Results instance from MMDetection.
 
         Returns:
             Detections: A new Detections object.
@@ -291,7 +355,8 @@ class Detections:
             >>> from mmdet.apis import DetInferencer
 
             >>> inferencer = DetInferencer(model_name, checkpoint, device)
-            >>> mmdet_result = inferencer(SOURCE_IMAGE_PATH, out_dir='./output', return_datasample=True)["predictions"][0]
+            >>> mmdet_result = inferencer(SOURCE_IMAGE_PATH, out_dir='./output',
+            ...                           return_datasample=True)["predictions"][0]
             >>> detections = sv.Detections.from_mmdet(mmdet_result)
             ```
         """
@@ -304,7 +369,8 @@ class Detections:
     @classmethod
     def from_transformers(cls, transformers_results: dict) -> Detections:
         """
-        Creates a Detections instance from object detection [transformer](https://github.com/huggingface/transformers) inference result.
+        Creates a Detections instance from object detection
+        [transformer](https://github.com/huggingface/transformers) inference result.
 
         Returns:
             Detections: A new Detections object.
@@ -318,13 +384,16 @@ class Detections:
     @classmethod
     def from_detectron2(cls, detectron2_results) -> Detections:
         """
-        Create a Detections object from the [Detectron2](https://github.com/facebookresearch/detectron2) inference result.
+        Create a Detections 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.
+            detectron2_results: The output of a
+                Detectron2 model containing instances with prediction data.
 
         Returns:
-            (Detections): A Detections object containing the bounding boxes, class IDs, and confidences of the predictions.
+            (Detections): A Detections object containing the bounding boxes,
+                class IDs, and confidences of the predictions.
 
         Example:
             ```python
@@ -339,7 +408,6 @@ class Detections:
             >>> cfg.MODEL.WEIGHTS = "path/to/model_weights.pth"
             >>> predictor = DefaultPredictor(cfg)
             >>> result = predictor(image)
-
             >>> detections = sv.Detections.from_detectron2(result)
             ```
         """
@@ -355,14 +423,18 @@ class Detections:
     @classmethod
     def from_roboflow(cls, roboflow_result: dict, class_list: List[str]) -> Detections:
         """
-        Create a Detections object from the [Roboflow](https://roboflow.com/) API inference result.
+        Create a Detections object from the [Roboflow](https://roboflow.com/)
+            API inference result.
 
         Args:
-            roboflow_result (dict): The result from the Roboflow API containing predictions.
-            class_list (List[str]): A list of class names corresponding to the class IDs in the API result.
+            roboflow_result (dict): The result from the
+                Roboflow API containing predictions.
+            class_list (List[str]): A list of class names
+                corresponding to the class IDs in the API result.
 
         Returns:
-            (Detections): A Detections object containing the bounding boxes, class IDs, and confidences of the predictions.
+            (Detections): A Detections object containing the bounding boxes, class IDs,
+                and confidences of the predictions.
 
         Example:
             ```python
@@ -399,7 +471,9 @@ class Detections:
     @classmethod
     def from_sam(cls, sam_result: List[dict]) -> Detections:
         """
-        Creates a Detections instance from [Segment Anything Model](https://github.com/facebookresearch/segment-anything) inference result.
+        Creates a Detections instance from
+        [Segment Anything Model](https://github.com/facebookresearch/segment-anything)
+        inference result.
 
         Args:
             sam_result (List[dict]): The output Results instance from SAM
@@ -410,14 +484,19 @@ class Detections:
         Example:
             ```python
             >>> import supervision as sv
-            >>> from segment_anything import sam_model_registry, SamAutomaticMaskGenerator
+            >>> from segment_anything import (
+            ...     sam_model_registry,
+            ...     SamAutomaticMaskGenerator
+            ...     )
 
-            >>> sam = sam_model_registry[MODEL_TYPE](checkpoint=CHECKPOINT_PATH).to(device=DEVICE)
+            >>> 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)
             ```
         """
+
         sorted_generated_masks = sorted(
             sam_result, key=lambda x: x["area"], reverse=True
         )
@@ -430,10 +509,12 @@ class Detections:
     @classmethod
     def from_paddledet(cls, paddledet_result) -> Detections:
         """
-        Creates a Detections instance from [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection) inference result.
+        Creates a Detections instance from
+            [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection)
+            inference result.
 
         Args:
-            paddledet_result (List[dict]): The output Results instance from SAM
+            paddledet_result (List[dict]): The output Results instance from PaddleDet
 
         Returns:
             Detections: A new Detections object.
@@ -454,7 +535,7 @@ class Detections:
 
             >>> paddledet_result = trainer.predict([images])[0]
 
-            >>> detections = sv.Detections.from_paddledet(paddledet_result=paddledet_result)
+            >>> detections = sv.Detections.from_paddledet(paddledet_result)
             ```
         """
         return cls(
@@ -466,7 +547,8 @@ class Detections:
     @classmethod
     def empty(cls) -> Detections:
         """
-        Create an empty Detections object with no bounding boxes, confidences, or class IDs.
+        Create an empty Detections object with no bounding boxes,
+            confidences, or class IDs.
 
         Returns:
             (Detections): An empty Detections object.
@@ -489,15 +571,18 @@ class Detections:
         """
         Merge a list of Detections objects into a single Detections object.
 
-        This method takes a list of Detections objects and combines their respective fields (`xyxy`, `mask`,
-        `confidence`, `class_id`, and `tracker_id`) into a single Detections object. If all elements in a field are not
-        `None`, the corresponding field will be stacked. Otherwise, the field will be set to `None`.
+        This method takes a list of Detections objects and combines their
+        respective fields (`xyxy`, `mask`, `confidence`, `class_id`, and `tracker_id`)
+        into a single Detections object. If all elements in a field are not
+        `None`, the corresponding field will be stacked.
+        Otherwise, the field will be set to `None`.
 
         Args:
             detections_list (List[Detections]): A list of Detections objects to merge.
 
         Returns:
-            (Detections): A single Detections object containing the merged data from the input list.
+            (Detections): A single Detections object containing
+                the merged data from the input list.
 
         Example:
             ```python
@@ -517,13 +602,14 @@ class Detections:
             list(field) for field in zip(*detections_tuples_list)
         ]
 
-        all_not_none = lambda l: all(x is not None for x in l)
+        def __all_not_none(item_list: List[Any]):
+            return all(x is not None for x in item_list)
 
         xyxy = np.vstack(xyxy)
-        mask = np.vstack(mask) if all_not_none(mask) else None
-        confidence = np.hstack(confidence) if all_not_none(confidence) else None
-        class_id = np.hstack(class_id) if all_not_none(class_id) else None
-        tracker_id = np.hstack(tracker_id) if all_not_none(tracker_id) else None
+        mask = np.vstack(mask) if __all_not_none(mask) else None
+        confidence = np.hstack(confidence) if __all_not_none(confidence) else None
+        class_id = np.hstack(class_id) if __all_not_none(class_id) else None
+        tracker_id = np.hstack(tracker_id) if __all_not_none(tracker_id) else None
 
         return cls(
             xyxy=xyxy,
@@ -538,10 +624,12 @@ class Detections:
         Returns the bounding box coordinates for a specific anchor.
 
         Args:
-            anchor (Position): Position of bounding box anchor for which to return the coordinates.
+            anchor (Position): Position of bounding box anchor
+                for which to return the coordinates.
 
         Returns:
-            np.ndarray: An array of shape `(n, 2)` containing the bounding box anchor coordinates in format `[x, y]`.
+            np.ndarray: An array of shape `(n, 2)` containing the bounding
+                box anchor coordinates in format `[x, y]`.
         """
         if anchor == Position.CENTER:
             return np.array(
@@ -564,7 +652,8 @@ class Detections:
         Get a subset of the Detections object.
 
         Args:
-            index (Union[int, slice, List[int], np.ndarray]): The index or indices of the subset of the Detections
+            index (Union[int, slice, List[int], np.ndarray]):
+                The index or indices of the subset of the Detections
 
         Returns:
             (Detections): A subset of the Detections object.
@@ -599,11 +688,14 @@ class Detections:
     @property
     def area(self) -> np.ndarray:
         """
-        Calculate the area of each detection in the set of object detections. If masks field is defined property
-        returns are of each mask. If only box is given property return area of each box.
+        Calculate the area of each detection in the set of object detections.
+        If masks field is defined property returns are of each mask.
+        If only box is given property return area of each box.
 
         Returns:
-          np.ndarray: An array of floats containing the area of each detection in the format of `(area_1, area_2, ..., area_n)`, where n is the number of detections.
+          np.ndarray: An array of floats containing the area of each detection
+            in the format of `(area_1, area_2, ..., area_n)`,
+            where n is the number of detections.
         """
         if self.mask is not None:
             return np.array([np.sum(mask) for mask in self.mask])
@@ -616,7 +708,9 @@ class Detections:
         Calculate the area of each bounding box in the set of object detections.
 
         Returns:
-            np.ndarray: An array of floats containing the area of each bounding box in the format of `(area_1, area_2, ..., area_n)`, where n is the number of detections.
+            np.ndarray: An array of floats containing the area of each bounding
+                box in the format of `(area_1, area_2, ..., area_n)`,
+                where n is the number of detections.
         """
         return (self.xyxy[:, 3] - self.xyxy[:, 1]) * (self.xyxy[:, 2] - self.xyxy[:, 0])
 
@@ -627,21 +721,26 @@ class Detections:
         Perform non-maximum suppression on the current set of object detections.
 
         Args:
-            threshold (float, optional): The intersection-over-union threshold to use for non-maximum suppression. Defaults to 0.5.
-            class_agnostic (bool, optional): Whether to perform class-agnostic non-maximum suppression. If True, the class_id of each detection will be ignored. Defaults to False.
+            threshold (float, optional): The intersection-over-union threshold
+                to use for non-maximum suppression. Defaults to 0.5.
+            class_agnostic (bool, optional): Whether to perform class-agnostic
+                non-maximum suppression. If True, the class_id of each detection
+                will be ignored. Defaults to False.
 
         Returns:
-            Detections: A new Detections object containing the subset of detections after non-maximum suppression.
+            Detections: A new Detections object containing the subset of detections
+                after non-maximum suppression.
 
         Raises:
-            AssertionError: If `confidence` is None and class_agnostic is False. If `class_id` is None and class_agnostic is False.
+            AssertionError: If `confidence` is None and class_agnostic is False.
+                If `class_id` is None and class_agnostic is False.
         """
         if len(self) == 0:
             return self
 
         assert (
             self.confidence is not None
-        ), f"Detections confidence must be given for NMS to be executed."
+        ), "Detections confidence must be given for NMS to be executed."
 
         if class_agnostic:
             predictions = np.hstack((self.xyxy, self.confidence.reshape(-1, 1)))
@@ -651,8 +750,8 @@ class Detections:
             return self[indices]
 
         assert self.class_id is not None, (
-            f"Detections class_id must be given for NMS to be executed. If you intended to perform class agnostic "
-            f"NMS set class_agnostic=True."
+            "Detections class_id must be given for NMS to be executed. If you intended"
+            " to perform class agnostic NMS set class_agnostic=True."
         )
 
         predictions = np.hstack(

supervision/detection/line_counter.py

@@ -113,7 +113,8 @@ class LineZoneAnnotator:
 
         Attributes:
             frame (np.ndarray): The image on which the line will be drawn.
-            line_counter (LineCounter): The line counter that will be used to draw the line.
+            line_counter (LineCounter): The line counter
+                that will be used to draw the line.
 
         Returns:
             np.ndarray: The image with the line drawn on it.

supervision/detection/tools/inference_slicer.py

@@ -0,0 +1,156 @@
+from typing import Callable, Optional, Tuple
+
+import numpy as np
+
+from supervision.detection.core import Detections, validate_inference_callback
+from supervision.detection.utils import move_boxes
+from supervision.utils.image import crop_image
+
+
+def move_detections(detections: Detections, offset: np.array) -> Detections:
+    """
+    Args:
+        detections (sv.Detections): Detections object to be moved.
+        offset (np.array): An array of shape `(2,)` containing offset values in format
+            is `[dx, dy]`.
+    Returns:
+        (sv.Detections) repositioned Detections object.
+    """
+    detections.xyxy = move_boxes(xyxy=detections.xyxy, offset=offset)
+    return detections
+
+
+class InferenceSlicer:
+    """
+    InferenceSlicer performs slicing-based inference for small target detection. This
+    method, often referred to as Slicing Adaptive Inference (SAHI), involves dividing a
+    larger image into smaller slices, performing inference on each slice, and then
+    merging the detections.
+
+    Attributes:
+        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)`.
+        iou_threshold (Optional[float]): Intersection over Union (IoU) threshold used
+            for non-max suppression.
+        callback (Callable): A function that performs inference on a given image slice
+            and returns detections.
+
+    Note:
+        The class ensures that slices do not exceed the boundaries of the original
+        image. As a result, the final slices in the row and column dimensions might be
+        smaller than the specified slice dimensions if the image's width or height is
+        not a multiple of the slice's width or height minus the overlap.
+    """
+
+    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),
+        iou_threshold: Optional[float] = 0.5,
+    ):
+        self.slice_wh = slice_wh
+        self.overlap_ratio_wh = overlap_ratio_wh
+        self.iou_threshold = iou_threshold
+        self.callback = callback
+        validate_inference_callback(callback=callback)
+
+    def __call__(self, image: np.ndarray) -> Detections:
+        """
+        Performs slicing-based inference on the provided image using the specified
+            callback.
+
+        Args:
+            image (np.ndarray): The input image on which inference needs to be
+                performed. The image should be in the format
+                `(height, width, channels)`.
+
+        Returns:
+            Detections: A collection of detections for the entire image after merging
+                results from all slices and applying NMS.
+
+        Example:
+            ```python
+            >>> import cv2
+            >>> import supervision as sv
+            >>> from ultralytics import YOLO
+
+            >>> image = cv2.imread(SOURCE_IMAGE_PATH)
+            >>> model = YOLO(...)
+
+            >>> def callback(image_slice: np.ndarray) -> sv.Detections:
+            ...     result = model(image_slice)[0]
+            ...     return sv.Detections.from_ultralytics(result)
+
+            >>> slicer = sv.InferenceSlicer(callback = callback)
+
+            >>> detections = slicer(image)
+            ```
+        """
+        detections_list = []
+        resolution_wh = (image.shape[1], image.shape[0])
+        offsets = self._generate_offset(
+            resolution_wh=resolution_wh,
+            slice_wh=self.slice_wh,
+            overlap_ratio_wh=self.overlap_ratio_wh,
+        )
+
+        for offset in offsets:
+            image_slice = crop_image(image=image, xyxy=offset)
+            detections = self.callback(image_slice)
+            detections = move_detections(detections=detections, offset=offset[:2])
+            detections_list.append(detections)
+        return Detections.merge(detections_list=detections_list).with_nms(
+            threshold=self.iou_threshold
+        )
+
+    @staticmethod
+    def _generate_offset(
+        resolution_wh: Tuple[int, int],
+        slice_wh: Tuple[int, int],
+        overlap_ratio_wh: Tuple[float, float],
+    ) -> np.ndarray:
+        """
+        Generate offset coordinates for slicing an image based on the given resolution,
+        slice dimensions, and overlap ratios.
+
+        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.
+
+        Returns:
+            np.ndarray: An array of shape `(n, 4)` containing coordinates for each
+                slice in the format `[xmin, ymin, xmax, ymax]`.
+
+        Note:
+            The function ensures that slices do not exceed the boundaries of the
+                original image. As a result, the final slices in the row and column
+                dimensions might be smaller than the specified slice dimensions if the
+                image's width or height is not a multiple of the slice's width or
+                height minus the overlap.
+        """
+        slice_width, slice_height = slice_wh
+        image_width, image_height = resolution_wh
+        overlap_ratio_width, overlap_ratio_height = overlap_ratio_wh
+
+        width_stride = slice_width - int(overlap_ratio_width * slice_width)
+        height_stride = slice_height - int(overlap_ratio_height * slice_height)
+
+        ws = np.arange(0, image_width, width_stride)
+        hs = np.arange(0, image_height, height_stride)
+
+        xmin, ymin = np.meshgrid(ws, hs)
+        xmax = np.clip(xmin + slice_width, 0, image_width)
+        ymax = np.clip(ymin + slice_height, 0, image_height)
+
+        offsets = np.stack([xmin, ymin, xmax, ymax], axis=-1).reshape(-1, 4)
+
+        return offsets

supervision/detection/tools/polygon_zone.py

@@ -17,9 +17,11 @@ class PolygonZone:
     A class for defining a polygon-shaped zone within a frame for detecting objects.
 
     Attributes:
-        polygon (np.ndarray): A polygon represented by a numpy array of shape `(N, 2)`, containing the `x`, `y` coordinates of the points.
+        polygon (np.ndarray): A polygon represented by a numpy array of shape
+            `(N, 2)`, containing the `x`, `y` coordinates of the points.
         frame_resolution_wh (Tuple[int, int]): The frame resolution (width, height)
-        triggering_position (Position): The position within the bounding box that triggers the zone (default: Position.BOTTOM_CENTER)
+        triggering_position (Position): The position within the bounding
+            box that triggers the zone (default: Position.BOTTOM_CENTER)
         current_count (int): The current count of detected objects within the zone
         mask (np.ndarray): The 2D bool mask for the polygon zone
     """
@@ -45,10 +47,12 @@ class PolygonZone:
         Determines if the detections are within the polygon zone.
 
         Parameters:
-            detections (Detections): The detections to be checked against the polygon zone
+            detections (Detections): The detections
+                to be checked against the polygon zone
 
         Returns:
-            np.ndarray: A boolean numpy array indicating if each detection is within the polygon zone
+            np.ndarray: A boolean numpy array indicating
+                if each detection is within the polygon zone
         """
 
         clipped_xyxy = clip_boxes(
@@ -65,7 +69,8 @@ class PolygonZone:
 
 class PolygonZoneAnnotator:
     """
-    A class for annotating a polygon-shaped zone within a frame with a count of detected objects.
+    A class for annotating a polygon-shaped zone within a
+        frame with a count of detected objects.
 
     Attributes:
         zone (PolygonZone): The polygon zone to be annotated
@@ -75,7 +80,8 @@ class PolygonZoneAnnotator:
         text_scale (float): The scale of the text on the polygon, default is 0.5
         text_thickness (int): The thickness of the text on the polygon, default is 1
         text_padding (int): The padding around the text on the polygon, default is 10
-        font (int): The font type for the text on the polygon, default is cv2.FONT_HERSHEY_SIMPLEX
+        font (int): The font type for the text on the polygon,
+            default is cv2.FONT_HERSHEY_SIMPLEX
         center (Tuple[int, int]): The center of the polygon for text placement
     """
 
@@ -105,7 +111,8 @@ 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 within the polygon zone (default: None)
+            label (Optional[str]): An optional label for the count of detected objects
+                within the polygon zone (default: None)
 
         Returns:
             np.ndarray: The image with the polygon zone and count of detected objects

supervision/detection/utils.py

@@ -10,29 +10,37 @@ def polygon_to_mask(polygon: np.ndarray, resolution_wh: Tuple[int, int]) -> np.n
     """Generate a mask from a polygon.
 
