🪵 supervision-0.12.0 changelog updates

Add 0.12.0 changelog

.github/workflows/docs.yml

@@ -5,14 +5,15 @@ on:
     branches:
       - master
       - main
+      - develop
 jobs:
   deploy:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
-      - uses: actions/setup-python@v2
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
         with:
           python-version: 3.x
       - run: pip install mkdocs-material
       - run: pip install "mkdocstrings[python]"
-      - run: mkdocs gh-deploy --force
+      - run: mkdocs gh-deploy --force

.github/workflows/publish.yml

@@ -16,17 +16,32 @@ jobs:
         with:
           ref: ${{ github.head_ref }}
       - name: 🐍 Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        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
-          pip install ".[dev]"
-      - name: 🚀 Publish to PyPi
-        env: 
-          PYPI_USERNAME: ${{ secrets.PYPI_USERNAME }}
-          PYPI_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
-          PYPI_TEST_PASSWORD: ${{ secrets.PYPI_TEST_PASSWORD }}
+          virtualenv venv
+          source venv/bin/activate
+          python -m pip install --upgrade pip
+          python -m pip install --upgrade poetry
+          poetry install
+
+      - name:  🏗️ Build source and wheel distributions
         run: |
-          make publish -e PYPI_USERNAME=$PYPI_USERNAME -e PYPI_PASSWORD=$PYPI_PASSWORD -e PYPI_TEST_PASSWORD=$PYPI_TEST_PASSWORD
+          python -m pip install --upgrade build twine
+          python -m build
+          twine check --strict dist/*
+      - name: 🚀 Publish 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_USERNAME }}
+          password: ${{ secrets.PYPI_TEST_PASSWORD }}

.github/workflows/test.yml

@@ -2,21 +2,19 @@ name: Test WorkFlow
 
 on:
   pull_request:
-    branches: [main]
+    branches: [main, develop]
 
 jobs:
   build:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.7, 3.8, 3.9, '3.10']
+        python-version: ["3.8", "3.9", "3.10","3.11"]
     steps:
       - name: 🛎️ Checkout
         uses: actions/checkout@v3
-        with:
-          ref: ${{ github.head_ref }}
       - name: 🐍 Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
       - name: 🦾 Install dependencies

CITATION.cff

@@ -2,7 +2,7 @@ cff-version: 1.2.0
 author: Roboflow
 message: If you use this software, please cite it as below.
 title: supervision
-version: 0.11.0
+version: 0.11.1
 date-released: 2023-01-19
 license: MIT
 repository-code: https://github.com/roboflow/supervision

Makefile

@@ -16,7 +16,7 @@ check_code_quality:
 	flake8 $(check_dirs) --count --max-line-length=88 --exit-zero  --ignore=D --extend-ignore=E203,E501,W503  --statistics
 	
 publish:
-	python setup.py sdist bdist_wheel
+	poetry build
 	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 

README.md

@@ -25,29 +25,13 @@
 ## 💻 install
 
 Pip install the supervision package in a
-[**3.11>=Python>=3.7**](https://www.python.org/) environment.
+[**3.11>=Python>=3.8**](https://www.python.org/) environment.
 
 ```bash
-pip install supervision
+pip install supervision[desktop]
 ```
 
-<details close>
-<summary>👉 install from source</summary>
-
-```bash
-# 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
-
-# install
-pip install -e ".[dev]"
-```
-
-</details>
+Read more about desktop, headless and local installation in our [guide](https://roboflow.github.io/supervision/).
 
 ## 🔥 quickstart
 
@@ -237,6 +221,30 @@ pip install -e ".[dev]"
 
 </details>
 
+### [model evaluation](https://roboflow.github.io/supervision/metrics/detection/)
+
+```python
+>>> import supervision as sv
+
+>>> dataset = sv.DetectionDataset.from_yolo(...)
+
+>>> def callback(image: np.ndarray) -> sv.Detections:
+...     ...
+
+>>> confusion_matrix = sv.ConfusionMatrix.benchmark(
+...     dataset = dataset,
+...     callback = callback
+... )
+
+>>> confusion_matrix.matrix
+array([
+    [0., 0., 0., 0.],
+    [0., 1., 0., 1.],
+    [0., 1., 1., 0.],
+    [1., 1., 0., 0.]
+])
+```
+
 ## 🎬 tutorials
 
 <p align="left">
@@ -255,11 +263,7 @@ pip install -e ".[dev]"
 
 ## 📚 documentation
 
-Curious how Supervision can help you solve problems on your project? Visit our [documentation](https://roboflow.github.io/supervision) page!
-
-## 💜 built with supervision
-
-You built something cool using supervision? [Let us know!](https://github.com/roboflow/supervision/discussions/categories/built-with-supervision)
+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/changelog.md

@@ -1,6 +1,53 @@
+### 0.12.0 <small>July 24, 2023</small>
+
+!!! warning
+
+    With the `supervision-0.12.0` release, we are terminating official support for Python 3.7.
+
+- Added [#177](https://github.com/roboflow/supervision/pull/177): initial support for object detection model benchmarking with [`sv.ConfusionMatrix`](https://roboflow.github.io/supervision/metrics/detection/#confusionmatrix).
+
+```python
+>>> import supervision as sv
+>>> from ultralytics import YOLO
+
+>>> dataset = sv.DetectionDataset.from_yolo(...)
+
+>>> model = YOLO(...)
+>>> def callback(image: np.ndarray) -> sv.Detections:
+...     result = model(image)[0]
+...     return sv.Detections.from_yolov8(result)
+
+>>> confusion_matrix = sv.ConfusionMatrix.benchmark(
+...     dataset = dataset,
+...     callback = callback
+... )
+
+>>> confusion_matrix.matrix
+array([
+    [0., 0., 0., 0.],
+    [0., 1., 0., 1.],
+    [0., 1., 1., 0.],
+    [1., 1., 0., 0.]
+])
+```
+
+- Added [#173](https://github.com/roboflow/supervision/pull/173): [`Detections.from_mmdetection`](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.from_mmdetection) to enable seamless integration with [MMDetection](https://github.com/open-mmlab/mmdetection) framework.
+
+- Added [#130](https://github.com/roboflow/supervision/issues/130): ability to [install](https://roboflow.github.io/supervision/) package in `headless` or `desktop` mode.
+
+- Changed [#180](https://github.com/roboflow/supervision/pull/180): packing method from `setup.py` to `pyproject.toml`.
+
+- Fixed [#188](https://github.com/roboflow/supervision/issues/188): [`sv.DetectionDataset.from_cooc`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.from_coco) can't be loaded when there are images without annotations.
+
+- Fixed [#226](https://github.com/roboflow/supervision/issues/226): [`sv.DetectionDataset.from_yolo`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.from_yolo) can't load background instances.
+
+### 0.11.1 <small>June 29, 2023</small>
+
+- Fix [#165](https://github.com/roboflow/supervision/pull/165): [`as_folder_structure`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.ClassificationDataset.as_folder_structure) fails to save [`sv.ClassificationDataset`](https://roboflow.github.io/supervision/dataset/core/#classificationdataset) when it is result of inference.
+
 ### 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
@@ -16,7 +63,7 @@
 ... )
 ```
 
-- 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
@@ -40,13 +87,13 @@
 ['cat', 'dog', 'person']
 ```
 