     Args:
-        polygon (np.ndarray): The polygon for which the mask should be generated, given as a list of vertices.
+        polygon (np.ndarray): The polygon for which the mask should be generated,
+            given as a list of vertices.
         resolution_wh (Tuple[int, int]): The width and height of the desired resolution.
 
     Returns:
-        np.ndarray: The generated 2D mask, where the polygon is marked with `1`'s and the rest is filled with `0`'s.
+        np.ndarray: The generated 2D mask, where the polygon is marked with
+            `1`'s and the rest is filled with `0`'s.
     """
     width, height = resolution_wh
     mask = np.zeros((height, width))
+
     cv2.fillPoly(mask, [polygon], color=1)
     return mask
 
 
 def box_iou_batch(boxes_true: np.ndarray, boxes_detection: np.ndarray) -> np.ndarray:
     """
-    Compute Intersection over Union (IoU) of two sets of bounding boxes - `boxes_true` and `boxes_detection`. Both sets
-    of boxes are expected to be in `(x_min, y_min, x_max, y_max)` format.
+    Compute Intersection over Union (IoU) of two sets of bounding boxes -
+        `boxes_true` and `boxes_detection`. Both sets
+        of boxes are expected to be in `(x_min, y_min, x_max, y_max)` format.
 
     Args:
-        boxes_true (np.ndarray): 2D `np.ndarray` representing ground-truth boxes. `shape = (N, 4)` where `N` is number of true objects.
-        boxes_detection (np.ndarray): 2D `np.ndarray` representing detection boxes. `shape = (M, 4)` where `M` is number of detected objects.
+        boxes_true (np.ndarray): 2D `np.ndarray` representing ground-truth boxes.
+            `shape = (N, 4)` where `N` is number of true objects.
+        boxes_detection (np.ndarray): 2D `np.ndarray` representing detection boxes.
+            `shape = (M, 4)` where `M` is number of detected objects.
 
     Returns:
-        np.ndarray: Pairwise IoU of boxes from `boxes_true` and `boxes_detection`. `shape = (N, M)` where `N` is number of true objects and `M` is number of detected objects.
+        np.ndarray: Pairwise IoU of boxes from `boxes_true` and `boxes_detection`.
+            `shape = (N, M)` where `N` is number of true objects and
+            `M` is number of detected objects.
     """
 
     def box_area(box):
@@ -55,17 +63,22 @@ def non_max_suppression(
     Perform Non-Maximum Suppression (NMS) on object detection predictions.
 
     Args:
-        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 to use for non-maximum 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
+            to use for non-maximum suppression.
 
     Returns:
-        np.ndarray: A boolean array indicating which predictions to keep after non-maximum suppression.
+        np.ndarray: A boolean array indicating which predictions to keep after n
+            on-maximum suppression.
 
     Raises:
-        AssertionError: If `iou_threshold` is not within the closed range from `0` to `1`.
+        AssertionError: If `iou_threshold` is not within the
+            closed range from `0` to `1`.
     """
     assert 0 <= iou_threshold <= 1, (
-        f"Value of `iou_threshold` must be in the closed range from 0 to 1, "
+        "Value of `iou_threshold` must be in the closed range from 0 to 1, "
         f"{iou_threshold} given."
     )
     rows, columns = predictions.shape
@@ -89,7 +102,8 @@ def non_max_suppression(
         if not keep[index]:
             continue
 
-        # drop detections with iou > iou_threshold and same category as current detections
+        # drop detections with iou > iou_threshold and
+        # same category as current detections
         condition = (iou > iou_threshold) & (categories == category)
         keep = keep & ~condition
 
@@ -103,14 +117,16 @@ def clip_boxes(
     Clips bounding boxes coordinates to fit within the frame resolution.
 
     Args:
-        boxes_xyxy (np.ndarray): A numpy array of shape `(N, 4)` where each row corresponds to a bounding box in
+        boxes_xyxy (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)`.
-        frame_resolution_wh (Tuple[int, int]): A tuple of the form `(width, height)` representing the resolution of the
-        frame.
+        frame_resolution_wh (Tuple[int, int]): A tuple of the form `(width, height)`
+            representing the resolution of the frame.
 
     Returns:
-        np.ndarray: A numpy array of shape `(N, 4)` where each row corresponds to a bounding box with coordinates
-        clipped to fit within the frame resolution.
+        np.ndarray: A numpy array of shape `(N, 4)` where each row
+            corresponds to a bounding box with coordinates clipped to fit
+            within the frame resolution.
     """
     result = np.copy(boxes_xyxy)
     width, height = frame_resolution_wh
@@ -131,10 +147,12 @@ def mask_to_xyxy(masks: np.ndarray) -> np.ndarray:
     Converts a 3D `np.array` of 2D bool masks into a 2D `np.array` of bounding boxes.
 
     Parameters:
-        masks (np.ndarray): A 3D `np.array` of shape `(N, W, H)` containing 2D bool masks
+        masks (np.ndarray): A 3D `np.array` of shape `(N, W, H)`
+            containing 2D bool masks
 
     Returns:
-        np.ndarray: A 2D `np.array` of shape `(N, 4)` containing the bounding boxes `(x_min, y_min, x_max, y_max)` for each mask
+        np.ndarray: A 2D `np.array` of shape `(N, 4)` containing the bounding boxes
+            `(x_min, y_min, x_max, y_max)` for each mask
     """
     n = masks.shape[0]
     bboxes = np.zeros((n, 4), dtype=int)
@@ -155,12 +173,14 @@ def mask_to_polygons(mask: np.ndarray) -> List[np.ndarray]:
     Converts a binary mask to a list of polygons.
 
     Parameters:
-        mask (np.ndarray): A binary mask represented as a 2D NumPy array of shape `(H, W)`,
-            where H and W are the height and width of the mask, respectively.
+        mask (np.ndarray): A binary mask represented as a 2D NumPy array of
+            shape `(H, W)`, where H and W are the height and width of
+            the mask, respectively.
 
     Returns:
-        List[np.ndarray]: A list of polygons, where each polygon is represented by a NumPy array of shape `(N, 2)`,
-            containing the `x`, `y` coordinates of the points. Polygons with fewer points than `MIN_POLYGON_POINT_COUNT = 3`
+        List[np.ndarray]: A list of polygons, where each polygon is represented by a
+            NumPy array of shape `(N, 2)`, containing the `x`, `y` coordinates
+            of the points. Polygons with fewer points than `MIN_POLYGON_POINT_COUNT = 3`
             are excluded from the output.
     """
 
@@ -183,15 +203,21 @@ def filter_polygons_by_area(
     Filters a list of polygons based on their area.
 
     Parameters:
-        polygons (List[np.ndarray]): A list of polygons, where each polygon is represented by a NumPy array of shape `(N, 2)`,
+        polygons (List[np.ndarray]): A list of polygons, where each polygon is
+            represented by a NumPy array of shape `(N, 2)`,
             containing the `x`, `y` coordinates of the points.
-        min_area (Optional[float]): The minimum area threshold. Only polygons with an area greater than or equal to this value
-            will be included in the output. If set to None, no minimum area constraint will be applied.
-        max_area (Optional[float]): The maximum area threshold. Only polygons with an area less than or equal to this value
-            will be included in the output. If set to None, no maximum area constraint will be applied.
+        min_area (Optional[float]): The minimum area threshold.
+            Only polygons with an area greater than or equal to this value
+            will be included in the output. If set to None,
+            no minimum area constraint will be applied.
+        max_area (Optional[float]): The maximum area threshold.
+            Only polygons with an area less than or equal to this value
+            will be included in the output. If set to None,
+            no maximum area constraint will be applied.
 
     Returns:
-        List[np.ndarray]: A new list of polygons containing only those with areas within the specified thresholds.
+        List[np.ndarray]: A new list of polygons containing only those with
+            areas within the specified thresholds.
     """
     if min_area is None and max_area is None:
         return polygons
@@ -213,7 +239,8 @@ def polygon_to_xyxy(polygon: np.ndarray) -> np.ndarray:
             containing the `x`, `y` coordinates of the points.
 
     Returns:
-        np.ndarray: A 1D NumPy array containing the bounding box `(x_min, y_min, x_max, y_max)` of the input polygon.
+        np.ndarray: A 1D NumPy array containing the bounding box
+            `(x_min, y_min, x_max, y_max)` of the input polygon.
     """
     x_min, y_min = np.min(polygon, axis=0)
     x_max, y_max = np.max(polygon, axis=0)
@@ -226,16 +253,23 @@ def approximate_polygon(
     """
     Approximates a given polygon by reducing a certain percentage of points.
 
-    This function uses the Ramer-Douglas-Peucker algorithm to simplify the input polygon by reducing the number of points
-    while preserving the general shape.
+    This function uses the Ramer-Douglas-Peucker algorithm to simplify the input
+        polygon by reducing the number of points
+        while preserving the general shape.
 
     Parameters:
-        polygon (np.ndarray): A 2D NumPy array of shape `(N, 2)` containing the `x`, `y` coordinates of the input polygon's points.
-        percentage (float): The percentage of points to be removed from the input polygon, in the range `[0, 1)`.
-        epsilon_step (float): Approximation accuracy step. Epsilon is the maximum distance between the original curve and its approximation.
+        polygon (np.ndarray): A 2D NumPy array of shape `(N, 2)` containing
+            the `x`, `y` coordinates of the input polygon's points.
+        percentage (float): The percentage of points to be removed from the
+            input polygon, in the range `[0, 1)`.
+        epsilon_step (float): Approximation accuracy step.
+            Epsilon is the maximum distance between the original curve
+            and its approximation.
 
     Returns:
-        np.ndarray: A new 2D NumPy array of shape `(M, 2)`, where `M <= N * (1 - percentage)`, containing the `x`, `y` coordinates of the
+        np.ndarray: A new 2D NumPy array of shape `(M, 2)`,
+            where `M <= N * (1 - percentage)`, containing
+            the `x`, `y` coordinates of the
             approximated polygon's points.
     """
 
@@ -321,23 +355,37 @@ def process_roboflow_result(
         x_max = x_min + width
         y_max = y_min + height
 
-        xyxy.append([x_min, y_min, x_max, y_max])
-        class_id.append(class_list.index(prediction["class"]))
-        confidence.append(prediction["confidence"])
-
         if "points" not in prediction:
-            continue
+            xyxy.append([x_min, y_min, x_max, y_max])
+            class_id.append(class_list.index(prediction["class"]))
+            confidence.append(prediction["confidence"])
+        elif len(prediction["points"]) >= 3:
+            polygon = np.array(
+                [[point["x"], point["y"]] for point in prediction["points"]], dtype=int
+            )
+            mask = polygon_to_mask(polygon, resolution_wh=(image_width, image_height))
+            xyxy.append([x_min, y_min, x_max, y_max])
+            class_id.append(class_list.index(prediction["class"]))
+            confidence.append(prediction["confidence"])
+            masks.append(mask)
 
-        polygon = np.array(
-            [[point["x"], point["y"]] for point in prediction["points"]], dtype=int
-        )
-
-        mask = polygon_to_mask(polygon, resolution_wh=(image_width, image_height))
-        masks.append(mask)
-
-    xyxy = np.array(xyxy)
-    confidence = np.array(confidence)
-    class_id = np.array(class_id).astype(int)
+    xyxy = np.array(xyxy) if len(xyxy) > 0 else np.empty((0, 4))
+    confidence = np.array(confidence) if len(confidence) > 0 else np.empty(0)
+    class_id = np.array(class_id).astype(int) if len(class_id) > 0 else np.empty(0)
     masks = np.array(masks, dtype=bool) if len(masks) > 0 else None
 
     return xyxy, confidence, class_id, masks
+
+
+def move_boxes(xyxy: np.ndarray, offset: np.ndarray) -> np.ndarray:
+    """
+    Args:
+        xyxy (np.ndarray): An array of shape `(n, 4)` containing the bounding boxes
+            coordinates in format `[x1, y1, x2, y2]`
+        offset (np.array): An array of shape `(2,)` containing offset values in format
+            is `[dx, dy]`.
+
+    Returns:
+        (np.ndarray) repositioned bounding boxes
+    """
+    return xyxy + np.hstack([offset, offset])

supervision/draw/color.py

@@ -42,7 +42,8 @@ class Color:
         """
         Creates a Color instance from a color hex string
 
-        :param color_hex: str : The color hex string in the format of "fff", "ffffff", "#fff", or "#ffffff"
+        :param color_hex: str : The color hex string in the format
+            of "fff", "ffffff", "#fff", or "#ffffff"
         :return: Color : A Color instance representing the color
 
         Example:
@@ -105,7 +106,8 @@ class ColorPalette:
         """
         Creates a ColorPalette instance from a list of color hex strings
 
-        :param color_hex_list: List[str] : A list of color hex strings in the format of "fff", "ffffff", "#fff", or "#ffffff"
+        :param color_hex_list: List[str] : A list of color hex strings in the
+            format of "fff", "ffffff", "#fff", or "#ffffff"
         :return: ColorPalette : A ColorPalette instance representing the color palette
 
         Example:

supervision/draw/utils.py

@@ -115,15 +115,19 @@ def draw_text(
     Draw text with background on a scene.
 
     Parameters:
-        scene (np.ndarray): A 2-dimensional numpy ndarray representing an image or scene.
+        scene (np.ndarray): A 2-dimensional numpy ndarray representing an image or scene
         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_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 when drawing a rectangle in the background. Defaults to 10.
-        text_font (int, optional): The font to use for the text. Defaults to cv2.FONT_HERSHEY_SIMPLEX.
-        background_color (Color, optional): The color of the background rectangle, if one is to be drawn. Defaults to None.
+        text_padding (int, optional): 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.
+            Defaults to cv2.FONT_HERSHEY_SIMPLEX.
+        background_color (Color, optional): The color of the background rectangle,
+            if one is to be drawn. Defaults to None.
 
     Returns:
         np.ndarray: The input scene with the text drawn on it.
@@ -132,7 +136,7 @@ def draw_text(
         ```python
         >>> scene = np.zeros((100, 100, 3), dtype=np.uint8)
         >>> text_anchor = Point(x=50, y=50)
-        >>> scene = draw_text(scene=scene, text="Hello, world!", text_anchor=text_anchor)
+        >>> scene = draw_text(scene=scene, text="Hello, world!",text_anchor=text_anchor)
         ```
     """
     text_width, text_height = cv2.getTextSize(

supervision/geometry/utils.py

@@ -7,13 +7,18 @@ def get_polygon_center(polygon: np.ndarray) -> Point:
     """
     Calculate the center of a polygon.
 
-    This function takes in a polygon as a 2-dimensional numpy ndarray and returns the center of the polygon as a Point object. The center is calculated as the mean of the polygon's vertices along each axis, and is rounded down to the nearest integer.
+    This function takes in a polygon as a 2-dimensional numpy ndarray and
+    returns the center of the polygon as a Point object.
+    The center is calculated as the mean of the polygon's vertices along each axis,
+    and is rounded down to the nearest integer.
 
     Parameters:
-        polygon (np.ndarray): A 2-dimensional numpy ndarray representing the vertices of the polygon.
+        polygon (np.ndarray): A 2-dimensional numpy ndarray representing the
+            vertices of the polygon.
 
     Returns:
-        Point: The center of the polygon, represented as a Point object with x and y attributes.
+        Point: The center of the polygon, represented as a
+            Point object with x and y attributes.
 
     Examples:
         ```python

supervision/metrics/detection.py

@@ -21,7 +21,8 @@ def detections_to_tensor(
         detections (sv.Detections): Detections/Targets in the format of sv.Detections
         with_confidence (bool): Whether to include confidence in the tensor
     Returns:
-        (np.ndarray): Detections as numpy tensors as in (xyxy, class_id, confidence) order
+        (np.ndarray): Detections as numpy tensors as in (xyxy, class_id,
+            confidence) order
     """
     if detections.class_id is None:
         raise ValueError(
@@ -46,18 +47,21 @@ def validate_input_tensors(predictions: List[np.ndarray], targets: List[np.ndarr
     """
     if len(predictions) != len(targets):
         raise ValueError(
-            f"Number of predictions ({len(predictions)}) and targets ({len(targets)}) must be equal."
+            f"Number of predictions ({len(predictions)}) and"
+            f"targets ({len(targets)}) must be equal."
         )
     if len(predictions) > 0:
         if not isinstance(predictions[0], np.ndarray) or not isinstance(
             targets[0], np.ndarray
         ):
             raise ValueError(
-                f"Predictions and targets must be lists of numpy arrays. Got {type(predictions[0])} and {type(targets[0])} instead."
+                f"Predictions and targets must be lists of numpy arrays."
+                f"Got {type(predictions[0])} and {type(targets[0])} instead."
             )
         if predictions[0].shape[1] != 6:
             raise ValueError(
-                f"Predictions must have shape (N, 6). Got {predictions[0].shape} instead."
+                f"Predictions must have shape (N, 6)."
+                f"Got {predictions[0].shape} instead."
             )
         if targets[0].shape[1] != 5:
             raise ValueError(
@@ -71,10 +75,14 @@ class ConfusionMatrix:
     Confusion matrix for object detection tasks.
 
     Attributes:
-        matrix (np.ndarray): An 2D `np.ndarray` of shape `(len(classes) + 1, len(classes) + 1)` containing the number of `TP`, `FP`, `FN` and `TN` for each class.
+        matrix (np.ndarray): An 2D `np.ndarray` of shape
+            `(len(classes) + 1, len(classes) + 1)`
+            containing the number of `TP`, `FP`, `FN` and `TN` for each class.
         classes (List[str]): Model class names.
-        conf_threshold (float): Detection confidence threshold between `0` and `1`. Detections with lower confidence will be excluded from the matrix.
-        iou_threshold (float): Detection IoU threshold between `0` and `1`. Detections with lower IoU will be classified as `FP`.
+        conf_threshold (float): Detection confidence threshold between `0` and `1`.
+            Detections with lower confidence will be excluded from the matrix.
+        iou_threshold (float): Detection IoU threshold between `0` and `1`.
+            Detections with lower IoU will be classified as `FP`.
     """
 
     matrix: np.ndarray
@@ -98,8 +106,10 @@ class ConfusionMatrix:
             targets (List[Detections]): Detections objects from ground-truth.
             predictions (List[Detections]): Detections objects predicted by the model.
             classes (List[str]): Model class names.
-            conf_threshold (float): Detection confidence threshold between `0` and `1`. Detections with lower confidence will be excluded.
-            iou_threshold (float): Detection IoU threshold between `0` and `1`. Detections with lower IoU will be classified as `FP`.
+            conf_threshold (float): Detection confidence threshold between `0` and `1`.
+                Detections with lower confidence will be excluded.
+            iou_threshold (float): Detection IoU threshold between `0` and `1`.
+                Detections with lower IoU will be classified as `FP`.
 
         Returns:
             ConfusionMatrix: New instance of ConfusionMatrix.
@@ -162,11 +172,19 @@ class ConfusionMatrix:
         Calculate confusion matrix based on predicted and ground-truth detections.
 
         Args:
-            predictions (List[np.ndarray]): Each element of the list describes a single image and has `shape = (M, 6)` where `M` is the number of detected objects. Each row is expected to be in `(x_min, y_min, x_max, y_max, class, conf)` format.
-            targets (List[np.ndarray]): Each element of the list describes a single image and has `shape = (N, 5)` where `N` is the number of ground-truth objects. Each row is expected to be in `(x_min, y_min, x_max, y_max, class)` format.
+            predictions (List[np.ndarray]): Each element of the list describes a single
+                image and has `shape = (M, 6)` where `M` is the number of detected
+                objects. Each row is expected to be in
+                `(x_min, y_min, x_max, y_max, class, conf)` format.
+            targets (List[np.ndarray]): Each element of the list describes a single
+                image and has `shape = (N, 5)` where `N` is the number of
+                ground-truth objects. Each row is expected to be in
+                `(x_min, y_min, x_max, y_max, class)` format.
             classes (List[str]): Model class names.
-            conf_threshold (float): Detection confidence threshold between `0` and `1`. Detections with lower confidence will be excluded.
-            iou_threshold (float): Detection iou  threshold between `0` and `1`. Detections with lower iou will be classified as `FP`.
+            conf_threshold (float): Detection confidence threshold between `0` and `1`.
+                Detections with lower confidence will be excluded.
+            iou_threshold (float): Detection iou  threshold between `0` and `1`.
+                Detections with lower iou will be classified as `FP`.
 
         Returns:
             ConfusionMatrix: New instance of ConfusionMatrix.
@@ -246,11 +264,19 @@ class ConfusionMatrix:
         Calculate confusion matrix for a batch of detections for a single image.
 
         Args:
-            predictions (np.ndarray): Batch prediction. Describes a single image and has `shape = (M, 6)` where `M` is the number of detected objects. Each row is expected to be in `(x_min, y_min, x_max, y_max, class, conf)` format.
-            targets (np.ndarray): Batch target labels. Describes a single image and has `shape = (N, 5)` where `N` is the number of ground-truth objects. Each row is expected to be in `(x_min, y_min, x_max, y_max, class)` format.
+            predictions (np.ndarray): Batch prediction. Describes a single image and
+                has `shape = (M, 6)` where `M` is the number of detected objects.
+                Each row is expected to be in
+                `(x_min, y_min, x_max, y_max, class, conf)` format.
+            targets (np.ndarray): Batch target labels. Describes a single image and
+                has `shape = (N, 5)` where `N` is the number of ground-truth objects.
+                Each row is expected to be in
+                `(x_min, y_min, x_max, y_max, class)` format.
             num_classes (int): Number of classes.
-            conf_threshold (float): Detection confidence threshold between `0` and `1`. Detections with lower confidence will be excluded.
-            iou_threshold (float): Detection iou  threshold between `0` and `1`. Detections with lower iou will be classified as `FP`.
+            conf_threshold (float): Detection confidence threshold between `0` and `1`.
+                Detections with lower confidence will be excluded.
+            iou_threshold (float): Detection iou  threshold between `0` and `1`.
+                Detections with lower iou will be classified as `FP`.
 
         Returns:
             np.ndarray: Confusion matrix based on a single image.
@@ -304,8 +330,8 @@ class ConfusionMatrix:
     @staticmethod
     def _drop_extra_matches(matches: np.ndarray) -> np.ndarray:
         """
-        Deduplicate matches. If there are multiple matches for the same true or predicted box,
-        only the one with the highest IoU is kept.
+        Deduplicate matches. If there are multiple matches for the same true or
+        predicted box, only the one with the highest IoU is kept.
         """
         if matches.shape[0] > 0:
             matches = matches[matches[:, 2].argsort()[::-1]]
@@ -327,9 +353,12 @@ class ConfusionMatrix:
 
         Args:
             dataset (DetectionDataset): Object detection dataset used for evaluation.
-            callback (Callable[[np.ndarray], Detections]): Function that takes an image as input and returns Detections object.
-            conf_threshold (float): Detection confidence threshold between `0` and `1`. Detections with lower confidence will be excluded.
-            iou_threshold (float): Detection IoU threshold between `0` and `1`. Detections with lower IoU will be classified as `FP`.
+            callback (Callable[[np.ndarray], Detections]): Function that takes an image
+                as input and returns Detections object.
+            conf_threshold (float): Detection confidence threshold between `0` and `1`.
+                Detections with lower confidence will be excluded.
+            iou_threshold (float): Detection IoU threshold between `0` and `1`.
+                Detections with lower IoU will be classified as `FP`.
 
         Returns:
             ConfusionMatrix: New instance of ConfusionMatrix.
@@ -344,7 +373,7 @@ class ConfusionMatrix:
             >>> model = YOLO(...)
             >>> def callback(image: np.ndarray) -> sv.Detections:
             ...     result = model(image)[0]
-            ...     return sv.Detections.from_yolov8(result)
+            ...     return sv.Detections.from_ultralytics(result)
 
             >>> confusion_matrix = sv.ConfusionMatrix.benchmark(
             ...     dataset = dataset,
@@ -386,9 +415,11 @@ class ConfusionMatrix:
         Create confusion matrix plot and save it at selected location.
 
         Args:
-            save_path (Optional[str]): Path to save the plot. If not provided, plot will be displayed.
+            save_path (Optional[str]): Path to save the plot. If not provided,
+                plot will be displayed.
             title (Optional[str]): Title of the plot.
-            classes (Optional[List[str]]): List of classes to be displayed on the plot. If not provided, all classes will be displayed.
+            classes (Optional[List[str]]): List of classes to be displayed on the plot.
+                If not provided, all classes will be displayed.
             normalize (bool): If True, normalize the confusion matrix.
             fig_size (Tuple[int, int]): Size of the plot.
 
@@ -468,10 +499,15 @@ class MeanAveragePrecision:
     Mean Average Precision for object detection tasks.
 
     Attributes:
-        map50_95 (float): Mean Average Precision (mAP) calculated over IoU thresholds ranging from `0.50` to `0.95` with a step size of `0.05`.
-        map50 (float): Mean Average Precision (mAP) calculated specifically at an IoU threshold of `0.50`.
-        map75 (float): Mean Average Precision (mAP) calculated specifically at an IoU threshold of `0.75`.
-        per_class_ap50_95 (np.ndarray): Average Precision (AP) values calculated over IoU thresholds ranging from `0.50` to `0.95` with a step size of `0.05`, provided for each individual class.
+        map50_95 (float): Mean Average Precision (mAP) calculated over IoU thresholds
+            ranging from `0.50` to `0.95` with a step size of `0.05`.
+        map50 (float): Mean Average Precision (mAP) calculated specifically at
+            an IoU threshold of `0.50`.
+        map75 (float): Mean Average Precision (mAP) calculated specifically at
+            an IoU threshold of `0.75`.
+        per_class_ap50_95 (np.ndarray): Average Precision (AP) values calculated over
+            IoU thresholds ranging from `0.50` to `0.95` with a step size of `0.05`,
+            provided for each individual class.
     """
 
     map50_95: float
@@ -540,7 +576,8 @@ class MeanAveragePrecision:
 
         Args:
             dataset (DetectionDataset): Object detection dataset used for evaluation.
-            callback (Callable[[np.ndarray], Detections]): Function that takes an image as input and returns Detections object.
+            callback (Callable[[np.ndarray], Detections]): Function that takes
+                an image as input and returns Detections object.
         Returns:
             MeanAveragePrecision: New instance of MeanAveragePrecision.
 
@@ -554,7 +591,7 @@ class MeanAveragePrecision:
             >>> model = YOLO(...)
             >>> def callback(image: np.ndarray) -> sv.Detections:
             ...     result = model(image)[0]
-            ...     return sv.Detections.from_yolov8(result)
+            ...     return sv.Detections.from_ultralytics(result)
 
             >>> mean_average_precision = sv.MeanAveragePrecision.benchmark(
             ...     dataset = dataset,
@@ -583,11 +620,18 @@ class MeanAveragePrecision:
         targets: List[np.ndarray],
     ) -> MeanAveragePrecision:
         """
-        Calculate Mean Average Precision based on predicted and ground-truth detections at different threshold.
+        Calculate Mean Average Precision based on predicted and ground-truth
+            detections at different threshold.
 
         Args:
-            predictions (List[np.ndarray]): Each element of the list describes a single image and has `shape = (M, 6)` where `M` is the number of detected objects. Each row is expected to be in `(x_min, y_min, x_max, y_max, class, conf)` format.
-            targets (List[np.ndarray]): Each element of the list describes a single image and has `shape = (N, 5)` where `N` is the number of ground-truth objects. Each row is expected to be in `(x_min, y_min, x_max, y_max, class)` format.
+            predictions (List[np.ndarray]): Each element of the list describes
+                a single image and has `shape = (M, 6)` where `M` is
+                the number of detected objects. Each row is expected to be
+                in `(x_min, y_min, x_max, y_max, class, conf)` format.
+            targets (List[np.ndarray]): Each element of the list describes a single
+                image and has `shape = (N, 5)` where `N` is the
+                number of ground-truth objects. Each row is expected to be in
+                `(x_min, y_min, x_max, y_max, class)` format.
         Returns:
             MeanAveragePrecision: New instance of MeanAveragePrecision.
 
@@ -680,7 +724,8 @@ class MeanAveragePrecision:
     @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.
+        Compute the average precision using 101-point interpolation (COCO), given
+            the recall and precision curves.
 
         Args:
             recall (np.ndarray): The recall curve.
@@ -709,8 +754,14 @@ class MeanAveragePrecision:
         Match predictions with target labels based on IoU levels.
 
         Args:
-            predictions (np.ndarray): Batch prediction. Describes a single image and has `shape = (M, 6)` where `M` is the number of detected objects. Each row is expected to be in `(x_min, y_min, x_max, y_max, class, conf)` format.
-            targets (np.ndarray): Batch target labels. Describes a single image and has `shape = (N, 5)` where `N` is the number of ground-truth objects. Each row is expected to be in `(x_min, y_min, x_max, y_max, class)` format.
+            predictions (np.ndarray): Batch prediction. Describes a single image and
+                has `shape = (M, 6)` where `M` is the number of detected objects.
+                Each row is expected to be in
+                `(x_min, y_min, x_max, y_max, class, conf)` format.
+            targets (np.ndarray): Batch target labels. Describes a single image and
+                has `shape = (N, 5)` where `N` is the number of ground-truth objects.
+                Each row is expected to be in
+                `(x_min, y_min, x_max, y_max, class)` format.
             iou_thresholds (np.ndarray): Array contains different IoU thresholds.
 
         Returns:

supervision/tracker/byte_tracker/core.py

@@ -33,13 +33,16 @@ class STrack(BaseTrack):
     @staticmethod
     def multi_predict(stracks):
         if len(stracks) > 0:
-            multi_mean = np.asarray([st.mean.copy() for st in stracks])
-            multi_covariance = np.asarray([st.covariance for st in stracks])
+            multi_mean = []
+            multi_covariance = []
             for i, st in enumerate(stracks):
+                multi_mean.append(st.mean.copy())
+                multi_covariance.append(st.covariance)
                 if st.state != TrackState.Tracked:
                     multi_mean[i][7] = 0
+
             multi_mean, multi_covariance = STrack.shared_kalman.multi_predict(
-                multi_mean, multi_covariance
+                np.asarray(multi_mean), np.asarray(multi_covariance)
             )
             for i, (mean, cov) in enumerate(zip(multi_mean, multi_covariance)):
                 stracks[i].mean = mean
@@ -148,7 +151,8 @@ def detections2boxes(detections: Detections) -> np.ndarray:
     Args:
         detections (Detections): Detections/Targets in the format of sv.Detections.
     Returns:
-        (np.ndarray): Detections as numpy tensors as in `(x_min, y_min, x_max, y_max, confidence, class_id)` order.
+        (np.ndarray): Detections as numpy tensors as in
+            `(x_min, y_min, x_max, y_max, confidence, class_id)` order.
     """
     return np.hstack(
         (
@@ -164,7 +168,8 @@ class ByteTrack:
     Initialize the ByteTrack object.
 
     Parameters:
-        track_thresh (float, optional): Detection confidence threshold for track activation.
+        track_thresh (float, optional): Detection confidence threshold
+            for track activation.
         track_buffer (int, optional): Number of frames to buffer when a track is lost.
         match_thresh (float, optional): Threshold for matching tracks with detections.
         frame_rate (int, optional): The frame rate of the video.
@@ -191,7 +196,8 @@ class ByteTrack:
 
     def update_with_detections(self, detections: Detections) -> Detections:
         """
-        Updates the tracker with the provided detections and returns the updated detection results.
+        Updates the tracker with the provided detections and
+            returns the updated detection results.
 
         Parameters:
             detections: The new detections to update with.
@@ -208,14 +214,15 @@ class ByteTrack:
 
             >>> def callback(frame: np.ndarray, index: int) -> np.ndarray:
             ...     results = model(frame)[0]
-            ...     detections = sv.Detections.from_yolov8(results)
-            ...     detections = byte_tracker.update_from_detections(detections=detections)
+            ...     detections = sv.Detections.from_ultralytics(results)
+            ...     detections = byte_tracker.update_with_detections(detections)
             ...     labels = [
             ...         f"#{tracker_id} {model.model.names[class_id]} {confidence:0.2f}"
             ...         for _, _, confidence, class_id, tracker_id
             ...         in detections
             ...     ]
-            ...     return annotator.annotate(scene=frame.copy(), detections=detections, labels=labels)
+            ...     return annotator.annotate(scene=frame.copy(),
+            ...                               detections=detections, labels=labels)
 
             >>> sv.process_video(
             ...     source_path='...',
@@ -410,7 +417,8 @@ def joint_tracks(
         track_list_b: Second list of tracks (with track_id attribute).
 
     Returns:
-        Combined list of tracks from track_list_a and track_list_b without duplicate track_id values.
+        Combined list of tracks from track_list_a and track_list_b
+            without duplicate track_id values.
     """
     seen_track_ids = set()
     result = []
@@ -430,7 +438,8 @@ def sub_tracks(track_list_a: List, track_list_b: List) -> List[int]:
 
     Parameters:
         track_list_a: List of tracks (with track_id attribute).
-        track_list_b: List of tracks (with track_id attribute) to be subtracted from track_list_a.
+        track_list_b: List of tracks (with track_id attribute) to
+            be subtracted from track_list_a.
     Returns:
         List of remaining tracks from track_list_a after subtraction.
     """

supervision/tracker/byte_tracker/kalman_filter.py

@@ -35,10 +35,13 @@ class KalmanFilter:
         Create track from an unassociated measurement.
 
         Args:
-            measurement (ndarray): Bounding box coordinates (x, y, a, h) with center position (x, y), aspect ratio a, and height h.
+            measurement (ndarray): Bounding box coordinates (x, y, a, h) with
+                center position (x, y), aspect ratio a, and height h.
 
         Returns:
-            Tuple[ndarray, ndarray]: Returns the mean vector (8 dimensional) and covariance matrix (8x8 dimensional) of the new track. Unobserved velocities are initialized to 0 mean.
+            Tuple[ndarray, ndarray]: Returns the mean vector (8 dimensional) and
+                covariance matrix (8x8 dimensional) of the new track.
+                Unobserved velocities are initialized to 0 mean.
         """
         mean_pos = measurement
         mean_vel = np.zeros_like(mean_pos)
@@ -64,11 +67,15 @@ class KalmanFilter:
         Run Kalman filter prediction step.
 
         Args:
-            mean (ndarray): The 8 dimensional mean vector of the object state at the previous time step.
-            covariance (ndarray): The 8x8 dimensional covariance matrix of the object state at the previous time step.
+            mean (ndarray): The 8 dimensional mean vector of the object
+                state at the previous time step.
+            covariance (ndarray): The 8x8 dimensional covariance matrix of
+                the object state at the previous time step.
 
         Returns:
-            Tuple[ndarray, ndarray]: Returns the mean vector and covariance matrix of the predicted state. Unobserved velocities are initialized to 0 mean.
+            Tuple[ndarray, ndarray]: Returns the mean vector and
+                covariance matrix of the predicted state.
+                Unobserved velocities are initialized to 0 mean.
         """
         std_pos = [
             self._std_weight_position * mean[3],
@@ -103,7 +110,8 @@ class KalmanFilter:
             covariance (ndarray): The state's covariance matrix (8x8 dimensional).
 
         Returns:
-            Tuple[ndarray, ndarray]: Returns the projected mean and covariance matrix of the given state estimate.
+            Tuple[ndarray, ndarray]: Returns the projected mean and
+                covariance matrix of the given state estimate.
         """
         std = [
             self._std_weight_position * mean[3],
@@ -126,11 +134,15 @@ class KalmanFilter:
         Run Kalman filter prediction step (Vectorized version).
 
         Args:
-            mean (ndarray): The Nx8 dimensional mean matrix of the object states at the previous time step.
-            covariance (ndarray): The Nx8x8 dimensional covariance matrices of the object states at the previous time step.
+            mean (ndarray): The Nx8 dimensional mean matrix
+                of the object states at the previous time step.
+            covariance (ndarray): The Nx8x8 dimensional covariance matrices
+                of the object states at the previous time step.
 
         Returns:
-            Tuple[ndarray, ndarray]: Returns the mean vector and covariance matrix of the predicted state. Unobserved velocities are initialized to 0 mean.
+            Tuple[ndarray, ndarray]: Returns the mean vector and
+                covariance matrix of the predicted state.
+                Unobserved velocities are initialized to 0 mean.
         """
         std_pos = [
             self._std_weight_position * mean[:, 3],
@@ -166,10 +178,13 @@ class KalmanFilter:
         Args:
             mean (ndarray): The predicted state's mean vector (8 dimensional).
             covariance (ndarray): The state's covariance matrix (8x8 dimensional).
-            measurement (ndarray): The 4-dimensional measurement vector (x, y, a, h), where (x, y) is the center position, a the aspect ratio, and h the height of the bounding box.
+            measurement (ndarray): The 4-dimensional measurement vector (x, y, a, h),
+                where (x, y) is the center position, a the aspect ratio,
+                and h the height of the bounding box.
 