-- Added [[#162](https://github.com/roboflow/supervision/pull/162)]: additional `start` and `end` arguments to [`sv.get_video_frames_generator`](https://roboflow.github.io/supervision/utils/video/#get_video_frames_generator) allowing to generate frames only for a selected part of the video.
+- Added [#162](https://github.com/roboflow/supervision/pull/162): additional `start` and `end` arguments to [`sv.get_video_frames_generator`](https://roboflow.github.io/supervision/utils/video/#get_video_frames_generator) allowing to generate frames only for a selected part of the video.
 
-- Fix [[#157](https://github.com/roboflow/supervision/pull/157)]: incorrect loading of YOLO dataset class names from `data.yaml`.
+- Fix [#157](https://github.com/roboflow/supervision/pull/157): incorrect loading of YOLO dataset class names from `data.yaml`.
 
 ### 0.10.0 <small>June 14, 2023</small>
 
-- Added [[#125](https://github.com/roboflow/supervision/pull/125)]: ability to load and save [`sv.ClassificationDataset`](https://roboflow.github.io/supervision/dataset/core/#classificationdataset) in a folder structure format.
+- Added [#125](https://github.com/roboflow/supervision/pull/125): ability to load and save [`sv.ClassificationDataset`](https://roboflow.github.io/supervision/dataset/core/#classificationdataset) in a folder structure format.
 
 ```python
 >>> import supervision as sv
@@ -60,17 +107,17 @@
 ... )
 ```
 
-- 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 [#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.
+- 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>
 
-- Added [[#118](https://github.com/roboflow/supervision/pull/118)]: ability to select [`sv.Detections`](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.__getitem__) by index, list of indexes or slice. Here is an example illustrating the new selection methods.
+- Added [#118](https://github.com/roboflow/supervision/pull/118): ability to select [`sv.Detections`](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.__getitem__) by index, list of indexes or slice. Here is an example illustrating the new selection methods.
 
 ```python
 >>> import supervision as sv
@@ -84,11 +131,11 @@
 2
 ```
 
-- 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 [#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 [#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.
+- 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.
 
 ```python
 >>> import supervision as sv
@@ -98,12 +145,12 @@
 ...         sink.save_image(image=image)
 ```
 
-- Fixed [[#106](https://github.com/roboflow/supervision/issues/106)]: inconvenient handling of [`sv.PolygonZone`](https://roboflow.github.io/supervision/detection/tools/polygon_zone/#polygonzone) coordinates. Now `sv.PolygonZone` accepts coordinates in the form of `[[x1, y1], [x2, y2], ...]` that can be both integers and floats.
+- Fixed [#106](https://github.com/roboflow/supervision/issues/106): inconvenient handling of [`sv.PolygonZone`](https://roboflow.github.io/supervision/detection/tools/polygon_zone/#polygonzone) coordinates. Now `sv.PolygonZone` accepts coordinates in the form of `[[x1, y1], [x2, y2], ...]` that can be both integers and floats.
 
 ### 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): 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). 
 
 ```python
 >>> import roboflow
@@ -127,7 +174,7 @@
 ['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
@@ -139,27 +186,27 @@
 (700, 300)
 ```
 
-- Changed [[#100](https://github.com/roboflow/supervision/pull/100)]: default value of `approximation_percentage` parameter from `0.75` to `0.0` in `DetectionDataset.as_yolo` and `DetectionDataset.as_pascal_voc`.
+- Changed [#100](https://github.com/roboflow/supervision/pull/100): default value of `approximation_percentage` parameter from `0.75` to `0.0` in `DetectionDataset.as_yolo` and `DetectionDataset.as_pascal_voc`.
 
 ### 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 [[#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.
+- 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 [#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)]: 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.
-- Changed [[#71](https://github.com/roboflow/supervision/pull/71)]: `generate_2d_mask` to `polygon_to_mask`.
+- 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.
+- Changed [#71](https://github.com/roboflow/supervision/pull/71): `generate_2d_mask` to `polygon_to_mask`.
 
 ### 0.5.2 <small>April 13, 2023</small>
 
-- Fixed [[#63](https://github.com/roboflow/supervision/pull/63)]: `LineZone.trigger` function expects 4 values instead of 5.
+- Fixed [#63](https://github.com/roboflow/supervision/pull/63): `LineZone.trigger` function expects 4 values instead of 5.
 
 ### 0.5.1 <small>April 12, 2023</small>
 
@@ -168,28 +215,28 @@
 
 ### 0.5.0 <small>April 10, 2023</small>
 
-- Added [[#58](https://github.com/roboflow/supervision/pull/58)]: `Detections.mask` to enable segmentation support.
-- Added [[#58](https://github.com/roboflow/supervision/pull/58)]: `MaskAnnotator` to allow easy `Detections.mask` annotation.
-- 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.
+- Added [#58](https://github.com/roboflow/supervision/pull/58): `Detections.mask` to enable segmentation support.
+- Added [#58](https://github.com/roboflow/supervision/pull/58): `MaskAnnotator` to allow easy `Detections.mask` annotation.
+- 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> 
 
-- 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.
-- Added [[#56](https://github.com/roboflow/supervision/pull/56)]: `plot_images_grid` to allow easy plotting of multiple images on single plot.
-- 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`.
+- 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.
+- Added [#56](https://github.com/roboflow/supervision/pull/56): `plot_images_grid` to allow easy plotting of multiple images on single plot.
+- 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> 
 
-- 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> 
 
-- 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.
+- 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> 
 

docs/index.md

@@ -9,29 +9,65 @@
   </p>
 </div>
 
-## 👋 Welcome
+## 👋 Hello
 
-Supervision is a set of easy-to-use utilities that will come in handy in any computer vision project. 
+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! 
 
-**Supervision** is still in 
-pre-release stage 🚧 Keep your eyes open for potential bugs and be aware that at this stage our API is still fluid and may change.
-
-## 💻 How to Install
+## 💻 Install
 
 You can install `supervision` with pip in a 
-[**3.11>=Python>=3.7**](https://www.python.org/) environment.
+[**3.11>=Python>=3.8**](https://www.python.org/) environment.
 
-!!! example "Pip install method (recommended)"
+!!! example "pip install (recommended)"
 
-    ```bash
-    pip install supervision
-    ```
+    === "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. 
 
-!!! example "Git clone method (for development)"
+        ```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.
 
-    ```bash
-    git https://github.com/roboflow/supervision.git
-    cd supervision
-    pip install -e '.[dev]'
-    ```
-    See contributing section to know more about contributing to the project
+        ```bash
+        pip install supervision[desktop]
+        ```
+
+!!! example "git clone (for development)"
+
+    === "virtualenv"
+
+        ```bash
+        # 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

@@ -0,0 +1,8 @@
+!!! warning
+
+    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
+
+:::supervision.metrics.detection.ConfusionMatrix

mkdocs.yml

@@ -39,6 +39,8 @@ nav:
             - Polygon Zone: detection/tools/polygon_zone.md
     - Dataset:
         - Core: dataset/core.md
+    - Metrics:
+      - Detection Models: metrics/detection.md
     - Draw:
         - Utils: draw/utils.md
     - Utils:

pyproject.toml

@@ -0,0 +1,75 @@
+[tool.poetry]
+name = "supervision"
+version = "0.12.0"
+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>"]
+readme = "README.md"
+packages = [{include = "supervision"}]
+homepage = "https://github.com/roboflow/supervision"
+repository = "https://github.com/roboflow/supervision"
+documentation = "https://github.com/roboflow/supervision/blob/main/README.md"
+keywords = ["machine-learning", "deep-learning", "vision", "ML", "DL", "AI", "YOLOv5", "YOLOv8", "Roboflow"]
+
+classifiers=[
+    'Intended Audience :: Developers',
+    'Intended Audience :: Science/Research',
+    'License :: OSI Approved :: BSD License',
+    'Programming Language :: Python :: 3',
+    'Programming Language :: Python :: 3.8',
+    'Programming Language :: Python :: 3.9',
+    'Programming Language :: Python :: 3.10',
+    'Programming Language :: Python :: 3.11',
+    'Programming Language :: Python :: 3 :: Only',
+    'Topic :: Software Development',
+    'Topic :: Scientific/Engineering',
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Scientific/Engineering :: Image Recognition",
+    'Typing :: Typed',
+    'Operating System :: Microsoft :: Windows',
+    'Operating System :: POSIX',
+    'Operating System :: Unix',
+    'Operating System :: MacOS'
+]
+
+[tool.poetry.dependencies]
+python = ">=3.8,<3.12.0"
+numpy = "^1.20.0"
+matplotlib = "^3.7.1"
+pyyaml = "^6.0"
+pillow = "^8.4.0"
+opencv-python = { version = "^4.8.0.74", optional = true }
+opencv-python-headless = "^4.8.0.74"
+
+
+[tool.poetry.extras]
+desktop = ["opencv-python"]
+
+
+[tool.poetry.group.dev.dependencies]
+twine = "^4.0.2"
+pytest = "^7.2.2"
+wheel = "^0.40.0"
+notebook = "^6.5.3"
+build = "^0.10.0"
+ruff = "^0.0.280"
+isort = "^5.12.0"
+black = "^23.7.0"
+mypy = "^1.4.1"
+pre-commit = "^3.3.3"
+flake8 = { version = "*", python = ">=3.8.1,<3.12.0" }
+
+
+[tool.poetry.group.docs.dependencies]
+mkdocs-material = "^9.1.4"
+mkdocstrings = {extras = ["python"], version = "^0.20.0"}
+
+[tool.setuptools]
+include-package-data = false
+
+[tool.setuptools.packages.find]
+exclude = ["docs*", "test*"]
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

setup.py

@@ -1,71 +0,0 @@
-import setuptools
-from setuptools import find_packages
-import re
-from pathlib import Path
-
-FILE = Path(__file__).resolve()
-PARENT = FILE.parent  # root directory
-README = (PARENT / "README.md").read_text(encoding="utf-8")
-
-
-def get_version():
-    file = PARENT / 'supervision/__init__.py'
-    return re.search(r'^__version__ = [\'"]([^\'"]*)[\'"]', file.read_text(encoding="utf-8"), re.M)[1]
-    
-
-setuptools.setup(
-    name='supervision',
-    version=get_version(),
-    author='Piotr Skalski',
-    author_email='piotr.skalski92@gmail.com',
-    license='MIT',
-    description='A set of easy-to-use utils that will come in handy in any Computer Vision project',
-    long_description=README,
-    long_description_content_type='text/markdown',
-    url='https://github.com/roboflow/supervision',
-    install_requires=[
-        'numpy>=1.20.0',
-        'opencv-python',
-        'matplotlib',
-        'pyyaml'
-    ],
-    packages=find_packages(exclude=("tests",)),
-    extras_require={
-        'dev': [
-            'flake8',
-            'black==22.3.0',
-            'isort',
-            'twine',
-            'pytest',
-            'wheel',
-            'notebook',
-            'mkdocs-material',
-            'mkdocstrings[python]'
-        ],
-    },
-    classifiers=[
-        'Development Status :: 4 - Beta',
-        'Intended Audience :: Developers',
-        'Intended Audience :: Education',
-        'Intended Audience :: Science/Research',
-        'License :: OSI Approved :: MIT License',
-        'Programming Language :: Python :: 3',
-        'Programming Language :: Python :: 3.7',
-        'Programming Language :: Python :: 3.8',
-        'Programming Language :: Python :: 3.9',
-        'Programming Language :: Python :: 3.10',
-        'Programming Language :: Python :: 3.11',
-        'Programming Language :: Python :: 3 :: Only',
-        'Topic :: Software Development',
-        'Topic :: Scientific/Engineering',
-        "Topic :: Scientific/Engineering :: Artificial Intelligence",
-        "Topic :: Scientific/Engineering :: Image Recognition",
-        'Typing :: Typed',
-        'Operating System :: Microsoft :: Windows',
-        'Operating System :: POSIX',
-        'Operating System :: Unix',
-        'Operating System :: MacOS'
-    ],
-    keywords="machine-learning, deep-learning, vision, ML, DL, AI, YOLOv5, YOLOv8, SAM, Roboflow",
-    python_requires='>=3.7',
-)