         Returns:
-            Tuple[ndarray, ndarray]: Returns the measurement-corrected state distribution.
+            Tuple[ndarray, ndarray]: Returns the measurement-corrected
+                state distribution.
         """
         projected_mean, projected_cov = self.project(mean, covariance)
 

supervision/utils/file.py

@@ -21,11 +21,13 @@ def list_files_with_extensions(
     directory: Union[str, Path], extensions: Optional[List[str]] = None
 ) -> List[Path]:
     """
-    List files in a directory with specified extensions or all files if no extensions are provided.
+    List files in a directory with specified extensions or
+        all files if no extensions are provided.
 
     Args:
         directory (Union[str, Path]): The directory path as a string or Path object.
-        extensions (Optional[List[str]]): A list of file extensions to filter. Default is None, which lists all files.
+        extensions (Optional[List[str]]): A list of file extensions to filter.
+            Default is None, which lists all files.
 
     Returns:
         (List[Path]): A list of Path objects for the matching files.
@@ -38,9 +40,11 @@ def list_files_with_extensions(
         >>> files = sv.list_files_with_extensions(directory='my_directory')
 
         >>> # List only files with '.txt' and '.md' extensions
-        >>> files = sv.list_files_with_extensions(directory='my_directory', extensions=['txt', 'md'])
+        >>> files = sv.list_files_with_extensions(
+        ...     directory='my_directory', extensions=['txt', 'md'])
         ```
     """
+
     directory = Path(directory)
     files_with_extensions = []
 

supervision/utils/image.py

@@ -6,13 +6,14 @@ import cv2
 import numpy as np
 
 
-def crop(image: np.ndarray, xyxy: np.ndarray) -> np.ndarray:
+def crop_image(image: np.ndarray, xyxy: np.ndarray) -> np.ndarray:
     """
     Crops the given image based on the given bounding box.
 
     Args:
         image (np.ndarray): The image to be cropped, represented as a numpy array.
-        xyxy (np.ndarray): A numpy array containing the bounding box coordinates in the format (x1, y1, x2, y2).
+        xyxy (np.ndarray): A numpy array containing the bounding box coordinates
+            in the format (x1, y1, x2, y2).
 
     Returns:
         (np.ndarray): The cropped image as a numpy array.
@@ -24,7 +25,7 @@ def crop(image: np.ndarray, xyxy: np.ndarray) -> np.ndarray:
         >>> detection = sv.Detections(...)
         >>> with sv.ImageSink(target_dir_path='target/directory/path') as sink:
         ...     for xyxy in detection.xyxy:
-        ...         cropped_image = sv.crop(image=image, xyxy=xyxy)
+        ...         cropped_image = sv.crop_image(image=image, xyxy=xyxy)
         ...         sink.save_image(image=image)
         ```
     """
@@ -47,18 +48,23 @@ class ImageSink:
 
         Args:
             target_dir_path (str): The target directory where images will be saved.
-            overwrite (bool, optional): Whether to overwrite the existing directory. Defaults to False.
-            image_name_pattern (str, optional): The image file name pattern. Defaults to "image_{:05d}.png".
+            overwrite (bool, optional): Whether to overwrite the existing directory.
+                Defaults to False.
+            image_name_pattern (str, optional): The image file name pattern.
+                Defaults to "image_{:05d}.png".
 
         Examples:
             ```python
             >>> import supervision as sv
 
-            >>> with sv.ImageSink(target_dir_path='target/directory/path', overwrite=True) as sink:
-            ...     for image in sv.get_video_frames_generator(source_path='source_video.mp4', stride=2):
+            >>> with sv.ImageSink(target_dir_path='target/directory/path',
+            ...                   overwrite=True) as sink:
+            ...     for image in sv.get_video_frames_generator(
+            ...         source_path='source_video.mp4', stride=2):
             ...         sink.save_image(image=image)
             ```
         """
+
         self.target_dir_path = target_dir_path
         self.overwrite = overwrite
         self.image_name_pattern = image_name_pattern
@@ -80,7 +86,9 @@ class ImageSink:
 
         Args:
             image (np.ndarray): The image to be saved.
-            image_name (str, optional): The name to use for the saved image. If not provided, a name will be generated using the `image_name_pattern`.
+            image_name (str, optional): The name to use for the saved image.
+                If not provided, a name will be
+                generated using the `image_name_pattern`.
         """
         if image_name is None:
             image_name = self.image_name_pattern.format(self.image_count)

supervision/utils/notebook.py

@@ -50,9 +50,12 @@ def plot_images_grid(
 
     Args:
        images (List[np.ndarray]): A list of images as numpy arrays.
-       grid_size (Tuple[int, int]): A tuple specifying the number of rows and columns for the grid.
-       titles (Optional[List[str]]): A list of titles for each image. Defaults to None.
-       size (Tuple[int, int]): A tuple specifying the width and height of the entire plot in inches.
+       grid_size (Tuple[int, int]): A tuple specifying the number
+            of rows and columns for the grid.
+       titles (Optional[List[str]]): A list of titles for each image.
+            Defaults to None.
+       size (Tuple[int, int]): A tuple specifying the width and
+            height of the entire plot in inches.
        cmap (str): the colormap to use for single channel images.
 
     Raises:
@@ -78,7 +81,8 @@ def plot_images_grid(
 
     if len(images) > nrows * ncols:
         raise ValueError(
-            "The number of images exceeds the grid size. Please increase the grid size or reduce the number of images."
+            "The number of images exceeds the grid size. Please increase the grid size"
+            " or reduce the number of images."
         )
 
     fig, axes = plt.subplots(nrows=nrows, ncols=ncols, figsize=size)

supervision/utils/video.py

@@ -10,13 +10,15 @@ import numpy as np
 @dataclass
 class VideoInfo:
     """
-    A class to store video information, including width, height, fps and total number of frames.
+    A class to store video information, including width, height, fps and
+        total number of frames.
 
     Attributes:
         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, default is None
+        total_frames (int, optional): total number of frames in the video,
+            default is None
 
     Examples:
         ```python
@@ -61,7 +63,8 @@ class VideoSink:
 
     Attributes:
         target_path (str): The path to the output file where the video will be saved.
-        video_info (VideoInfo): Information about the video resolution, fps, and total frame count.
+        video_info (VideoInfo): Information about the video resolution, fps,
+            and total frame count.
 
     Example:
         ```python
@@ -69,8 +72,10 @@ class VideoSink:
 
         >>> video_info = sv.VideoInfo.from_video_path(video_path='source_video.mp4')
 
-        >>> with sv.VideoSink(target_path='target_video.mp4', video_info=video_info) as sink:
-        ...     for frame in get_video_frames_generator(source_path='source_video.mp4', stride=2):
+        >>> with sv.VideoSink(target_path='target_video.mp4',
+        ...                   video_info=video_info) as sink:
+        ...     for frame in get_video_frames_generator(source_path='source_video.mp4',
+        ...                                             stride=2):
         ...         sink.write_frame(frame=frame)
         ```
     """
@@ -103,7 +108,7 @@ def _validate_and_setup_video(source_path: str, start: int, end: Optional[int]):
         raise Exception(f"Could not open video at {source_path}")
     total_frames = int(video.get(cv2.CAP_PROP_FRAME_COUNT))
     if end is not None and end > total_frames:
-        raise Exception(f"Requested frames are outbound")
+        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)
@@ -118,12 +123,16 @@ def get_video_frames_generator(
 
     Args:
         source_path (str): The path of the video file.
-        stride (int): Indicates the interval at which frames are returned, skipping stride - 1 frames between each.
-        start (int): Indicates the starting position from which 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.
+        stride (int): Indicates the interval at which frames are returned,
+            skipping stride - 1 frames between each.
+        start (int): Indicates the starting position from which
+            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.
 
     Returns:
-        (Generator[np.ndarray, None, None]): A generator that yields the frames of the video.
+        (Generator[np.ndarray, None, None]): A generator that yields the
+            frames of the video.
 
     Examples:
         ```python
@@ -154,12 +163,16 @@ def process_video(
     callback: Callable[[np.ndarray, int], np.ndarray],
 ) -> None:
     """
-    Process a video file by applying a callback function on each frame and saving the result to a target video file.
+    Process a video file by applying a callback function on each frame
+        and saving the result to a target video file.
 
     Args:
         source_path (str): The path to the source video file.
         target_path (str): The path to the target video file.
-        callback (Callable[[np.ndarray, int], np.ndarray]): A function that takes in a numpy ndarray representation of a video frame and an int index of the frame and returns a processed numpy ndarray representation of the frame.
+        callback (Callable[[np.ndarray, int], np.ndarray]): A function that takes in
+            a numpy ndarray representation of a video frame and an
+            int index of the frame and returns a processed numpy ndarray
+            representation of the frame.
 
     Examples:
         ```python

test/classification/test_core.py

@@ -1,8 +1,8 @@
-from typing import List, Optional, Tuple
 from contextlib import ExitStack as DoesNotRaise
+from typing import Optional, Tuple
 
-import pytest
 import numpy as np
+import pytest
 
 from supervision.classification.core import Classifications
 

test/dataset/formats/test_coco.py

@@ -1,13 +1,17 @@
 from contextlib import ExitStack as DoesNotRaise
-from typing import List, Tuple, Dict
+from typing import Dict, List, Tuple
 
+import numpy as np
 import pytest
 
 from supervision import Detections
-from supervision.dataset.formats.coco import classes_to_coco_categories, coco_categories_to_classes, \
-    group_coco_annotations_by_image_id, coco_annotations_to_detections, build_coco_class_index_mapping
-
-import numpy as np
+from supervision.dataset.formats.coco import (
+    build_coco_class_index_mapping,
+    classes_to_coco_categories,
+    coco_annotations_to_detections,
+    coco_categories_to_classes,
+    group_coco_annotations_by_image_id,
+)
 
 
 def mock_cock_coco_annotation(
@@ -15,7 +19,7 @@ def mock_cock_coco_annotation(
     image_id: int = 0,
     category_id: int = 0,
     bbox: Tuple[float, float, float, float] = (0.0, 0.0, 0.0, 0.0),
-    area: float = 0.0
+    area: float = 0.0,
 ) -> dict:
     return {
         "id": annotation_id,
@@ -23,103 +27,52 @@ def mock_cock_coco_annotation(
         "category_id": category_id,
         "bbox": list(bbox),
         "area": area,
-        "iscrowd": 0
+        "iscrowd": 0,
     }
 
 
 @pytest.mark.parametrize(
     "coco_categories, expected_result, exception",
     [
+        ([], [], DoesNotRaise()),  # empty coco categories
         (
-            [],
-            [],
-            DoesNotRaise()
-        ),  # empty coco categories
-        (
-            [
-                {
-                    "id": 0,
-                    "name": "fashion-assistant",
-                    "supercategory": "none"
-                }
-            ],
+            [{"id": 0, "name": "fashion-assistant", "supercategory": "none"}],
             ["fashion-assistant"],
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # single coco category with supercategory == "none"
         (
             [
-                {
-                    "id": 0,
-                    "name": "fashion-assistant",
-                    "supercategory": "none"
-                },
-                {
-                    "id": 1,
-                    "name": "baseball cap",
-                    "supercategory": "fashion-assistant"
-                }
+                {"id": 0, "name": "fashion-assistant", "supercategory": "none"},
+                {"id": 1, "name": "baseball cap", "supercategory": "fashion-assistant"},
             ],
-            [
-                "fashion-assistant", "baseball cap"
-            ],
-            DoesNotRaise()
-        ),  # two coco categories; one with supercategory == "none" and one with supercategory != "none"
+            ["fashion-assistant", "baseball cap"],
+            DoesNotRaise(),
+        ),  # two coco categories; one with supercategory == "none" and
+        # one with supercategory != "none"
         (
             [
-                {
-                    "id": 0,
-                    "name": "fashion-assistant",
-                    "supercategory": "none"
-                },
-                {
-                    "id": 1,
-                    "name": "baseball cap",
-                    "supercategory": "fashion-assistant"
-                },
-                {
-                    "id": 2,
-                    "name": "hoodie",
-                    "supercategory": "fashion-assistant"
-                }
+                {"id": 0, "name": "fashion-assistant", "supercategory": "none"},
+                {"id": 1, "name": "baseball cap", "supercategory": "fashion-assistant"},
+                {"id": 2, "name": "hoodie", "supercategory": "fashion-assistant"},
             ],
-            [
-                "fashion-assistant",
-                "baseball cap",
-                "hoodie"
-            ],
-            DoesNotRaise()
-        ),  # three coco categories; one with supercategory == "none" and two with supercategory != "none"
+            ["fashion-assistant", "baseball cap", "hoodie"],
+            DoesNotRaise(),
+        ),  # three coco categories; one with supercategory == "none" and
+        # two with supercategory != "none"
         (
             [
-                {
-                    "id": 0,
-                    "name": "fashion-assistant",
-                    "supercategory": "none"
-                },
-                {
-                    "id": 2,
-                    "name": "hoodie",
-                    "supercategory": "fashion-assistant"
-                },
-                {
-                    "id": 1,
-                    "name": "baseball cap",
-                    "supercategory": "fashion-assistant"
-                }
+                {"id": 0, "name": "fashion-assistant", "supercategory": "none"},
+                {"id": 2, "name": "hoodie", "supercategory": "fashion-assistant"},
+                {"id": 1, "name": "baseball cap", "supercategory": "fashion-assistant"},
             ],
-            [
-                "fashion-assistant",
-                "baseball cap",
-                "hoodie"
-            ],
-            DoesNotRaise()
-        ),  # three coco categories; one with supercategory == "none" and two with supercategory != "none" (different order)
-    ]
+            ["fashion-assistant", "baseball cap", "hoodie"],
+            DoesNotRaise(),
+        ),  # three coco categories; one with supercategory == "none" and
+        # two with supercategory != "none" (different order)
+    ],
 )
 def test_coco_categories_to_classes(
-    coco_categories: List[dict],
-    expected_result: List[str],
-    exception: Exception
+    coco_categories: List[dict], expected_result: List[str], exception: Exception
 ) -> None:
     with exception:
         result = coco_categories_to_classes(coco_categories=coco_categories)
@@ -129,26 +82,14 @@ def test_coco_categories_to_classes(
 @pytest.mark.parametrize(
     "classes, exception",
     [
-        (
-            [],
-            DoesNotRaise()
-        ),  # empty classes
-        (
-            [
-                "baseball cap"
-            ],
-            DoesNotRaise()
-        ),  # single class
-        (
-            [
-                "baseball cap",
-                "hoodie"
-            ],
-            DoesNotRaise()
-        ),  # two classes
-    ]
+        ([], DoesNotRaise()),  # empty classes
+        (["baseball cap"], DoesNotRaise()),  # single class
+        (["baseball cap", "hoodie"], DoesNotRaise()),  # two classes
+    ],
 )
-def test_classes_to_coco_categories_and_back_to_classes(classes: List[str], exception: Exception) -> None:
+def test_classes_to_coco_categories_and_back_to_classes(
+    classes: List[str], exception: Exception
+) -> None:
     with exception:
         coco_categories = classes_to_coco_categories(classes=classes)
         result = coco_categories_to_classes(coco_categories=coco_categories)
@@ -158,36 +99,36 @@ def test_classes_to_coco_categories_and_back_to_classes(classes: List[str], exce
 @pytest.mark.parametrize(
     "coco_annotations, expected_result, exception",
     [
+        ([], {}, DoesNotRaise()),  # empty coco annotations
         (
-            [],
-            {},
-            DoesNotRaise()
-        ),  # empty coco annotations
-        (
-            [
-                mock_cock_coco_annotation(annotation_id=0, image_id=0, category_id=0)
-            ],
+            [mock_cock_coco_annotation(annotation_id=0, image_id=0, category_id=0)],
             {
                 0: [
-                    mock_cock_coco_annotation(annotation_id=0, image_id=0, category_id=0)
+                    mock_cock_coco_annotation(
+                        annotation_id=0, image_id=0, category_id=0
+                    )
                 ]
             },
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # single coco annotation
         (
             [
                 mock_cock_coco_annotation(annotation_id=0, image_id=0, category_id=0),
-                mock_cock_coco_annotation(annotation_id=1, image_id=1, category_id=0)
+                mock_cock_coco_annotation(annotation_id=1, image_id=1, category_id=0),
             ],
             {
                 0: [
-                    mock_cock_coco_annotation(annotation_id=0, image_id=0, category_id=0)
+                    mock_cock_coco_annotation(
+                        annotation_id=0, image_id=0, category_id=0
+                    )
                 ],
                 1: [
-                    mock_cock_coco_annotation(annotation_id=1, image_id=1, category_id=0)
-                ]
+                    mock_cock_coco_annotation(
+                        annotation_id=1, image_id=1, category_id=0
+                    )
+                ],
             },
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # two coco annotations
         (
             [
@@ -201,29 +142,41 @@ def test_classes_to_coco_categories_and_back_to_classes(classes: List[str], exce
             ],
             {
                 0: [
-                    mock_cock_coco_annotation(annotation_id=0, image_id=0, category_id=0),
+                    mock_cock_coco_annotation(
+                        annotation_id=0, image_id=0, category_id=0
+                    ),
                 ],
                 1: [
-                    mock_cock_coco_annotation(annotation_id=1, image_id=1, category_id=1),
-                    mock_cock_coco_annotation(annotation_id=2, image_id=1, category_id=2),
+                    mock_cock_coco_annotation(
+                        annotation_id=1, image_id=1, category_id=1
+                    ),
+                    mock_cock_coco_annotation(
+                        annotation_id=2, image_id=1, category_id=2
+                    ),
                 ],
                 2: [
-                    mock_cock_coco_annotation(annotation_id=3, image_id=2, category_id=3),
+                    mock_cock_coco_annotation(
+                        annotation_id=3, image_id=2, category_id=3
+                    ),
                 ],
                 3: [
-                    mock_cock_coco_annotation(annotation_id=4, image_id=3, category_id=1),
-                    mock_cock_coco_annotation(annotation_id=5, image_id=3, category_id=2),
-                    mock_cock_coco_annotation(annotation_id=5, image_id=3, category_id=3),
-                ]
+                    mock_cock_coco_annotation(
+                        annotation_id=4, image_id=3, category_id=1
+                    ),
+                    mock_cock_coco_annotation(
+                        annotation_id=5, image_id=3, category_id=2
+                    ),
+                    mock_cock_coco_annotation(
+                        annotation_id=5, image_id=3, category_id=3
+                    ),
+                ],
             },
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # two coco annotations
-    ]
+    ],
 )
 def test_group_coco_annotations_by_image_id(
-    coco_annotations: List[dict],
-    expected_result: dict,
-    exception: Exception
+    coco_annotations: List[dict], expected_result: dict, exception: Exception
 ) -> None:
     with exception:
         result = group_coco_annotations_by_image_id(coco_annotations=coco_annotations)
@@ -238,187 +191,113 @@ def test_group_coco_annotations_by_image_id(
             (1000, 1000),
             False,
             Detections.empty(),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # empty image annotations
         (
             [
-                mock_cock_coco_annotation(category_id=0, bbox=(0, 0, 100, 100), area=100 * 100)
+                mock_cock_coco_annotation(
+                    category_id=0, bbox=(0, 0, 100, 100), area=100 * 100
+                )
             ],
             (1000, 1000),
             False,
             Detections(
-                xyxy=np.array([
-                    [          0,           0,         100,         100]
-                ], dtype=np.float32),
-                class_id=np.array([
-                    0
-                ], dtype=int)
+                xyxy=np.array([[0, 0, 100, 100]], dtype=np.float32),
+                class_id=np.array([0], dtype=int),
             ),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # single image annotations
         (
             [
-                mock_cock_coco_annotation(category_id=0, bbox=(0, 0, 100, 100), area=100 * 100),
-                mock_cock_coco_annotation(category_id=0, bbox=(100, 100, 100, 100), area=100 * 100),
+                mock_cock_coco_annotation(
+                    category_id=0, bbox=(0, 0, 100, 100), area=100 * 100
+                ),
+                mock_cock_coco_annotation(
+                    category_id=0, bbox=(100, 100, 100, 100), area=100 * 100
+                ),
             ],
             (1000, 1000),
             False,
             Detections(
-                xyxy=np.array([
-                    [          0,           0,         100,         100],
-                    [        100,         100,         200,         200]
-                ], dtype=np.float32),
-                class_id=np.array([
-                    0, 0
-                ], dtype=int)
+                xyxy=np.array(
+                    [[0, 0, 100, 100], [100, 100, 200, 200]], dtype=np.float32
+                ),
+                class_id=np.array([0, 0], dtype=int),
             ),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # two image annotations
-    ]
+    ],
 )
 def test_coco_annotations_to_detections(
     image_annotations: List[dict],
     resolution_wh: Tuple[int, int],
     with_masks: bool,
     expected_result: Detections,
-    exception: Exception
+    exception: Exception,
 ) -> None:
     with exception:
         result = coco_annotations_to_detections(
             image_annotations=image_annotations,
             resolution_wh=resolution_wh,
-            with_masks=with_masks
+            with_masks=with_masks,
         )
         assert result == expected_result
 