supervision/__init__.py

@@ -1,4 +1,11 @@
-__version__ = "0.11.0"
+import importlib.metadata as importlib_metadata
+
+try:
+    # This will read version from pyproject.toml
+    __version__ = importlib_metadata.version(__package__ or __name__)
+except importlib_metadata.PackageNotFoundError:
+    __version__ = "development"
+
 
 from supervision.classification.core import Classifications
 from supervision.dataset.core import (
@@ -23,6 +30,7 @@ from supervision.draw.color import Color, ColorPalette
 from supervision.draw.utils import draw_filled_rectangle, draw_polygon, draw_text
 from supervision.geometry.core import Point, Position, Rect
 from supervision.geometry.utils import get_polygon_center
+from supervision.metrics.detection import ConfusionMatrix
 from supervision.utils.file import list_files_with_extensions
 from supervision.utils.image import ImageSink, crop
 from supervision.utils.notebook import plot_image, plot_images_grid

supervision/dataset/core.py

@@ -584,7 +584,7 @@ class ClassificationDataset(BaseDataset):
             class_id = (
                 classification.class_id[0]
                 if classification.confidence is None
-                else classification.get_top_k(1)[0]
+                else classification.get_top_k(1)[0][0]
             )
             class_name = self.classes[class_id]
             image_path = os.path.join(root_directory_path, class_name, image_name)

supervision/dataset/formats/coco.py

@@ -6,7 +6,10 @@ from typing import Dict, List, Tuple
 import cv2
 import numpy as np
 
-from supervision.dataset.utils import approximate_mask_with_polygons
+from supervision.dataset.utils import (
+    approximate_mask_with_polygons,
+    map_detections_class_id,
+)
 from supervision.detection.core import Detections
 from supervision.detection.utils import polygon_to_mask
 from supervision.utils.file import read_json_file, save_json_file
@@ -19,6 +22,18 @@ def coco_categories_to_classes(coco_categories: List[dict]) -> List[str]:
     ]
 
 
+def build_coco_class_index_mapping(
+    coco_categories: List[dict], target_classes: List[str]
+) -> Dict[int, int]:
+    source_class_to_index = {
+        category["name"]: category["id"] for category in coco_categories
+    }
+    return {
+        source_class_to_index[target_class_name]: target_class_index
+        for target_class_index, target_class_name in enumerate(target_classes)
+    }
+
+
 def classes_to_coco_categories(classes: List[str]) -> List[dict]:
     return [
         {
@@ -124,6 +139,9 @@ def load_coco_annotations(
 ) -> Tuple[List[str], Dict[str, np.ndarray], Dict[str, Detections]]:
     coco_data = read_json_file(file_path=annotations_path)
     classes = coco_categories_to_classes(coco_categories=coco_data["categories"])
+    class_index_mapping = build_coco_class_index_mapping(
+        coco_categories=coco_data["categories"], target_classes=classes
+    )
     coco_images = coco_data["images"]
     coco_annotations_groups = group_coco_annotations_by_image_id(
         coco_annotations=coco_data["annotations"]
@@ -147,6 +165,10 @@ def load_coco_annotations(
             resolution_wh=(image_width, image_height),
             with_masks=force_masks,
         )
+        annotation = map_detections_class_id(
+            source_to_target_mapping=class_index_mapping,
+            detections=annotation,
+        )
 
         images[image_name] = image
         annotations[image_name] = annotation
@@ -177,8 +199,7 @@ def save_coco_annotations(
     coco_images = []
     coco_categories = classes_to_coco_categories(classes=classes)
 
-    image_id = 0
-    annotation_id = 0
+    image_id, annotation_id = 1, 1
     for image_name, image in images.items():
         image_height, image_width, _ = image.shape
 

supervision/dataset/formats/yolo.py

@@ -52,24 +52,16 @@ def _polygons_to_masks(
     )
 
 
-def _pair_image_with_annotation(
-    image_paths: List[Union[str, Path]], annotation_paths: List[Union[str, Path]]
-) -> List[Tuple[Union[str, Path], Union[str, Path]]]:
-    image_dict = {p.stem: p for p in image_paths}
-    return [
-        (image_dict[annotation_path.stem], annotation_path)
-        for annotation_path in annotation_paths
-        if annotation_path.stem in image_dict
-    ]
-
-
 def _with_mask(lines: List[str]) -> bool:
     return any([len(line.split()) > 5 for line in lines])
 
 
 def _extract_class_names(file_path: str) -> List[str]:
     data = read_yaml_file(file_path=file_path)
-    return data["names"]
+    names = data["names"]
+    if isinstance(names, dict):
+        names = [names[key] for key in sorted(names.keys())]
+    return names
 
 
 def _image_name_to_annotation_name(image_name: str) -> str:
@@ -137,14 +129,21 @@ def load_yolo_annotations(
     annotation_paths = list_files_with_extensions(
         directory=annotations_directory_path, extensions=["txt"]
     )
-    path_pairs = _pair_image_with_annotation(
-        image_paths=image_paths, annotation_paths=annotation_paths
-    )
+
     classes = _extract_class_names(file_path=data_yaml_path)
     images = {}
     annotations = {}
-    for image_path, annotation_path in path_pairs:
+
+    for image_path in image_paths:
+        image_name = Path(image_path).stem
         image = cv2.imread(str(image_path))
+
+        annotation_path = os.path.join(annotations_directory_path, f"{image_name}.txt")
+        if not os.path.exists(annotation_path):
+            images[image_path.name] = image
+            annotations[image_path.name] = Detections.empty()
+            continue
+
         lines = read_txt_file(str(annotation_path))
         h, w, _ = image.shape
         resolution_wh = (w, h)

supervision/dataset/utils.py

@@ -83,9 +83,11 @@ def map_detections_class_id(
         )
 