+
 @pytest.mark.parametrize(
     "coco_categories, target_classes, expected_result, exception",
     [
+        ([], [], {}, DoesNotRaise()),  # empty coco categories
         (
-            [],
-            [],
-            {},
-            DoesNotRaise()
-        ), # empty coco categories
-        (
-            [
-                {
-                    "id": 0,
-                    "name": "fashion-assistant",
-                    "supercategory": "none"
-                }
-            ],
-            [
-                "fashion-assistant"
-            ],
-            {
-                0: 0
-            },
-            DoesNotRaise()
+            [{"id": 0, "name": "fashion-assistant", "supercategory": "none"}],
+            ["fashion-assistant"],
+            {0: 0},
+            DoesNotRaise(),
         ),  # single coco category starting from 0
         (
-            [
-                {
-                    "id": 1,
-                    "name": "fashion-assistant",
-                    "supercategory": "none"
-                }
-            ],
-            [
-                "fashion-assistant"
-            ],
-            {
-                1: 0
-            },
-            DoesNotRaise()
+            [{"id": 1, "name": "fashion-assistant", "supercategory": "none"}],
+            ["fashion-assistant"],
+            {1: 0},
+            DoesNotRaise(),
         ),  # single coco category starting from 1
         (
             [
-                {
-                    "id": 0,
-                    "name": "fashion-assistant",
-                    "supercategory": "none"
-                },
-                {
-                    "id": 2,
-                    "name": "hoodie",
-                    "supercategory": "fashion-assistant"
-                },
-                {
-                    "id": 1,
-                    "name": "baseball cap",
-                    "supercategory": "fashion-assistant"
-                }
+                {"id": 0, "name": "fashion-assistant", "supercategory": "none"},
+                {"id": 2, "name": "hoodie", "supercategory": "fashion-assistant"},
+                {"id": 1, "name": "baseball cap", "supercategory": "fashion-assistant"},
             ],
-            [
-                "fashion-assistant",
-                "baseball cap",
-                "hoodie"
-            ],
-            {
-                0: 0,
-                1: 1,
-                2: 2
-            },
-            DoesNotRaise()
+            ["fashion-assistant", "baseball cap", "hoodie"],
+            {0: 0, 1: 1, 2: 2},
+            DoesNotRaise(),
         ),  # three coco categories
         (
             [
-                {
-                    "id": 2,
-                    "name": "hoodie",
-                    "supercategory": "fashion-assistant"
-                },
-                {
-                    "id": 1,
-                    "name": "baseball cap",
-                    "supercategory": "fashion-assistant"
-                }
+                {"id": 2, "name": "hoodie", "supercategory": "fashion-assistant"},
+                {"id": 1, "name": "baseball cap", "supercategory": "fashion-assistant"},
             ],
-            [
-                "baseball cap",
-                "hoodie"
-            ],
-            {
-                2: 1,
-                1: 0
-            },
-            DoesNotRaise()
+            ["baseball cap", "hoodie"],
+            {2: 1, 1: 0},
+            DoesNotRaise(),
         ),  # two coco categories
         (
             [
-                {
-                    "id": 3,
-                    "name": "hoodie",
-                    "supercategory": "fashion-assistant"
-                },
-                {
-                    "id": 1,
-                    "name": "baseball cap",
-                    "supercategory": "fashion-assistant"
-                }
+                {"id": 3, "name": "hoodie", "supercategory": "fashion-assistant"},
+                {"id": 1, "name": "baseball cap", "supercategory": "fashion-assistant"},
             ],
-            [
-                "baseball cap",
-                "hoodie"
-            ],
-            {
-                3: 1,
-                1: 0
-            },
-            DoesNotRaise()
+            ["baseball cap", "hoodie"],
+            {3: 1, 1: 0},
+            DoesNotRaise(),
         ),  # two coco categories with missing category
-    ]
+    ],
 )
 def test_build_coco_class_index_mapping(
     coco_categories: List[dict],
     target_classes: List[str],
     expected_result: Dict[int, int],
-    exception: Exception
+    exception: Exception,
 ) -> None:
     with exception:
         result = build_coco_class_index_mapping(
-            coco_categories=coco_categories,
-            target_classes=target_classes
+            coco_categories=coco_categories, target_classes=target_classes
         )
         assert result == expected_result

test/dataset/formats/test_pascal_voc.py

@@ -33,20 +33,25 @@ def are_xml_elements_equal(elem1, elem2):
     "xyxy, name, polygon, expected_result, exception",
     [
         (
-            [0, 0, 10, 10],
+            np.array([0, 0, 10, 10]),
             "test",
             None,
             ET.fromstring(
-                """<object><name>test</name><bndbox><xmin>0</xmin><ymin>0</ymin><xmax>10</xmax><ymax>10</ymax></bndbox></object>"""
+                """<object><name>test</name><bndbox><xmin>1</xmin><ymin>1</ymin>
+                <xmax>11</xmax><ymax>11</ymax></bndbox></object>"""
             ),
             DoesNotRaise(),
         ),
         (
-            [0, 0, 10, 10],
+            np.array([0, 0, 10, 10]),
             "test",
-            [[0, 0], [10, 0], [10, 10], [0, 10]],
+            np.array([[0, 0], [10, 0], [10, 10], [0, 10]]),
             ET.fromstring(
-                """<object><name>test</name><bndbox><xmin>0</xmin><ymin>0</ymin><xmax>10</xmax><ymax>10</ymax></bndbox><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></object>"""
+                """<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>
+                <y2>1</y2><x3>11</x3><y3>11</y3><x4>1</x4><y4>11</y4>
+                </polygon></object>"""
             ),
             DoesNotRaise(),
         ),
@@ -69,9 +74,10 @@ def test_object_to_pascal_voc(
     [
         (
             ET.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>"""
+                """<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>"""
             ),
-            [[0, 0], [10, 0], [10, 10], [0, 10]],
+            np.array([[0, 0], [10, 0], [10, 10], [0, 10]]),
             DoesNotRaise(),
         )
     ],
@@ -83,16 +89,27 @@ def test_parse_polygon_points(
 ):
     with exception:
         result = parse_polygon_points(polygon_element)
-        assert result == expected_result
+        assert np.array_equal(result, expected_result)
 
 
-ONE_CLASS_N_BBOX = """<annotation><object><name>test</name><bndbox><xmin>0</xmin><ymin>0</ymin><xmax>10</xmax><ymax>10</ymax></bndbox></object><object><name>test</name><bndbox><xmin>10</xmin><ymin>10</ymin><xmax>20</xmax><ymax>20</ymax></bndbox></object></annotation>"""
+ONE_CLASS_N_BBOX = """<annotation><object><name>test</name><bndbox><xmin>1</xmin>
+<ymin>1</ymin><xmax>11</xmax><ymax>11</ymax>
+</bndbox></object><object><name>test</name><bndbox><xmin>11</xmin><ymin>11</ymin>
+<xmax>21</xmax><ymax>21</ymax></bndbox></object></annotation>"""
 
 
-ONE_CLASS_ONE_BBOX = """<annotation><object><name>test</name><bndbox><xmin>0</xmin><ymin>0</ymin><xmax>10</xmax><ymax>10</ymax></bndbox></object></annotation>"""
+ONE_CLASS_ONE_BBOX = """<annotation><object><name>test</name><bndbox>
+<xmin>1</xmin><ymin>1</ymin><xmax>11</xmax><ymax>11</ymax></bndbox></object>
+</annotation>"""
 
 
-N_CLASS_N_BBOX = """<annotation><object><name>test</name><bndbox><xmin>0</xmin><ymin>0</ymin><xmax>10</xmax><ymax>10</ymax></bndbox></object><object><name>test</name><bndbox><xmin>20</xmin><ymin>30</ymin><xmax>30</xmax><ymax>40</ymax></bndbox></object><object><name>test2</name><bndbox><xmin>10</xmin><ymin>10</ymin><xmax>20</xmax><ymax>20</ymax></bndbox></object></annotation>"""
+N_CLASS_N_BBOX = """<annotation><object><name>test</name><bndbox><xmin>1</xmin>
+<ymin>1</ymin><xmax>11</xmax><ymax>11</ymax>
+</bndbox></object><object><name>test</name><bndbox>
+<xmin>21</xmin><ymin>31</ymin><xmax>31</xmax><ymax>41</ymax></bndbox>
+</object><object><name>test2</name><bndbox><xmin>
+11</xmin><ymin>11</ymin><xmax>21</xmax><ymax>
+21</ymax></bndbox></object></annotation>"""
 
 NO_DETECTIONS = """<annotation></annotation>"""
 

test/dataset/formats/test_yolo.py

@@ -1,12 +1,16 @@
 from contextlib import ExitStack as DoesNotRaise
-from typing import List, Tuple, Optional
+from typing import List, Optional, Tuple
 
-import pytest
 import numpy as np
+import pytest
 
+from supervision.dataset.formats.yolo import (
+    _image_name_to_annotation_name,
+    _with_mask,
+    object_to_yolo,
+    yolo_annotations_to_detections,
+)
 from supervision.detection.core import Detections
-from supervision.dataset.formats.yolo import yolo_annotations_to_detections, _with_mask, _image_name_to_annotation_name, \
-    object_to_yolo
 
 
 def _mock_simple_mask(resolution_wh: Tuple[int, int], box: List[int]) -> np.array:
@@ -17,223 +21,188 @@ def _mock_simple_mask(resolution_wh: Tuple[int, int], box: List[int]) -> np.arra
 
 
 # The result of _mock_simple_mask is a little different from the result produced by cv2.
-def _arrays_almost_equal(arr1: np.ndarray, arr2: np.ndarray, threshold: float = 0.99) -> bool:
+def _arrays_almost_equal(
+    arr1: np.ndarray, arr2: np.ndarray, threshold: float = 0.99
+) -> bool:
     equal_elements = np.equal(arr1, arr2)
     proportion_equal = np.mean(equal_elements)
     return proportion_equal >= threshold
 
 
 @pytest.mark.parametrize(
-    'lines, expected_result, exception',
+    "lines, expected_result, exception",
     [
+        ([], False, DoesNotRaise()),  # empty yolo annotation file
         (
-            [],
+            ["0 0.5 0.5 0.2 0.2"],
             False,
-            DoesNotRaise()
-        ),  # empty yolo annotation file
-        (
-            [
-                '0 0.5 0.5 0.2 0.2'
-            ],
-            False,
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # yolo annotation file with single line with box
         (
-                [
-                    '0 0.50 0.50 0.20 0.20',
-                    '1 0.11 0.47 0.22 0.30'
-                ],
-                False,
-                DoesNotRaise()
-        ),  # yolo annotation file with two lines with box
-        (
-            [
-                '0 0.5 0.5 0.2 0.2'
-            ],
+            ["0 0.50 0.50 0.20 0.20", "1 0.11 0.47 0.22 0.30"],
             False,
-            DoesNotRaise()
-        ),
+            DoesNotRaise(),
+        ),  # yolo annotation file with two lines with box
+        (["0 0.5 0.5 0.2 0.2"], False, DoesNotRaise()),
         (
-            [
-                '0 0.4 0.4 0.6 0.4 0.6 0.6 0.4 0.6'
-            ],
+            ["0 0.4 0.4 0.6 0.4 0.6 0.6 0.4 0.6"],
             True,
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # yolo annotation file with single line with polygon
         (
-            [
-                '0 0.4 0.4 0.6 0.4 0.6 0.6 0.4 0.6',
-                '1 0.11 0.47 0.22 0.30'
-            ],
+            ["0 0.4 0.4 0.6 0.4 0.6 0.6 0.4 0.6", "1 0.11 0.47 0.22 0.30"],
             True,
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # yolo annotation file with two lines - one box and one polygon
-    ]
+    ],
 )
-def test_with_mask(lines: List[str], expected_result: Optional[bool], exception: Exception) -> None:
+def test_with_mask(
+    lines: List[str], expected_result: Optional[bool], exception: Exception
+) -> None:
     with exception:
         result = _with_mask(lines=lines)
         assert result == expected_result
 
 
 @pytest.mark.parametrize(
-    'lines, resolution_wh, with_masks, expected_result, exception',
+    "lines, resolution_wh, with_masks, expected_result, exception",
     [
         (
             [],
             (1000, 1000),
             False,
             Detections.empty(),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # empty yolo annotation file
         (
-            [
-                '0 0.5 0.5 0.2 0.2'
-            ],
+            ["0 0.5 0.5 0.2 0.2"],
             (1000, 1000),
             False,
             Detections(
-                xyxy=np.array([
-                    [400, 400, 600, 600]
-                ], dtype=np.float32),
-                class_id=np.array([0], dtype=int)
+                xyxy=np.array([[400, 400, 600, 600]], dtype=np.float32),
+                class_id=np.array([0], dtype=int),
             ),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # yolo annotation file with single line with box
         (
-            [
-                '0 0.50 0.50 0.20 0.20',
-                '1 0.11 0.47 0.22 0.30'
-            ],
+            ["0 0.50 0.50 0.20 0.20", "1 0.11 0.47 0.22 0.30"],
             (1000, 1000),
             False,
             Detections(
-                xyxy=np.array([
-                    [400, 400, 600, 600],
-                    [  0, 320, 220, 620]
-                ], dtype=np.float32),
-                class_id=np.array([0, 1], dtype=int)
+                xyxy=np.array(
+                    [[400, 400, 600, 600], [0, 320, 220, 620]], dtype=np.float32
+                ),
+                class_id=np.array([0, 1], dtype=int),
             ),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # yolo annotation file with two lines with box
         (
-            [
-                '0 0.5 0.5 0.2 0.2'
-            ],
+            ["0 0.5 0.5 0.2 0.2"],
             (1000, 1000),
             True,
             Detections(
-                xyxy=np.array([
-                    [400, 400, 600, 600]
-                ], dtype=np.float32),
+                xyxy=np.array([[400, 400, 600, 600]], dtype=np.float32),
                 class_id=np.array([0], dtype=int),
-                mask=np.array([
-                    _mock_simple_mask(resolution_wh=(1000, 1000), box=[400, 400, 600, 600])
-                ], dtype=bool)
+                mask=np.array(
+                    [
+                        _mock_simple_mask(
+                            resolution_wh=(1000, 1000), box=[400, 400, 600, 600]
+                        )
+                    ],
+                    dtype=bool,
+                ),
             ),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # yolo annotation file with single line with box in with_masks mode
         (
-            [
-                '0 0.4 0.4 0.6 0.4 0.6 0.6 0.4 0.6'
-            ],
+            ["0 0.4 0.4 0.6 0.4 0.6 0.6 0.4 0.6"],
             (1000, 1000),
             True,
             Detections(
-                xyxy=np.array([
-                    [400, 400, 600, 600]
-                ], dtype=np.float32),
+                xyxy=np.array([[400, 400, 600, 600]], dtype=np.float32),
                 class_id=np.array([0], dtype=int),
-                mask=np.array([
-                    _mock_simple_mask(resolution_wh=(1000, 1000), box=[400, 400, 600, 600])
-                ], dtype=bool)
+                mask=np.array(
+                    [
+                        _mock_simple_mask(
+                            resolution_wh=(1000, 1000), box=[400, 400, 600, 600]
+                        )
+                    ],
+                    dtype=bool,
+                ),
             ),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # yolo annotation file with single line with polygon
         (
-            [
-                '0 0.4 0.4 0.6 0.4 0.6 0.6 0.4 0.6',
-                '1 0.11 0.47 0.22 0.30'
-            ],
+            ["0 0.4 0.4 0.6 0.4 0.6 0.6 0.4 0.6", "1 0.11 0.47 0.22 0.30"],
             (1000, 1000),
             True,
             Detections(
-                xyxy=np.array([
-                    [400, 400, 600, 600],
-                    [  0, 320, 220, 620]
-                ], dtype=np.float32),
+                xyxy=np.array(
+                    [[400, 400, 600, 600], [0, 320, 220, 620]], dtype=np.float32
+                ),
                 class_id=np.array([0, 1], dtype=int),
-                mask=np.array([
-                    _mock_simple_mask(resolution_wh=(1000, 1000), box=[400, 400, 600, 600]),
-                    _mock_simple_mask(resolution_wh=(1000, 1000), box=[  0, 320, 220, 620])
-                ], dtype=bool)
+                mask=np.array(
+                    [
+                        _mock_simple_mask(
+                            resolution_wh=(1000, 1000), box=[400, 400, 600, 600]
+                        ),
+                        _mock_simple_mask(
+                            resolution_wh=(1000, 1000), box=[0, 320, 220, 620]
+                        ),
+                    ],
+                    dtype=bool,
+                ),
             ),
-            DoesNotRaise()
-        ),  # yolo annotation file with two lines - one box and one polygon in with_masks mode
+            DoesNotRaise(),
+        ),  # yolo annotation file with two lines -
+        # one box and one polygon in with_masks mode
         (
-            [
-                '0 0.4 0.4 0.6 0.4 0.6 0.6 0.4 0.6',
-                '1 0.11 0.47 0.22 0.30'
-            ],
+            ["0 0.4 0.4 0.6 0.4 0.6 0.6 0.4 0.6", "1 0.11 0.47 0.22 0.30"],
             (1000, 1000),
             False,
             Detections(
-                xyxy=np.array([
-                    [400, 400, 600, 600],
-                    [  0, 320, 220, 620]
-                ], dtype=np.float32),
-                class_id=np.array([0, 1], dtype=int)
+                xyxy=np.array(
+                    [[400, 400, 600, 600], [0, 320, 220, 620]], dtype=np.float32
+                ),
+                class_id=np.array([0, 1], dtype=int),
             ),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # yolo annotation file with two lines - one box and one polygon
-    ]
+    ],
 )
 def test_yolo_annotations_to_detections(
     lines: List[str],
     resolution_wh: Tuple[int, int],
     with_masks: bool,
     expected_result: Optional[Detections],
-    exception: Exception
+    exception: Exception,
 ) -> None:
     with exception:
         result = yolo_annotations_to_detections(
-            lines=lines,
-            resolution_wh=resolution_wh,
-            with_masks=with_masks)
+            lines=lines, resolution_wh=resolution_wh, with_masks=with_masks
+        )
         assert np.array_equal(result.xyxy, expected_result.xyxy)
         assert np.array_equal(result.class_id, expected_result.class_id)
-        assert (result.mask is None and expected_result.mask is None) or _arrays_almost_equal(result.mask, expected_result.mask)
+        assert (
+            result.mask is None and expected_result.mask is None
+        ) or _arrays_almost_equal(result.mask, expected_result.mask)
 
 
 @pytest.mark.parametrize(
-    'image_name, expected_result, exception',
+    "image_name, expected_result, exception",
     [
+        ("image.png", "image.txt", DoesNotRaise()),  # simple png image
+        ("image.jpeg", "image.txt", DoesNotRaise()),  # simple jpeg image
+        ("image.jpg", "image.txt", DoesNotRaise()),  # simple jpg image
         (
-            'image.png',
-            'image.txt',
-            DoesNotRaise()
-        ),  # simple png image
-        (
-            'image.jpeg',
-            'image.txt',
-            DoesNotRaise()
-        ),  # simple jpeg image
-        (
-            'image.jpg',
-            'image.txt',
-            DoesNotRaise()
-        ),  # simple jpg image
-        (
-            'image.000.jpg',
-            'image.000.txt',
-            DoesNotRaise()
+            "image.000.jpg",
+            "image.000.txt",
+            DoesNotRaise(),
         ),  # jpg image with multiple dots in name
-    ]
+    ],
 )
 def test_image_name_to_annotation_name(
-    image_name: str,
-    expected_result: Optional[str],
-    exception: Exception
+    image_name: str, expected_result: Optional[str], exception: Exception
 ) -> None:
     with exception:
         result = _image_name_to_annotation_name(image_name=image_name)
@@ -241,64 +210,70 @@ def test_image_name_to_annotation_name(
 
 
 @pytest.mark.parametrize(
-    'xyxy, class_id, image_shape, polygon, expected_result, exception',
+    "xyxy, class_id, image_shape, polygon, expected_result, exception",
     [
         (
             np.array([100, 100, 200, 200], dtype=np.float32),
             1,
             (1000, 1000, 3),
             None,
-            '1 0.15000 0.15000 0.10000 0.10000',
-            DoesNotRaise()
+            "1 0.15000 0.15000 0.10000 0.10000",
+            DoesNotRaise(),
         ),  # square bounding box on square image
         (
             np.array([100, 100, 200, 200], dtype=np.float32),
             1,
             (800, 1000, 3),
             None,
-            '1 0.15000 0.18750 0.10000 0.12500',
-            DoesNotRaise()
+            "1 0.15000 0.18750 0.10000 0.12500",
+            DoesNotRaise(),
         ),  # square bounding box on horizontal image
         (
             np.array([100, 100, 200, 200], dtype=np.float32),
             1,
             (1000, 800, 3),
             None,
-            '1 0.18750 0.15000 0.12500 0.10000',
-            DoesNotRaise()
+            "1 0.18750 0.15000 0.12500 0.10000",
+            DoesNotRaise(),
         ),  # square bounding box on vertical image
         (
             np.array([100, 200, 200, 400], dtype=np.float32),
             1,
             (1000, 1000, 3),
             None,
-            '1 0.15000 0.30000 0.10000 0.20000',
-            DoesNotRaise()
+            "1 0.15000 0.30000 0.10000 0.20000",
+            DoesNotRaise(),
         ),  # horizontal bounding box on square image
         (
             np.array([200, 100, 400, 200], dtype=np.float32),
             1,
             (1000, 1000, 3),
             None,
-            '1 0.30000 0.15000 0.20000 0.10000',
-            DoesNotRaise()
+            "1 0.30000 0.15000 0.20000 0.10000",
+            DoesNotRaise(),
         ),  # vertical bounding box on square image
         (
             np.array([100, 100, 200, 200], dtype=np.float32),
             1,
             (1000, 1000, 3),
-            np.array([
-                [100, 100],
-                [200, 100],
-                [200, 200],
-                [100, 100]
-            ], dtype=np.float32),
-            '1 0.10000 0.10000 0.20000 0.10000 0.20000 0.20000 0.10000 0.10000',
-            DoesNotRaise()
+            np.array(
+                [[100, 100], [200, 100], [200, 200], [100, 100]], dtype=np.float32
+            ),
+            "1 0.10000 0.10000 0.20000 0.10000 0.20000 0.20000 0.10000 0.10000",
+            DoesNotRaise(),
         ),  # square mask on square image
-    ]
+    ],
 )
-def test_object_to_yolo(xyxy: np.ndarray, class_id: int, image_shape: Tuple[int, int, int], polygon: Optional[np.ndarray], expected_result: Optional[str], exception: Exception) -> None:
+def test_object_to_yolo(
+    xyxy: np.ndarray,
+    class_id: int,
+    image_shape: Tuple[int, int, int],
+    polygon: Optional[np.ndarray],
+    expected_result: Optional[str],
+    exception: Exception,
+) -> None:
     with exception:
-        result = object_to_yolo(xyxy=xyxy, class_id=class_id, image_shape=image_shape, polygon=polygon)
+        result = object_to_yolo(
+            xyxy=xyxy, class_id=class_id, image_shape=image_shape, polygon=polygon
+        )
         assert result == expected_result

test/dataset/test_core.py

@@ -1,13 +1,11 @@
+from contextlib import ExitStack as DoesNotRaise
+from test.utils import mock_detections
 from typing import List, Optional
 
+import numpy as np
 import pytest
 
 from supervision import DetectionDataset
-from contextlib import ExitStack as DoesNotRaise
-
-import numpy as np
-
-from test.utils import mock_detections
 
 
 @pytest.mark.parametrize(
@@ -16,159 +14,181 @@ from test.utils import mock_detections
         (
             [],
             DetectionDataset(classes=[], images={}, annotations={}),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # empty dataset list
         (
-            [
-                DetectionDataset(classes=[], images={}, annotations={})
-            ],
+            [DetectionDataset(classes=[], images={}, annotations={})],
             DetectionDataset(classes=[], images={}, annotations={}),
-            DoesNotRaise()
+            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={}),
-            DoesNotRaise()
+            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={}),
-            DoesNotRaise()
+            DetectionDataset(
+                classes=["cat", "dog", "person"], images={}, annotations={}
+            ),
+            DoesNotRaise(),
         ),  # two datasets; no images and annotations, different classes
         (
             [
                 DetectionDataset(
-                    classes=['dog', 'person'],
+                    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),
+                        "image-1.png": np.zeros((100, 100, 3), dtype=np.uint8),
+                        "image-2.png": np.zeros((100, 100, 3), dtype=np.uint8),
                     },
                     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]),
-                    }
+                        "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]
+                        ),
+                    },
                 ),
                 DetectionDataset(classes=[], images={}, annotations={}),
             ],
             DetectionDataset(
-                classes=['dog', 'person'],
+                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),
+                    "image-1.png": np.zeros((100, 100, 3), dtype=np.uint8),
+                    "image-2.png": np.zeros((100, 100, 3), dtype=np.uint8),
                 },
                 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]),
-                }
+                    "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]),
+                },
             ),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # two datasets; images and annotations, the same classes
         (
             [
                 DetectionDataset(
-                    classes=['dog', 'person'],
+                    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),
+                        "image-1.png": np.zeros((100, 100, 3), dtype=np.uint8),
+                        "image-2.png": np.zeros((100, 100, 3), dtype=np.uint8),
                     },
                     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]),
-                    }
+                        "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]
+                        ),
+                    },
                 ),
-                DetectionDataset(classes=['cat'], images={}, annotations={}),
+                DetectionDataset(classes=["cat"], images={}, annotations={}),
             ],
             DetectionDataset(
-                classes=['cat', 'dog', 'person'],
+                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-1.png": np.zeros((100, 100, 3), dtype=np.uint8),
+                    "image-2.png": np.zeros((100, 100, 3), dtype=np.uint8),
                 },
                 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]),
-                }
+                    "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]),
+                },
             ),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # two datasets; images and annotations, different classes
         (
             [
                 DetectionDataset(
-                    classes=['dog', 'person'],
+                    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),
+                        "image-1.png": np.zeros((100, 100, 3), dtype=np.uint8),
+                        "image-2.png": np.zeros((100, 100, 3), dtype=np.uint8),
                     },
                     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]),
-                    }
+                        "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]
+                        ),
+                    },
                 ),
                 DetectionDataset(
-                    classes=['cat'],
+                    classes=["cat"],
                     images={
-                        'image-3.png': np.zeros((100, 100, 3), dtype=np.uint8),
+                        "image-3.png": np.zeros((100, 100, 3), dtype=np.uint8),
                     },
                     annotations={
-                        'image-3.png': mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[0]),
-                    }
+                        "image-3.png": mock_detections(
+                            xyxy=[[0, 0, 10, 10]], class_id=[0]
+                        ),
+                    },
                 ),
             ],
             DetectionDataset(
-                classes=['cat', 'dog', 'person'],
+                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),
+                    "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),
                 },
                 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]),
-                    'image-3.png': mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[0]),
-                }
+                    "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]),
+                    "image-3.png": mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[0]),
+                },
             ),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # two datasets; images and annotations, different classes
         (
             [
                 DetectionDataset(
-                    classes=['dog', 'person'],
+                    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),
+                        "image-1.png": np.zeros((100, 100, 3), dtype=np.uint8),
+                        "image-2.png": np.zeros((100, 100, 3), dtype=np.uint8),
                     },
                     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]),
-                    }
+                        "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]
+                        ),
+                    },
                 ),
                 DetectionDataset(
-                    classes=['dog', 'person'],
+                    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),
+                        "image-2.png": np.zeros((100, 100, 3), dtype=np.uint8),
+                        "image-3.png": np.zeros((100, 100, 3), dtype=np.uint8),
                     },
                     annotations={
-                        'image-2.png': mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[0]),
-                        'image-3.png': mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[1]),
-                    }
+                        "image-2.png": mock_detections(
+                            xyxy=[[0, 0, 10, 10]], class_id=[0]
+                        ),
+                        "image-3.png": mock_detections(
+                            xyxy=[[0, 0, 10, 10]], class_id=[1]
+                        ),
+                    },
                 ),
             ],
             None,
-            pytest.raises(ValueError)
-        )
-    ]
+            pytest.raises(ValueError),
+        ),
+    ],
 )
 def test_dataset_merge(
     dataset_list: List[DetectionDataset],
     expected_result: Optional[DetectionDataset],
-    exception: Exception
+    exception: Exception,
 ) -> None:
     with exception:
         result = DetectionDataset.merge(dataset_list=dataset_list)

test/dataset/test_utils.py

@@ -1,34 +1,31 @@
 from contextlib import ExitStack as DoesNotRaise
-from typing import List, TypeVar, Optional, Tuple, Dict
+from test.utils import mock_detections
+from typing import Dict, List, Optional, Tuple, TypeVar
 
 import pytest
 
 from supervision import Detections
-from supervision.dataset.utils import train_test_split, merge_class_lists, build_class_index_mapping, \
-    map_detections_class_id
-from test.utils import mock_detections
+from supervision.dataset.utils import (
+    build_class_index_mapping,
+    map_detections_class_id,
+    merge_class_lists,
+    train_test_split,
+)
 
 T = TypeVar("T")
 
 
 @pytest.mark.parametrize(
-    'data, train_ratio, random_state, shuffle, expected_result, exception',
+    "data, train_ratio, random_state, shuffle, expected_result, exception",
     [
-        (
-            [],
-            0.5,
-            None,
-            False,
-            ([], []),
-            DoesNotRaise()
-        ),  # empty data
+        ([], 0.5, None, False, ([], []), DoesNotRaise()),  # empty data
         (
             [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
             0.5,
             None,
             False,
             ([0, 1, 2, 3, 4], [5, 6, 7, 8, 9]),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # data with 10 numbers and 50% train split
         (
             [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
@@ -36,7 +33,7 @@ T = TypeVar("T")
             None,
             False,
             ([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], []),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # data with 10 numbers and 100% train split
         (
             [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
@@ -44,15 +41,15 @@ T = TypeVar("T")
             None,
             False,
             ([], [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # data with 10 numbers and 0% train split
         (
-            ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j'],
+            ["a", "b", "c", "d", "e", "f", "g", "h", "i", "j"],
             0.5,
             None,
             False,
-            (['a', 'b', 'c', 'd', 'e'], ['f', 'g', 'h', 'i', 'j']),
-            DoesNotRaise()
+            (["a", "b", "c", "d", "e"], ["f", "g", "h", "i", "j"]),
+            DoesNotRaise(),
         ),  # data with 10 chars and 50% train split
         (
             [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
@@ -60,7 +57,7 @@ T = TypeVar("T")
             23,
             True,
             ([7, 8, 5, 6, 3], [2, 9, 0, 1, 4]),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # data with 10 numbers and 50% train split with 23 random seed
         (
             [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
@@ -68,9 +65,9 @@ T = TypeVar("T")
             32,
             True,
             ([4, 6, 0, 8, 9], [5, 7, 2, 3, 1]),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # data with 10 numbers and 50% train split with 23 random seed
-    ]
+    ],
 )
 def test_train_test_split(
     data: List[T],
@@ -78,155 +75,140 @@ def test_train_test_split(
     random_state: int,
     shuffle: bool,
     expected_result: Optional[Tuple[List[T], List[T]]],
-    exception: Exception
+    exception: Exception,
 ) -> None:
     with exception:
-        result = train_test_split(data=data, train_ratio=train_ratio, random_state=random_state, shuffle=shuffle)
+        result = train_test_split(
+            data=data,
+            train_ratio=train_ratio,
+            random_state=random_state,
+            shuffle=shuffle,
+        )
         assert result == expected_result
 
 
 @pytest.mark.parametrize(
-    'class_lists, expected_result, exception',
+    "class_lists, expected_result, exception",
     [
+        ([], [], DoesNotRaise()),  # empty class lists
         (
-            [],
-            [],
-            DoesNotRaise()
-        ),  # empty class lists
-        (
-            [
-                ['dog', 'person']
-            ],
-            ['dog', 'person'],
-            DoesNotRaise()
+            [["dog", "person"]],
+            ["dog", "person"],
+            DoesNotRaise(),
         ),  # single class list; already alphabetically sorted
         (
-            [
-                ['person', 'dog']
-            ],
-            ['dog', 'person'],
-            DoesNotRaise()
+            [["person", "dog"]],
+            ["dog", "person"],
+            DoesNotRaise(),
         ),  # single class list; not alphabetically sorted
         (
-            [
-                ['dog', 'person'],
-                ['dog', 'person']
-            ],
-            ['dog', 'person'],
-            DoesNotRaise()
+            [["dog", "person"], ["dog", "person"]],
+            ["dog", "person"],
+            DoesNotRaise(),
         ),  # two class lists; the same classes; already alphabetically sorted
         (
-            [
-                ['dog', 'person'],
-                ['cat']
-            ],
-            ['cat', 'dog', 'person'],
-            DoesNotRaise()
+            [["dog", "person"], ["cat"]],
+            ["cat", "dog", "person"],
+            DoesNotRaise(),
         ),  # two class lists; different classes; already alphabetically sorted
-    ]
+    ],
 )
-def test_merge_class_maps(class_lists: List[List[str]], expected_result: List[str], exception: Exception) -> None:
+def test_merge_class_maps(
+    class_lists: List[List[str]], expected_result: List[str], exception: Exception
+) -> None:
     with exception:
         result = merge_class_lists(class_lists=class_lists)
         assert result == expected_result
 
 
 @pytest.mark.parametrize(
-    'source_classes, target_classes, expected_result, exception',
+    "source_classes, target_classes, expected_result, exception",
     [
+        ([], [], {}, DoesNotRaise()),  # empty class lists
+        ([], ["dog", "person"], {}, DoesNotRaise()),  # empty source class list
         (
-            [],
-            [],
-            {},
-            DoesNotRaise()
-        ),  # empty class lists
-        (
-            [],
-            ['dog', 'person'],
-            {},
-            DoesNotRaise()
-        ),  # empty source class list
-        (
-            ['dog', 'person'],
+            ["dog", "person"],
             [],
             None,
-            pytest.raises(ValueError)
+            pytest.raises(ValueError),
         ),  # empty target class list
         (
-            ['dog', 'person'],
-            ['dog', 'person'],
+            ["dog", "person"],
+            ["dog", "person"],
             {0: 0, 1: 1},
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # same class lists
         (
-            ['dog', 'person'],
-            ['person', 'dog'],
+            ["dog", "person"],
+            ["person", "dog"],
             {0: 1, 1: 0},
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # same class lists but not alphabetically sorted
         (
-            ['dog', 'person'],
-            ['cat', 'dog', 'person'],
+            ["dog", "person"],
+            ["cat", "dog", "person"],
             {0: 1, 1: 2},
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # source class list is a subset of target class list
         (
-            ['dog', 'person'],
-            ['cat', 'dog'],
+            ["dog", "person"],
+            ["cat", "dog"],
             None,
-            pytest.raises(ValueError)
+            pytest.raises(ValueError),
         ),  # source class list is not a subset of target class list
-    ]
+    ],
 )
 def test_build_class_index_mapping(
     source_classes: List[str],
     target_classes: List[str],
     expected_result: Optional[Dict[int, int]],
-    exception: Exception
+    exception: Exception,
 ) -> None:
     with exception:
-        result = build_class_index_mapping(source_classes=source_classes, target_classes=target_classes)
+        result = build_class_index_mapping(
+            source_classes=source_classes, target_classes=target_classes
+        )
         assert result == expected_result
 