     detections_copy = copy.deepcopy(detections)
-    detections_copy.class_id = np.vectorize(source_to_target_mapping.get)(
-        detections_copy.class_id
-    )
+
+    if len(detections) > 0:
+        detections_copy.class_id = np.vectorize(source_to_target_mapping.get)(
+            detections_copy.class_id
+        )
 
     return detections_copy
 

supervision/detection/core.py

@@ -228,6 +228,35 @@ class Detections:
             class_id=yolo_nas_results.prediction.labels.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.
+        Also supported for [mmyolo](https://github.com/open-mmlab/mmyolo)
+
+        Args:
+        mmdet_results (mmdet.structures.DetDataSample): The output Results instance from MMDetection
+
+        Returns:
+        Detections: A new Detections object.
+
+        Example:
+            ```python
+            >>> import cv2
+            >>> import supervision as sv
+            >>> 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]
+            >>> detections = sv.Detections.from_mmdet(mmdet_result)
+            ```
+        """
+        return cls(
+            xyxy=mmdet_results.pred_instances.bboxes.cpu().numpy(),
+            confidence=mmdet_results.pred_instances.scores.cpu().numpy(),
+            class_id=mmdet_results.pred_instances.labels.cpu().numpy().astype(int),
+        )
+
     @classmethod
     def from_transformers(cls, transformers_results: dict) -> Detections:
         """

supervision/metrics/detection.py

@@ -0,0 +1,458 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Callable, List, Optional, Tuple
+
+import matplotlib
+import matplotlib.pyplot as plt
+import numpy as np
+
+from supervision.dataset.core import DetectionDataset
+from supervision.detection.core import Detections
+from supervision.detection.utils import box_iou_batch
+
+
+@dataclass
+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.
+        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`.
+    """
+
+    matrix: np.ndarray
+    classes: List[str]
+    conf_threshold: float
+    iou_threshold: float
+
+    @classmethod
+    def from_detections(
+        cls,
+        predictions: List[Detections],
+        targets: List[Detections],
+        classes: List[str],
+        conf_threshold: float = 0.3,
+        iou_threshold: float = 0.5,
+    ) -> ConfusionMatrix:
+        """
+        Calculate confusion matrix based on predicted and ground-truth detections.
+
+        Args:
+            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`.
+
+        Returns:
+            ConfusionMatrix: New instance of ConfusionMatrix.
+
+        Example:
+            ```python
+            >>> import supervision as sv
+
+            >>> targets = [
+            ...     sv.Detections(...),
+            ...     sv.Detections(...)
+            ... ]
+
+            >>> predictions = [
+            ...     sv.Detections(...),
+            ...     sv.Detections(...)
+            ... ]
+
+            >>> confusion_matrix = sv.ConfusionMatrix.from_detections(
+            ...     predictions=predictions,
+            ...     targets=target,
+            ...     classes=['person', ...]
+            ... )
+
+            >>> confusion_matrix.matrix
+            array([
+                [0., 0., 0., 0.],
+                [0., 1., 0., 1.],
+                [0., 1., 1., 0.],
+                [1., 1., 0., 0.]
+            ])
+            ```
+        """
+
+        prediction_tensors = []
+        target_tensors = []
+        for prediction, target in zip(predictions, targets):
+            prediction_tensors.append(
+                ConfusionMatrix.detections_to_tensor(prediction, with_confidence=True)
+            )
+            target_tensors.append(
+                ConfusionMatrix.detections_to_tensor(target, with_confidence=False)
+            )
+        return cls.from_tensors(
+            predictions=prediction_tensors,
+            targets=target_tensors,
+            classes=classes,
+            conf_threshold=conf_threshold,
+            iou_threshold=iou_threshold,
+        )
+
+    @staticmethod
+    def detections_to_tensor(
+        detections: Detections, with_confidence: bool = False
+    ) -> np.ndarray:
+        if detections.class_id is None:
+            raise ValueError(
+                "ConfusionMatrix can only be calculated for Detections with class_id"
+            )
+
+        arrays_to_concat = [detections.xyxy, np.expand_dims(detections.class_id, 1)]
+
+        if with_confidence:
+            if detections.confidence is None:
+                raise ValueError(
+                    "ConfusionMatrix can only be calculated for Detections with confidence"
+                )
+            arrays_to_concat.append(np.expand_dims(detections.confidence, 1))
+
+        return np.concatenate(arrays_to_concat, axis=1)
+
+    @classmethod
+    def from_tensors(
+        cls,
+        predictions: List[np.ndarray],
+        targets: List[np.ndarray],
+        classes: List[str],
+        conf_threshold: float = 0.3,
+        iou_threshold: float = 0.5,
+    ) -> 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.
+            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`.
+
+        Returns:
+            ConfusionMatrix: New instance of ConfusionMatrix.
+
+        Example:
+            ```python
+            >>> import supervision as sv
+
+            >>> targets = (
+            ...     [
+            ...         array(
+            ...             [
+            ...                 [0.0, 0.0, 3.0, 3.0, 1],
+            ...                 [2.0, 2.0, 5.0, 5.0, 1],
+            ...                 [6.0, 1.0, 8.0, 3.0, 2],
+            ...             ]
+            ...         ),
+            ...         array([1.0, 1.0, 2.0, 2.0, 2]),
+            ...     ]
+            ... )
+
+            >>> predictions = [
+            ...     array(
+            ...         [
+            ...             [0.0, 0.0, 3.0, 3.0, 1, 0.9],
+            ...             [0.1, 0.1, 3.0, 3.0, 0, 0.9],
+            ...             [6.0, 1.0, 8.0, 3.0, 1, 0.8],
+            ...             [1.0, 6.0, 2.0, 7.0, 1, 0.8],
+            ...         ]
+            ...     ),
+            ...     array([[1.0, 1.0, 2.0, 2.0, 2, 0.8]])
+            ... ]
+
+            >>> confusion_matrix = sv.ConfusionMatrix.from_tensors(
+            ...     predictions=predictions,
+            ...     targets=targets,
+            ...     classes=['person', ...]
+            ... )
+
+            >>> confusion_matrix.matrix
+            array([
+                [0., 0., 0., 0.],
+                [0., 1., 0., 1.],
+                [0., 1., 1., 0.],
+                [1., 1., 0., 0.]
+            ])
+            ```
+        """
+        cls._validate_input_tensors(predictions, targets)
+
+        num_classes = len(classes)
+        matrix = np.zeros((num_classes + 1, num_classes + 1))
+        for true_batch, detection_batch in zip(targets, predictions):
+            matrix += cls.evaluate_detection_batch(
+                predictions=detection_batch,
+                targets=true_batch,
+                num_classes=num_classes,
+                conf_threshold=conf_threshold,
+                iou_threshold=iou_threshold,
+            )
+        return cls(
+            matrix=matrix,
+            classes=classes,
+            conf_threshold=conf_threshold,
+            iou_threshold=iou_threshold,
+        )
+
+    @classmethod
+    def _validate_input_tensors(
+        cls, predictions: List[np.ndarray], targets: List[np.ndarray]
+    ):
+        """
+        Checks for shape consistency of input tensors.
+        """
+        if len(predictions) != len(targets):
+            raise ValueError(
+                f"Number of predictions ({len(predictions)}) and 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."
+                )
+            if predictions[0].shape[1] != 6:
+                raise ValueError(
+                    f"Predictions must have shape (N, 6). Got {predictions[0].shape} instead."
+                )
+            if targets[0].shape[1] != 5:
+                raise ValueError(
+                    f"Targets must have shape (N, 5). Got {targets[0].shape} instead."
+                )
+
+    @staticmethod
+    def evaluate_detection_batch(
+        predictions: np.ndarray,
+        targets: np.ndarray,
+        num_classes: int,
+        conf_threshold: float,
+        iou_threshold: float,
+    ) -> np.ndarray:
+        """
+        Calculate confusion matrix for a batch of detections for a single image.
+
+        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.
+            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`.
+
+        Returns:
+            np.ndarray: Confusion matrix based on a single image.
+        """
+        result_matrix = np.zeros((num_classes + 1, num_classes + 1))
+
+        conf_idx = 5
+        confidence = predictions[:, conf_idx]
+        detection_batch_filtered = predictions[confidence > conf_threshold]
+
+        class_id_idx = 4
+        true_classes = np.array(targets[:, class_id_idx], dtype=np.int16)
+        detection_classes = np.array(
+            detection_batch_filtered[:, class_id_idx], dtype=np.int16
+        )
+        true_boxes = targets[:, :class_id_idx]
+        detection_boxes = detection_batch_filtered[:, :class_id_idx]
+
+        iou_batch = box_iou_batch(
+            boxes_true=true_boxes, boxes_detection=detection_boxes
+        )
+        matched_idx = np.asarray(iou_batch > iou_threshold).nonzero()
+
+        if matched_idx[0].shape[0]:
+            matches = np.stack(
+                (matched_idx[0], matched_idx[1], iou_batch[matched_idx]), axis=1
+            )
+            matches = ConfusionMatrix._drop_extra_matches(matches=matches)
+        else:
+            matches = np.zeros((0, 3))
+
+        matched_true_idx, matched_detection_idx, _ = matches.transpose().astype(
+            np.int16
+        )
+
+        for i, true_class_value in enumerate(true_classes):
+            j = matched_true_idx == i
+            if matches.shape[0] > 0 and sum(j) == 1:
+                result_matrix[
+                    true_class_value, detection_classes[matched_detection_idx[j]]
+                ] += 1  # TP
+            else:
+                result_matrix[true_class_value, num_classes] += 1  # FN
+
+        for i, detection_class_value in enumerate(detection_classes):
+            if not any(matched_detection_idx == i):
+                result_matrix[num_classes, detection_class_value] += 1  # FP
+
+        return result_matrix
+
+    @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.
+        """
+        if matches.shape[0] > 0:
+            matches = matches[matches[:, 2].argsort()[::-1]]
+            matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
+            matches = matches[matches[:, 2].argsort()[::-1]]
+            matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
+        return matches
+
+    @classmethod
+    def benchmark(
+        cls,
+        dataset: DetectionDataset,
+        callback: Callable[[np.ndarray], Detections],
+        conf_threshold: float = 0.3,
+        iou_threshold: float = 0.5,
+    ) -> ConfusionMatrix:
+        """
+        Create confusion matrix from dataset and callback function.
+
+        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`.
+
+        Returns:
+            ConfusionMatrix: New instance of ConfusionMatrix.
+
+        Example:
+            ```python
+            >>> import supervision as sv
+            >>> from ultralytics import YOLO
+
+            >>> dataset = sv.DetectionDataset.from_yolo(...)
+
+            >>> model = YOLO(...)
+            >>> def callback(image: np.ndarray) -> sv.Detections:
+            ...     result = model(image)[0]
+            ...     return sv.Detections.from_yolov8(result)
+
+            >>> confusion_matrix = sv.ConfusionMatrix.benchmark(
+            ...     dataset = dataset,
+            ...     callback = callback
+            ... )
+
+            >>> confusion_matrix.matrix
+            array([
+                [0., 0., 0., 0.],
+                [0., 1., 0., 1.],
+                [0., 1., 1., 0.],
+                [1., 1., 0., 0.]
+            ])
+            ```
+        """
+        predictions, targets = [], []
+        for img_name, img in dataset.images.items():
+            predictions_batch = callback(img)
+            predictions.append(predictions_batch)
+            targets_batch = dataset.annotations[img_name]
+            targets.append(targets_batch)
+        return cls.from_detections(
+            predictions=predictions,
+            targets=targets,
+            classes=dataset.classes,
+            conf_threshold=conf_threshold,
+            iou_threshold=iou_threshold,
+        )
+
+    def plot(
+        self,
+        save_path: Optional[str] = None,
+        title: Optional[str] = None,
+        classes: Optional[List[str]] = None,
+        normalize: bool = False,
+        fig_size: Tuple[int, int] = (12, 10),
+    ) -> matplotlib.figure.Figure:
+        """
+        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.
+            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.
+            normalize (bool): If True, normalize the confusion matrix.
+            fig_size (Tuple[int, int]): Size of the plot.
+
+        Returns:
+            matplotlib.figure.Figure: Confusion matrix plot.
+        """
+
+        array = self.matrix.copy()
+
+        if normalize:
+            eps = 1e-8
+            array = array / (array.sum(0).reshape(1, -1) + eps)
+
+        array[array < 0.005] = np.nan
+
+        fig, ax = plt.subplots(figsize=fig_size, tight_layout=True, facecolor="white")
+
+        class_names = classes if classes is not None else self.classes
+        use_labels_for_ticks = class_names is not None and (0 < len(class_names) < 99)
+        if use_labels_for_ticks:
+            x_tick_labels = class_names + ["FN"]
+            y_tick_labels = class_names + ["FP"]
+            num_ticks = len(x_tick_labels)
+        else:
+            x_tick_labels = None
+            y_tick_labels = None
+            num_ticks = len(array)
+        im = ax.imshow(array, cmap="Blues")
+
+        cbar = ax.figure.colorbar(im, ax=ax)
+        cbar.mappable.set_clim(vmin=0, vmax=np.nanmax(array))
+
+        if x_tick_labels is None:
+            tick_interval = 2
+        else:
+            tick_interval = 1
+        ax.set_xticks(np.arange(0, num_ticks, tick_interval), labels=x_tick_labels)
+        ax.set_yticks(np.arange(0, num_ticks, tick_interval), labels=y_tick_labels)
+
+        plt.setp(ax.get_xticklabels(), rotation=90, ha="right", rotation_mode="default")
+
+        labelsize = 10 if num_ticks < 50 else 8
+        ax.tick_params(axis="both", which="both", labelsize=labelsize)
+
+        if num_ticks < 30:
+            for i in range(array.shape[0]):
+                for j in range(array.shape[1]):
+                    n_preds = array[i, j]
+                    if not np.isnan(n_preds):
+                        ax.text(
+                            j,
+                            i,
+                            f"{n_preds:.2f}" if normalize else f"{n_preds:.0f}",
+                            ha="center",
+                            va="center",
+                            color="black"
+                            if n_preds < 0.5 * np.nanmax(array)
+                            else "white",
+                        )
+
+        if title:
+            ax.set_title(title, fontsize=20)
+
+        ax.set_xlabel("Predicted")
+        ax.set_ylabel("True")
+        ax.set_facecolor("white")
+        if save_path:
+            fig.savefig(
+                save_path, dpi=250, facecolor=fig.get_facecolor(), transparent=True
+            )
+        return fig