 
 @pytest.mark.parametrize(
-    'source_to_target_mapping, detections, expected_result, exception',
+    "source_to_target_mapping, detections, expected_result, exception",
     [
         (
             {},
             mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[0]),
             None,
-            pytest.raises(ValueError)
+            pytest.raises(ValueError),
         ),  # empty mapping
         (
             {0: 1},
             mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[0]),
             mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[1]),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # single mapping
         (
-                {0: 1, 1: 2},
-                Detections.empty(),
-                Detections.empty(),
-                DoesNotRaise()
+            {0: 1, 1: 2},
+            Detections.empty(),
+            Detections.empty(),
+            DoesNotRaise(),
         ),  # empty detections
         (
             {0: 1, 1: 2},
             mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[0]),
             mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[1]),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # multiple mappings
         (
             {0: 1, 1: 2},
             mock_detections(xyxy=[[0, 0, 10, 10], [0, 0, 10, 10]], class_id=[0, 1]),
             mock_detections(xyxy=[[0, 0, 10, 10], [0, 0, 10, 10]], class_id=[1, 2]),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # multiple mappings
         (
             {0: 1, 1: 2},
             mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[2]),
             None,
-            pytest.raises(ValueError)
+            pytest.raises(ValueError),
         ),  # class_id not in mapping
         (
             {0: 1, 1: 2},
@@ -234,14 +216,16 @@ def test_build_class_index_mapping(
             mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[1], confidence=[0.5]),
             DoesNotRaise(),
         ),  # confidence is not None
-    ]
+    ],
 )
 def test_map_detections_class_id(
     source_to_target_mapping: Dict[int, int],
     detections: Detections,
     expected_result: Optional[Detections],
-    exception: Exception
+    exception: Exception,
 ) -> None:
     with exception:
-        result = map_detections_class_id(source_to_target_mapping=source_to_target_mapping, detections=detections)
+        result = map_detections_class_id(
+            source_to_target_mapping=source_to_target_mapping, detections=detections
+        )
         assert result == expected_result

test/detection/test_core.py

@@ -1,46 +1,44 @@
 from contextlib import ExitStack as DoesNotRaise
+from test.utils import mock_detections
+from typing import List, Optional, Union
 
+import numpy as np
 import pytest
 
 from supervision import Detections
 
-from typing import Optional, Union, List
-
-import numpy as np
-
-from test.utils import mock_detections
-
-PREDICTIONS = np.array([
-        [       2254,         906,        2447,        1353,     0.90538,           0],
-        [       2049,        1133,        2226,        1371,     0.59002,          56],
-        [        727,        1224,         838,        1601,     0.51119,          39],
-        [        808,        1214,         910,        1564,     0.45287,          39],
-        [          6,          52,        1131,        2133,     0.45057,          72],
-        [        299,        1225,         512,        1663,     0.45029,          39],
-        [        529,         874,         645,         945,     0.31101,          39],
-        [          8,          47,        1935,        2135,     0.28192,          72],
-        [       2265,         813,        2328,         901,      0.2714,          62]
-    ], dtype=np.float32)
+PREDICTIONS = np.array(
+    [
+        [2254, 906, 2447, 1353, 0.90538, 0],
+        [2049, 1133, 2226, 1371, 0.59002, 56],
+        [727, 1224, 838, 1601, 0.51119, 39],
+        [808, 1214, 910, 1564, 0.45287, 39],
+        [6, 52, 1131, 2133, 0.45057, 72],
+        [299, 1225, 512, 1663, 0.45029, 39],
+        [529, 874, 645, 945, 0.31101, 39],
+        [8, 47, 1935, 2135, 0.28192, 72],
+        [2265, 813, 2328, 901, 0.2714, 62],
+    ],
+    dtype=np.float32,
+)
 
 DETECTIONS = Detections(
     xyxy=PREDICTIONS[:, :4],
     confidence=PREDICTIONS[:, 4],
-    class_id=PREDICTIONS[:, 5].astype(int)
+    class_id=PREDICTIONS[:, 5].astype(int),
 )
 
 
 @pytest.mark.parametrize(
-    'detections, index, expected_result, exception',
+    "detections, index, expected_result, exception",
     [
         (
             DETECTIONS,
             DETECTIONS.class_id == 0,
             mock_detections(
-                xyxy=[[2254, 906, 2447, 1353]],
-                confidence=[0.90538],
-                class_id=[0]
+                xyxy=[[2254, 906, 2447, 1353]], confidence=[0.90538], class_id=[0]
             ),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # take only detections with class_id = 0
         (
             DETECTIONS,
@@ -49,109 +47,90 @@ DETECTIONS = Detections(
                 xyxy=[
                     [2254, 906, 2447, 1353],
                     [2049, 1133, 2226, 1371],
-                    [727, 1224, 838, 1601]
+                    [727, 1224, 838, 1601],
                 ],
                 confidence=[0.90538, 0.59002, 0.51119],
-                class_id=[0, 56, 39]
+                class_id=[0, 56, 39],
             ),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # take only detections with confidence > 0.5
         (
             DETECTIONS,
-            np.array([True, True, True, True, True, True, True, True, True], dtype=bool),
+            np.array(
+                [True, True, True, True, True, True, True, True, True], dtype=bool
+            ),
             DETECTIONS,
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # take all detections
         (
             DETECTIONS,
-            np.array([False, False, False, False, False, False, False, False, False], dtype=bool),
+            np.array(
+                [False, False, False, False, False, False, False, False, False],
+                dtype=bool,
+            ),
             Detections(
                 xyxy=np.empty((0, 4), dtype=np.float32),
                 confidence=np.array([], dtype=np.float32),
-                class_id=np.array([], dtype=int)
+                class_id=np.array([], dtype=int),
             ),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # take no detections
         (
             DETECTIONS,
             [0, 2],
             mock_detections(
-                xyxy=[
-                    [2254, 906, 2447, 1353],
-                    [727, 1224, 838, 1601]
-                ],
+                xyxy=[[2254, 906, 2447, 1353], [727, 1224, 838, 1601]],
                 confidence=[0.90538, 0.51119],
-                class_id=[0, 39]
+                class_id=[0, 39],
             ),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # take only first and third detection using List[int] index
         (
             DETECTIONS,
             np.array([0, 2]),
             mock_detections(
-                xyxy=[
-                    [2254, 906, 2447, 1353],
-                    [727, 1224, 838, 1601]
-                ],
+                xyxy=[[2254, 906, 2447, 1353], [727, 1224, 838, 1601]],
                 confidence=[0.90538, 0.51119],
-                class_id=[0, 39]
+                class_id=[0, 39],
             ),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # take only first and third detection using np.ndarray index
         (
             DETECTIONS,
             0,
             mock_detections(
-                xyxy=[[2254, 906, 2447, 1353]],
-                confidence=[0.90538],
-                class_id=[0]
+                xyxy=[[2254, 906, 2447, 1353]], confidence=[0.90538], class_id=[0]
             ),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # take only first detection by index
         (
             DETECTIONS,
             slice(1, 3),
             mock_detections(
-                xyxy=[
-                    [2049, 1133, 2226, 1371],
-                    [727, 1224, 838, 1601]
-                ],
+                xyxy=[[2049, 1133, 2226, 1371], [727, 1224, 838, 1601]],
                 confidence=[0.59002, 0.51119],
-                class_id=[56, 39]
+                class_id=[56, 39],
             ),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # take only first detection by index slice (1, 3)
+        (DETECTIONS, 10, None, pytest.raises(IndexError)),  # index out of range
+        (DETECTIONS, [0, 2, 10], None, pytest.raises(IndexError)),  # index out of range
+        (DETECTIONS, np.array([0, 2, 10]), None, pytest.raises(IndexError)),
         (
             DETECTIONS,
-            10,
+            np.array(
+                [True, True, True, True, True, True, True, True, True, True, True]
+            ),
             None,
-            pytest.raises(IndexError)
-        ),  # index out of range
-        (
-            DETECTIONS,
-            [0, 2, 10],
-            None,
-            pytest.raises(IndexError)
-        ),  # index out of range
-        (
-            DETECTIONS,
-            np.array([0, 2, 10]),
-            None,
-            pytest.raises(IndexError)
+            pytest.raises(IndexError),
         ),
-        (
-            DETECTIONS,
-            np.array([True, True, True, True, True, True, True, True, True, True, True]),
-            None,
-            pytest.raises(IndexError)
-        )
-    ]
+    ],
 )
 def test_getitem(
-        detections: Detections,
-        index:  Union[int, slice, List[int], np.ndarray],
-        expected_result: Optional[Detections],
-        exception: Exception
+    detections: Detections,
+    index: Union[int, slice, List[int], np.ndarray],
+    expected_result: Optional[Detections],
+    exception: Exception,
 ) -> None:
     with exception:
         result = detections[index]
@@ -159,86 +138,54 @@ def test_getitem(
 
 
 @pytest.mark.parametrize(
-    'detections_list, expected_result, exception',
+    "detections_list, expected_result, exception",
     [
+        ([], Detections.empty(), DoesNotRaise()),  # empty detections list
         (
-            [],
+            [Detections.empty()],
             Detections.empty(),
-            DoesNotRaise()
-        ),  # empty detections list
-        (
-            [
-                Detections.empty()
-            ],
-            Detections.empty(),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # single empty detections
         (
-            [
-                mock_detections(xyxy=[[10, 10, 20, 20]])
-            ],
+            [mock_detections(xyxy=[[10, 10, 20, 20]])],
             mock_detections(xyxy=[[10, 10, 20, 20]]),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # single detection with xyxy field
         (
-            [
-                mock_detections(xyxy=[[10, 10, 20, 20]]),
-                Detections.empty()
-            ],
+            [mock_detections(xyxy=[[10, 10, 20, 20]]), Detections.empty()],
             mock_detections(xyxy=[[10, 10, 20, 20]]),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # single detection with xyxy field + empty detection
         (
             [
                 mock_detections(xyxy=[[10, 10, 20, 20]]),
-                mock_detections(xyxy=[[20, 20, 30, 30]])
+                mock_detections(xyxy=[[20, 20, 30, 30]]),
             ],
-            mock_detections(
-                xyxy=[
-                    [10, 10, 20, 20],
-                    [20, 20, 30, 30]
-                ]),
-            DoesNotRaise()
+            mock_detections(xyxy=[[10, 10, 20, 20], [20, 20, 30, 30]]),
+            DoesNotRaise(),
         ),  # two detections with xyxy field
         (
             [
-                mock_detections(
-                    xyxy=[[10, 10, 20, 20]],
-                    class_id=[0]),
-                mock_detections(
-                    xyxy=[[20, 20, 30, 30]])
+                mock_detections(xyxy=[[10, 10, 20, 20]], class_id=[0]),
+                mock_detections(xyxy=[[20, 20, 30, 30]]),
             ],
-            mock_detections(
-                xyxy=[
-                    [10, 10, 20, 20],
-                    [20, 20, 30, 30]
-                ]),
-            DoesNotRaise()
+            mock_detections(xyxy=[[10, 10, 20, 20], [20, 20, 30, 30]]),
+            DoesNotRaise(),
         ),  # detection with xyxy, class_id fields + detection with xyxy field
-(
+        (
             [
-                mock_detections(
-                    xyxy=[[10, 10, 20, 20]],
-                    class_id=[0]),
-                mock_detections(
-                    xyxy=[[20, 20, 30, 30]],
-                    class_id=[1]),
+                mock_detections(xyxy=[[10, 10, 20, 20]], class_id=[0]),
+                mock_detections(xyxy=[[20, 20, 30, 30]], class_id=[1]),
             ],
-            mock_detections(
-                xyxy=[
-                    [10, 10, 20, 20],
-                    [20, 20, 30, 30]
-                ],
-                class_id=[0, 1]
-            ),
-            DoesNotRaise()
+            mock_detections(xyxy=[[10, 10, 20, 20], [20, 20, 30, 30]], class_id=[0, 1]),
+            DoesNotRaise(),
         ),  # two detections with xyxy, class_id fields
-    ]
+    ],
 )
 def test_merge(
-        detections_list: List[Detections],
-        expected_result: Optional[Detections],
-        exception: Exception
+    detections_list: List[Detections],
+    expected_result: Optional[Detections],
+    exception: Exception,
 ) -> None:
     with exception:
         result = Detections.merge(detections_list=detections_list)

test/detection/test_utils.py

@@ -1,12 +1,19 @@
 from contextlib import ExitStack as DoesNotRaise
-from typing import Optional, Tuple, List
-
-import pytest
+from typing import List, Optional, Tuple
 
 import numpy as np
+import pytest
 
-from supervision.detection.utils import non_max_suppression, clip_boxes, filter_polygons_by_area, \
-    process_roboflow_result
+from supervision.detection.utils import (
+    clip_boxes,
+    filter_polygons_by_area,
+    move_boxes,
+    non_max_suppression,
+    process_roboflow_result,
+)
+
+TEST_MASK = np.zeros((1, 1000, 1000), dtype=bool)
+TEST_MASK[:, 300:351, 200:251] = True
 
 
 @pytest.mark.parametrize(
@@ -16,116 +23,101 @@ from supervision.detection.utils import non_max_suppression, clip_boxes, filter_
             np.empty(shape=(0, 5)),
             0.5,
             np.array([]),
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # single box with no category
         (
-            np.array([
-                [10.0, 10.0, 40.0, 40.0, 0.8]
-            ]),
+            np.array([[10.0, 10.0, 40.0, 40.0, 0.8]]),
             0.5,
-            np.array([
-                True
-            ]),
-            DoesNotRaise()
+            np.array([True]),
+            DoesNotRaise(),
         ),  # single box with no category
         (
-            np.array([
-                [10.0, 10.0, 40.0, 40.0, 0.8, 0]
-            ]),
+            np.array([[10.0, 10.0, 40.0, 40.0, 0.8, 0]]),
             0.5,
-            np.array([
-                True
-            ]),
-            DoesNotRaise()
+            np.array([True]),
+            DoesNotRaise(),
         ),  # single box with category
         (
-            np.array([
-                [10.0, 10.0, 40.0, 40.0, 0.8],
-                [15.0, 15.0, 40.0, 40.0, 0.9],
-            ]),
+            np.array(
+                [
+                    [10.0, 10.0, 40.0, 40.0, 0.8],
+                    [15.0, 15.0, 40.0, 40.0, 0.9],
+                ]
+            ),
             0.5,
-            np.array([
-                False,
-                True
-            ]),
-            DoesNotRaise()
+            np.array([False, True]),
+            DoesNotRaise(),
         ),  # two boxes with no category
         (
-            np.array([
-                [10.0, 10.0, 40.0, 40.0, 0.8, 0],
-                [15.0, 15.0, 40.0, 40.0, 0.9, 1],
-            ]),
+            np.array(
+                [
+                    [10.0, 10.0, 40.0, 40.0, 0.8, 0],
+                    [15.0, 15.0, 40.0, 40.0, 0.9, 1],
+                ]
+            ),
             0.5,
-            np.array([
-                True,
-                True
-            ]),
-            DoesNotRaise()
+            np.array([True, True]),
+            DoesNotRaise(),
         ),  # two boxes with different category
         (
-            np.array([
-                [10.0, 10.0, 40.0, 40.0, 0.8, 0],
-                [15.0, 15.0, 40.0, 40.0, 0.9, 0],
-            ]),
+            np.array(
+                [
+                    [10.0, 10.0, 40.0, 40.0, 0.8, 0],
+                    [15.0, 15.0, 40.0, 40.0, 0.9, 0],
+                ]
+            ),
             0.5,
-            np.array([
-                False,
-                True
-            ]),
-            DoesNotRaise()
+            np.array([False, True]),
+            DoesNotRaise(),
         ),  # two boxes with same category
         (
-            np.array([
-                [0.0, 0.0, 30.0, 40.0, 0.8],
-                [5.0, 5.0, 35.0, 45.0, 0.9],
-                [10.0, 10.0, 40.0, 50.0, 0.85],
-            ]),
+            np.array(
+                [
+                    [0.0, 0.0, 30.0, 40.0, 0.8],
+                    [5.0, 5.0, 35.0, 45.0, 0.9],
+                    [10.0, 10.0, 40.0, 50.0, 0.85],
+                ]
+            ),
             0.5,
-            np.array([
-                False,
-                True,
-                False
-            ]),
-            DoesNotRaise()
+            np.array([False, True, False]),
+            DoesNotRaise(),
         ),  # three boxes with no category
         (
-            np.array([
-                [0.0, 0.0, 30.0, 40.0, 0.8, 0],
-                [5.0, 5.0, 35.0, 45.0, 0.9, 1],
-                [10.0, 10.0, 40.0, 50.0, 0.85, 2],
-            ]),
+            np.array(
+                [
+                    [0.0, 0.0, 30.0, 40.0, 0.8, 0],
+                    [5.0, 5.0, 35.0, 45.0, 0.9, 1],
+                    [10.0, 10.0, 40.0, 50.0, 0.85, 2],
+                ]
+            ),
             0.5,
-            np.array([
-                True,
-                True,
-                True
-            ]),
-            DoesNotRaise()
+            np.array([True, True, True]),
+            DoesNotRaise(),
         ),  # three boxes with same category
         (
-            np.array([
-                [0.0, 0.0, 30.0, 40.0, 0.8, 0],
-                [5.0, 5.0, 35.0, 45.0, 0.9, 0],
-                [10.0, 10.0, 40.0, 50.0, 0.85, 1],
-            ]),
+            np.array(
+                [
+                    [0.0, 0.0, 30.0, 40.0, 0.8, 0],
+                    [5.0, 5.0, 35.0, 45.0, 0.9, 0],
+                    [10.0, 10.0, 40.0, 50.0, 0.85, 1],
+                ]
+            ),
             0.5,
-            np.array([
-                False,
-                True,
-                True
-            ]),
-            DoesNotRaise()
+            np.array([False, True, True]),
+            DoesNotRaise(),
         ),  # three boxes with different category
-    ]
+    ],
 )
 def test_non_max_suppression(
-        predictions: np.ndarray,
-        iou_threshold: float,
-        expected_result: Optional[np.ndarray],
-        exception: Exception
+    predictions: np.ndarray,
+    iou_threshold: float,
+    expected_result: Optional[np.ndarray],
+    exception: Exception,
 ) -> None:
     with exception:
-        result = non_max_suppression(predictions=predictions, iou_threshold=iou_threshold)
+        result = non_max_suppression(
+            predictions=predictions, iou_threshold=iou_threshold
+        )
         assert np.array_equal(result, expected_result)
 