test/dataset/formats/test_coco.py

@@ -1,11 +1,11 @@
 from contextlib import ExitStack as DoesNotRaise
-from typing import List, Tuple
+from typing import List, Tuple, Dict
 
 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
+    group_coco_annotations_by_image_id, coco_annotations_to_detections, build_coco_class_index_mapping
 
 import numpy as np
 
@@ -290,3 +290,135 @@ def test_coco_annotations_to_detections(
             with_masks=with_masks
         )
         assert result == expected_result
+
+@pytest.mark.parametrize(
+    "coco_categories, target_classes, expected_result, exception",
+    [
+        (
+            [],
+            [],
+            {},
+            DoesNotRaise()
+        ), # empty coco categories
+        (
+            [
+                {
+                    "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()
+        ),  # 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"
+                }
+            ],
+            [
+                "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"
+                }
+            ],
+            [
+                "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"
+                }
+            ],
+            [
+                "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
+) -> None:
+    with exception:
+        result = build_coco_class_index_mapping(
+            coco_categories=coco_categories,
+            target_classes=target_classes
+        )
+        assert result == expected_result

test/dataset/test_core.py

@@ -172,5 +172,4 @@ def test_dataset_merge(
 ) -> None:
     with exception:
         result = DetectionDataset.merge(dataset_list=dataset_list)
-        print(result.images.keys())
         assert result == expected_result

test/dataset/test_utils.py

@@ -204,6 +204,12 @@ def test_build_class_index_mapping(
             mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[1]),
             DoesNotRaise()
         ),  # single mapping
+        (
+                {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]),