 
@@ -138,53 +130,37 @@ def test_non_max_suppression(
             np.empty(shape=(0, 4)),
         ),
         (
-            np.array([
-                [1.0, 1.0, 1279.0, 719.0]
-            ]),
+            np.array([[1.0, 1.0, 1279.0, 719.0]]),
             (1280, 720),
-            np.array([
-                [1.0, 1.0, 1279.0, 719.0]
-            ]),
+            np.array([[1.0, 1.0, 1279.0, 719.0]]),
         ),
         (
-            np.array([
-                [-1.0, 1.0, 1279.0, 719.0]
-            ]),
+            np.array([[-1.0, 1.0, 1279.0, 719.0]]),
             (1280, 720),
-            np.array([
-                [0.0, 1.0, 1279.0, 719.0]
-            ]),
+            np.array([[0.0, 1.0, 1279.0, 719.0]]),
         ),
         (
-            np.array([
-                [1.0, -1.0, 1279.0, 719.0]
-            ]),
+            np.array([[1.0, -1.0, 1279.0, 719.0]]),
             (1280, 720),
-            np.array([
-                [1.0, 0.0, 1279.0, 719.0]
-            ]),
+            np.array([[1.0, 0.0, 1279.0, 719.0]]),
         ),
         (
-            np.array([
-                [1.0, 1.0, 1281.0, 719.0]
-            ]),
+            np.array([[1.0, 1.0, 1281.0, 719.0]]),
             (1280, 720),
-            np.array([
-                [1.0, 1.0, 1280.0, 719.0]
-            ]),
+            np.array([[1.0, 1.0, 1280.0, 719.0]]),
         ),
         (
-            np.array([
-                [1.0, 1.0, 1279.0, 721.0]
-            ]),
+            np.array([[1.0, 1.0, 1279.0, 721.0]]),
             (1280, 720),
-            np.array([
-                [1.0, 1.0, 1279.0, 720.0]
-            ]),
+            np.array([[1.0, 1.0, 1279.0, 720.0]]),
         ),
-    ]
+    ],
 )
-def test_clip_boxes(boxes_xyxy: np.ndarray, frame_resolution_wh: Tuple[int, int], expected_result: np.ndarray) -> None:
+def test_clip_boxes(
+    boxes_xyxy: np.ndarray,
+    frame_resolution_wh: Tuple[int, int],
+    expected_result: np.ndarray,
+) -> None:
     result = clip_boxes(boxes_xyxy=boxes_xyxy, frame_resolution_wh=frame_resolution_wh)
     assert np.array_equal(result, expected_result)
 
@@ -197,83 +173,87 @@ def test_clip_boxes(boxes_xyxy: np.ndarray, frame_resolution_wh: Tuple[int, int]
             None,
             None,
             [np.array([[0, 0], [0, 10], [10, 10], [10, 0]])],
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # single polygon without area constraints
         (
             [np.array([[0, 0], [0, 10], [10, 10], [10, 0]])],
             50,
             None,
             [np.array([[0, 0], [0, 10], [10, 10], [10, 0]])],
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # single polygon with min_area constraint
         (
             [np.array([[0, 0], [0, 10], [10, 10], [10, 0]])],
             None,
             50,
             [],
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # single polygon with max_area constraint
         (
             [
                 np.array([[0, 0], [0, 10], [10, 10], [10, 0]]),
-                np.array([[0, 0], [0, 20], [20, 20], [20, 0]])
+                np.array([[0, 0], [0, 20], [20, 20], [20, 0]]),
             ],
             200,
             None,
             [np.array([[0, 0], [0, 20], [20, 20], [20, 0]])],
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # two polygons with min_area constraint
         (
             [
                 np.array([[0, 0], [0, 10], [10, 10], [10, 0]]),
-                np.array([[0, 0], [0, 20], [20, 20], [20, 0]])
+                np.array([[0, 0], [0, 20], [20, 20], [20, 0]]),
             ],
             None,
             200,
             [np.array([[0, 0], [0, 10], [10, 10], [10, 0]])],
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # two polygons with max_area constraint
         (
             [
                 np.array([[0, 0], [0, 10], [10, 10], [10, 0]]),
-                np.array([[0, 0], [0, 20], [20, 20], [20, 0]])
+                np.array([[0, 0], [0, 20], [20, 20], [20, 0]]),
             ],
             200,
             200,
             [],
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # two polygons with both area constraints
         (
             [
                 np.array([[0, 0], [0, 10], [10, 10], [10, 0]]),
-                np.array([[0, 0], [0, 20], [20, 20], [20, 0]])
+                np.array([[0, 0], [0, 20], [20, 20], [20, 0]]),
             ],
             100,
             100,
             [np.array([[0, 0], [0, 10], [10, 10], [10, 0]])],
-            DoesNotRaise()
-        ),  # two polygons with min_area and max_area equal to the area of the first polygon
+            DoesNotRaise(),
+        ),  # two polygons with min_area and
+        # max_area equal to the area of the first polygon
         (
             [
                 np.array([[0, 0], [0, 10], [10, 10], [10, 0]]),
-                np.array([[0, 0], [0, 20], [20, 20], [20, 0]])
+                np.array([[0, 0], [0, 20], [20, 20], [20, 0]]),
             ],
             400,
             400,
             [np.array([[0, 0], [0, 20], [20, 20], [20, 0]])],
-            DoesNotRaise()
-        ),  # two polygons with min_area and max_area equal to the area of the second polygon
-    ]
+            DoesNotRaise(),
+        ),  # two polygons with min_area and
+        # max_area equal to the area of the second polygon
+    ],
 )
 def test_filter_polygons_by_area(
-        polygons: List[np.ndarray],
-        min_area: Optional[float],
-        max_area: Optional[float],
-        expected_result: List[np.ndarray],
-        exception: Exception
+    polygons: List[np.ndarray],
+    min_area: Optional[float],
+    max_area: Optional[float],
+    expected_result: List[np.ndarray],
+    exception: Exception,
 ) -> None:
     with exception:
-        result = filter_polygons_by_area(polygons=polygons, min_area=min_area, max_area=max_area)
+        result = filter_polygons_by_area(
+            polygons=polygons, min_area=min_area, max_area=max_area
+        )
         assert len(result) == len(expected_result)
         for result_polygon, expected_result_polygon in zip(result, expected_result):
             assert np.array_equal(result_polygon, expected_result_polygon)
@@ -283,18 +263,10 @@ def test_filter_polygons_by_area(
     "roboflow_result, class_list, expected_result, exception",
     [
         (
-            {
-                "predictions": [],
-                "image": {"width": 1000, "height": 1000}
-            },
+            {"predictions": [], "image": {"width": 1000, "height": 1000}},
             ["person", "car", "truck"],
-            (
-                np.empty((0, 4)),
-                np.empty(0),
-                np.empty(0),
-                None
-             ),
-            DoesNotRaise()
+            (np.empty((0, 4)), np.empty(0), np.empty(0), None),
+            DoesNotRaise(),
         ),  # empty result
         (
             {
@@ -305,33 +277,216 @@ def test_filter_polygons_by_area(
                         "width": 50.0,
                         "height": 50.0,
                         "confidence": 0.9,
-                        "class": "person"
+                        "class": "person",
                     }
                 ],
-                "image": {"width": 1000, "height": 1000}
+                "image": {"width": 1000, "height": 1000},
             },
             ["person", "car", "truck"],
             (
-                np.array([
-                    [175.0, 275.0, 225.0, 325.0]
-                ]),
+                np.array([[175.0, 275.0, 225.0, 325.0]]),
                 np.array([0.9]),
                 np.array([0]),
-                None
-             ),
-            DoesNotRaise()
-        ),  # single bounding box
-    ]
+                None,
+            ),
+            DoesNotRaise(),
+        ),  # single correct object detection result
+        (
+            {
+                "predictions": [
+                    {
+                        "x": 200.0,
+                        "y": 300.0,
+                        "width": 50.0,
+                        "height": 50.0,
+                        "confidence": 0.9,
+                        "class": "person",
+                    },
+                    {
+                        "x": 500.0,
+                        "y": 500.0,
+                        "width": 100.0,
+                        "height": 100.0,
+                        "confidence": 0.8,
+                        "class": "truck",
+                    },
+                ],
+                "image": {"width": 1000, "height": 1000},
+            },
+            ["person", "car", "truck"],
+            (
+                np.array([[175.0, 275.0, 225.0, 325.0], [450.0, 450.0, 550.0, 550.0]]),
+                np.array([0.9, 0.8]),
+                np.array([0, 2]),
+                None,
+            ),
+            DoesNotRaise(),
+        ),  # two correct object detection result
+        (
+            {
+                "predictions": [
+                    {
+                        "x": 200.0,
+                        "y": 300.0,
+                        "width": 50.0,
+                        "height": 50.0,
+                        "confidence": 0.9,
+                        "class": "person",
+                        "points": [],
+                    }
+                ],
+                "image": {"width": 1000, "height": 1000},
+            },
+            ["person", "car", "truck"],
+            (np.empty((0, 4)), np.empty(0), np.empty(0), None),
+            DoesNotRaise(),
+        ),  # single incorrect instance segmentation result with no points
+        (
+            {
+                "predictions": [
+                    {
+                        "x": 200.0,
+                        "y": 300.0,
+                        "width": 50.0,
+                        "height": 50.0,
+                        "confidence": 0.9,
+                        "class": "person",
+                        "points": [{"x": 200.0, "y": 300.0}, {"x": 250.0, "y": 300.0}],
+                    }
+                ],
+                "image": {"width": 1000, "height": 1000},
+            },
+            ["person", "car", "truck"],
+            (np.empty((0, 4)), np.empty(0), np.empty(0), None),
+            DoesNotRaise(),
+        ),  # single incorrect instance segmentation result with no enough points
+        (
+            {
+                "predictions": [
+                    {
+                        "x": 200.0,
+                        "y": 300.0,
+                        "width": 50.0,
+                        "height": 50.0,
+                        "confidence": 0.9,
+                        "class": "person",
+                        "points": [
+                            {"x": 200.0, "y": 300.0},
+                            {"x": 250.0, "y": 300.0},
+                            {"x": 250.0, "y": 350.0},
+                            {"x": 200.0, "y": 350.0},
+                        ],
+                    }
+                ],
+                "image": {"width": 1000, "height": 1000},
+            },
+            ["person", "car", "truck"],
+            (
+                np.array([[175.0, 275.0, 225.0, 325.0]]),
+                np.array([0.9]),
+                np.array([0]),
+                TEST_MASK,
+            ),
+            DoesNotRaise(),
+        ),  # single incorrect instance segmentation result with no enough points
+        (
+            {
+                "predictions": [
+                    {
+                        "x": 200.0,
+                        "y": 300.0,
+                        "width": 50.0,
+                        "height": 50.0,
+                        "confidence": 0.9,
+                        "class": "person",
+                        "points": [
+                            {"x": 200.0, "y": 300.0},
+                            {"x": 250.0, "y": 300.0},
+                            {"x": 250.0, "y": 350.0},
+                            {"x": 200.0, "y": 350.0},
+                        ],
+                    },
+                    {
+                        "x": 500.0,
+                        "y": 500.0,
+                        "width": 100.0,
+                        "height": 100.0,
+                        "confidence": 0.8,
+                        "class": "truck",
+                        "points": [],
+                    },
+                ],
+                "image": {"width": 1000, "height": 1000},
+            },
+            ["person", "car", "truck"],
+            (
+                np.array([[175.0, 275.0, 225.0, 325.0]]),
+                np.array([0.9]),
+                np.array([0]),
+                TEST_MASK,
+            ),
+            DoesNotRaise(),
+        ),  # two instance segmentation results - one correct, one incorrect
+    ],
 )
 def test_process_roboflow_result(
-        roboflow_result: dict,
-        class_list: List[str],
-        expected_result: Tuple[np.ndarray, np.ndarray, np.ndarray, Optional[np.ndarray]],
-        exception: Exception
+    roboflow_result: dict,
+    class_list: List[str],
+    expected_result: Tuple[np.ndarray, np.ndarray, np.ndarray, Optional[np.ndarray]],
+    exception: Exception,
 ) -> None:
     with exception:
-        result = process_roboflow_result(roboflow_result=roboflow_result, class_list=class_list)
+        result = process_roboflow_result(
+            roboflow_result=roboflow_result, class_list=class_list
+        )
         assert np.array_equal(result[0], expected_result[0])
         assert np.array_equal(result[1], expected_result[1])
         assert np.array_equal(result[2], expected_result[2])
-        assert (result[3] is None and expected_result[3] is None) or (np.array_equal(result[3], expected_result[3]))
+        assert (result[3] is None and expected_result[3] is None) or (
+            np.array_equal(result[3], expected_result[3])
+        )
+
+
+@pytest.mark.parametrize(
+    "xyxy, offset, expected_result, exception",
+    [
+        (
+            np.empty(shape=(0, 4)),
+            np.array([0, 0]),
+            np.empty(shape=(0, 4)),
+            DoesNotRaise(),
+        ),  # empty xyxy array
+        (
+            np.array([[0, 0, 10, 10]]),
+            np.array([0, 0]),
+            np.array([[0, 0, 10, 10]]),
+            DoesNotRaise(),
+        ),  # single box with zero offset
+        (
+            np.array([[0, 0, 10, 10]]),
+            np.array([10, 10]),
+            np.array([[10, 10, 20, 20]]),
+            DoesNotRaise(),
+        ),  # single box with non-zero offset
+        (
+            np.array([[0, 0, 10, 10], [0, 0, 10, 10]]),
+            np.array([10, 10]),
+            np.array([[10, 10, 20, 20], [10, 10, 20, 20]]),
+            DoesNotRaise(),
+        ),  # two boxes with non-zero offset
+        (
+            np.array([[0, 0, 10, 10], [0, 0, 10, 10]]),
+            np.array([-10, -10]),
+            np.array([[-10, -10, 0, 0], [-10, -10, 0, 0]]),
+            DoesNotRaise(),
+        ),  # two boxes with negative offset
+    ],
+)
+def test_move_boxes(
+    xyxy: np.ndarray,
+    offset: np.ndarray,
+    expected_result: np.ndarray,
+    exception: Exception,
+) -> None:
+    result = move_boxes(xyxy=xyxy, offset=offset)
+    assert np.array_equal(result, expected_result)

test/geometry/test_dataclasses.py

@@ -1,6 +1,6 @@
 import pytest
 
-from supervision.geometry.core import Vector, Point
+from supervision.geometry.core import Point, Vector
 
 
 @pytest.mark.parametrize(

test/metrics/test_detection.py

@@ -1,12 +1,16 @@
 from contextlib import ExitStack as DoesNotRaise
+from test.utils import assert_almost_equal, mock_detections
 from typing import Optional, Union
 
 import numpy as np
 import pytest
 
 from supervision.detection.core import Detections
-from supervision.metrics.detection import ConfusionMatrix, detections_to_tensor, MeanAveragePrecision
-from test.utils import mock_detections, assert_almost_equal
+from supervision.metrics.detection import (
+    ConfusionMatrix,
+    MeanAveragePrecision,
+    detections_to_tensor,
+)
 
 CLASSES = np.arange(80)
 NUM_CLASSES = len(CLASSES)
@@ -147,15 +151,25 @@ BAD_CONF_MATRIX = worsen_ideal_conf_matrix(
             DoesNotRaise(),
         ),  # single detection; with confidence
         (
-            mock_detections(xyxy=[[0, 0, 10, 10], [0, 0, 20, 20]], class_id=[0, 1], confidence=[0.5, 0.2]),
+            mock_detections(
+                xyxy=[[0, 0, 10, 10], [0, 0, 20, 20]],
+                class_id=[0, 1],
+                confidence=[0.5, 0.2],
+            ),
             False,
             np.array([[0, 0, 10, 10, 0], [0, 0, 20, 20, 1]], dtype=np.float32),
             DoesNotRaise(),
         ),  # multiple detections; no confidence
         (
-            mock_detections(xyxy=[[0, 0, 10, 10], [0, 0, 20, 20]], class_id=[0, 1], confidence=[0.5, 0.2]),
+            mock_detections(
+                xyxy=[[0, 0, 10, 10], [0, 0, 20, 20]],
+                class_id=[0, 1],
+                confidence=[0.5, 0.2],
+            ),
             True,
-            np.array([[0, 0, 10, 10, 0, 0.5], [0, 0, 20, 20, 1, 0.2]], dtype=np.float32),
+            np.array(
+                [[0, 0, 10, 10, 0, 0.5], [0, 0, 20, 20, 1, 0.2]], dtype=np.float32
+            ),
             DoesNotRaise(),
         ),  # multiple detections; with confidence
     ],
@@ -164,18 +178,18 @@ def test_detections_to_tensor(
     detections: Detections,
     with_confidence: bool,
     expected_result: Optional[np.ndarray],
-    exception: Exception
+    exception: Exception,
 ):
     with exception:
         result = detections_to_tensor(
-            detections=detections,
-            with_confidence=with_confidence
+            detections=detections, with_confidence=with_confidence
         )
         assert np.array_equal(result, expected_result)
 
 
 @pytest.mark.parametrize(
-    "predictions, targets, classes, conf_threshold, iou_threshold, expected_result, exception",
+    "predictions, targets, classes, conf_threshold, iou_threshold, expected_result,"
+    " exception",
     [
         (
             DETECTION_TENSORS,
@@ -346,7 +360,8 @@ def test_from_tensors(
 
 
 @pytest.mark.parametrize(
-    "predictions, targets, num_classes, conf_threshold, iou_threshold, expected_result, exception",
+    "predictions, targets, num_classes, conf_threshold, iou_threshold, expected_result,"
+    " exception",
     [
         (
             DETECTION_TENSORS[0],
@@ -403,40 +418,42 @@ def test_drop_extra_matches(
 
 
 @pytest.mark.parametrize(
-    'recall, precision, expected_result, exception',
+    "recall, precision, expected_result, exception",
     [
         (
             np.array([1.0]),
             np.array([1.0]),
             1.0,
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # perfect recall and precision
         (
             np.array([0.0]),
             np.array([0.0]),
             0.0,
-            DoesNotRaise()
+            DoesNotRaise(),
         ),  # no recall and precision
         (
             np.array([0.0, 0.2, 0.2, 0.8, 0.8, 1.0]),
             np.array([0.7, 0.8, 0.4, 0.5, 0.1, 0.2]),
             0.5,
-            DoesNotRaise()
+            DoesNotRaise(),
         ),
         (
             np.array([0.0, 0.5, 0.5, 1.0]),
             np.array([0.75, 0.75, 0.75, 0.75]),
             0.75,
-            DoesNotRaise()
-        )
-    ]
+            DoesNotRaise(),
+        ),
+    ],
 )
 def test_compute_average_precision(
-        recall: np.ndarray,
-        precision: np.ndarray,
-        expected_result: float,
-        exception: Exception
+    recall: np.ndarray,
+    precision: np.ndarray,
+    expected_result: float,
+    exception: Exception,
 ) -> None:
     with exception:
-        result = MeanAveragePrecision.compute_average_precision(recall=recall, precision=precision)
+        result = MeanAveragePrecision.compute_average_precision(
+            recall=recall, precision=precision
+        )
         assert_almost_equal(result, expected_result, tolerance=0.01)