test/metrics/test_detection.py

@@ -0,0 +1,402 @@
+from contextlib import ExitStack as DoesNotRaise
+from typing import Optional, Union
+
+import numpy as np
+import pytest
+
+from supervision.detection.core import Detections
+from supervision.metrics.detection import ConfusionMatrix
+from test.utils import mock_detections
+
+CLASSES = np.arange(80)
+NUM_CLASSES = len(CLASSES)
+
+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,
+)
+
+TARGET_TENSORS = [
+    np.array(
+        [
+            [2254, 906, 2447, 1353, 0],
+            [2049, 1133, 2226, 1371, 56],
+            [727, 1224, 838, 1601, 39],
+            [808, 1214, 910, 1564, 39],
+            [6, 52, 1131, 2133, 72],
+            [299, 1225, 512, 1663, 39],
+            [529, 874, 645, 945, 39],
+            [8, 47, 1935, 2135, 72],
+            [2265, 813, 2328, 901, 62],
+        ]
+    )
+]
+
+DETECTIONS = Detections(
+    xyxy=PREDICTIONS[:, :4],
+    confidence=PREDICTIONS[:, 4],
+    class_id=PREDICTIONS[:, 5].astype(int),
+)
+CERTAIN_DETECTIONS = Detections(
+    xyxy=PREDICTIONS[:, :4],
+    confidence=np.ones(len(PREDICTIONS)),
+    class_id=PREDICTIONS[:, 5].astype(int),
+)
+
+DETECTION_TENSORS = [
+    np.concatenate(
+        [
+            det.xyxy,
+            np.expand_dims(det.class_id, 1),
+            np.expand_dims(det.confidence, 1),
+        ],
+        axis=1,
+    )
+    for det in [DETECTIONS]
+]
+CERTAIN_DETECTION_TENSORS = [
+    np.concatenate(
+        [
+            det.xyxy,
+            np.expand_dims(det.class_id, 1),
+            np.ones((len(det), 1)),
+        ],
+        axis=1,
+    )
+    for det in [DETECTIONS]
+]
+
+IDEAL_MATCHES = np.stack(
+    [
+        np.arange(len(PREDICTIONS)),
+        np.arange(len(PREDICTIONS)),
+        np.ones(len(PREDICTIONS)),
+    ],
+    axis=1,
+)
+
+
+def create_empty_conf_matrix(num_classes: int, do_add_dummy_class: bool = True):
+    if do_add_dummy_class:
+        num_classes += 1
+    return np.zeros((num_classes, num_classes))
+
+
+def update_ideal_conf_matrix(conf_matrix: np.ndarray, class_ids: np.ndarray):
+    for class_id, count in zip(*np.unique(class_ids, return_counts=True)):
+        class_id = int(class_id)
+        conf_matrix[class_id, class_id] += count
+    return conf_matrix
+
+
+def worsen_ideal_conf_matrix(
+    conf_matrix: np.ndarray, class_ids: Union[np.ndarray, list]
+):
+    for class_id in class_ids:
+        class_id = int(class_id)
+        conf_matrix[class_id, class_id] -= 1
+        conf_matrix[class_id, 80] += 1
+    return conf_matrix
+
+
+IDEAL_CONF_MATRIX = create_empty_conf_matrix(NUM_CLASSES)
+IDEAL_CONF_MATRIX = update_ideal_conf_matrix(IDEAL_CONF_MATRIX, PREDICTIONS[:, 5])
+
+GOOD_CONF_MATRIX = worsen_ideal_conf_matrix(IDEAL_CONF_MATRIX.copy(), [62, 72])
+
+BAD_CONF_MATRIX = worsen_ideal_conf_matrix(
+    IDEAL_CONF_MATRIX.copy(), [62, 72, 72, 39, 39, 39, 39, 56]
+)
+
+
+@pytest.mark.parametrize(
+    "detections, with_confidence, expected_result, exception",
+    [
+        (
+            Detections.empty(),
+            False,
+            np.empty((0, 5), dtype=np.float32),
+            DoesNotRaise(),
+        ),  # empty detections; no confidence
+        (
+            Detections.empty(),
+            True,
+            np.empty((0, 6), dtype=np.float32),
+            DoesNotRaise(),
+        ),  # empty detections; with confidence
+        (
+            mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[0], confidence=[0.5]),
+            False,
+            np.array([[0, 0, 10, 10, 0]], dtype=np.float32),
+            DoesNotRaise(),
+        ),  # single detection; no confidence
+        (
+            mock_detections(xyxy=[[0, 0, 10, 10]], class_id=[0], confidence=[0.5]),
+            True,
+            np.array([[0, 0, 10, 10, 0, 0.5]], dtype=np.float32),
+            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]),
+            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]),
+            True,
+            np.array([[0, 0, 10, 10, 0, 0.5], [0, 0, 20, 20, 1, 0.2]], dtype=np.float32),
+            DoesNotRaise(),
+        ),  # multiple detections; with confidence
+    ],
+)
+def test_detections_to_tensor(
+    detections: Detections,
+    with_confidence: bool,
+    expected_result: Optional[np.ndarray],
+    exception: Exception
+):
+    with exception:
+        result = ConfusionMatrix.detections_to_tensor(
+            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",
+    [
+        (
+            DETECTION_TENSORS,
+            TARGET_TENSORS,
+            CLASSES,
+            0.2,
+            0.5,
+            IDEAL_CONF_MATRIX,
+            DoesNotRaise(),
+        ),
+        (
+            [],
+            [],
+            CLASSES,
+            0.2,
+            0.5,
+            create_empty_conf_matrix(NUM_CLASSES),
+            DoesNotRaise(),
+        ),
+        (
+            DETECTION_TENSORS,
+            TARGET_TENSORS,
+            CLASSES,
+            0.3,
+            0.5,
+            GOOD_CONF_MATRIX,
+            DoesNotRaise(),
+        ),
+        (
+            DETECTION_TENSORS,
+            TARGET_TENSORS,
+            CLASSES,
+            0.6,
+            0.5,
+            BAD_CONF_MATRIX,
+            DoesNotRaise(),
+        ),
+        (
+            [
+                np.array(
+                    [
+                        [0.0, 0.0, 3.0, 3.0, 0, 0.9],  # correct detection of [0]
+                        [
+                            0.1,
+                            0.1,
+                            3.0,
+                            3.0,
+                            0,
+                            0.9,
+                        ],  # additional detection of [0] - FP
+                        [
+                            6.0,
+                            1.0,
+                            8.0,
+                            3.0,
+                            1,
+                            0.8,
+                        ],  # correct detection with incorrect class
+                        [1.0, 6.0, 2.0, 7.0, 1, 0.8],  # incorrect detection - FP
+                        [
+                            1.0,
+                            2.0,
+                            2.0,
+                            4.0,
+                            1,
+                            0.8,
+                        ],  # incorrect detection with low IoU - FP
+                    ]
+                )
+            ],
+            [
+                np.array(
+                    [
+                        [0.0, 0.0, 3.0, 3.0, 0],  # [0] detected
+                        [2.0, 2.0, 5.0, 5.0, 1],  # [1] undetected - FN
+                        [
+                            6.0,
+                            1.0,
+                            8.0,
+                            3.0,
+                            2,
+                        ],  # [2] correct detection with incorrect class
+                    ]
+                )
+            ],
+            CLASSES[:3],
+            0.6,
+            0.5,
+            np.array([[1, 0, 0, 0], [0, 0, 0, 1], [0, 1, 0, 0], [1, 2, 0, 0]]),
+            DoesNotRaise(),
+        ),
+        (
+            [
+                np.array(
+                    [
+                        [0.0, 0.0, 3.0, 3.0, 0, 0.9],  # correct detection of [0]
+                        [
+                            0.1,
+                            0.1,
+                            3.0,
+                            3.0,
+                            0,
+                            0.9,
+                        ],  # additional detection of [0] - FP
+                        [
+                            6.0,
+                            1.0,
+                            8.0,
+                            3.0,
+                            1,
+                            0.8,
+                        ],  # correct detection with incorrect class
+                        [1.0, 6.0, 2.0, 7.0, 1, 0.8],  # incorrect detection - FP
+                        [
+                            1.0,
+                            2.0,
+                            2.0,
+                            4.0,
+                            1,
+                            0.8,
+                        ],  # incorrect detection with low IoU - FP
+                    ]
+                )
+            ],
+            [
+                np.array(
+                    [
+                        [0.0, 0.0, 3.0, 3.0, 0],  # [0] detected
+                        [2.0, 2.0, 5.0, 5.0, 1],  # [1] undetected - FN
+                        [
+                            6.0,
+                            1.0,
+                            8.0,
+                            3.0,
+                            2,
+                        ],  # [2] correct detection with incorrect class
+                    ]
+                )
+            ],
+            CLASSES[:3],
+            0.6,
+            1.0,
+            np.array([[0, 0, 0, 1], [0, 0, 0, 1], [0, 0, 0, 1], [2, 3, 0, 0]]),
+            DoesNotRaise(),
+        ),
+    ],
+)
+def test_from_tensors(
+    predictions,
+    targets,
+    classes,
+    conf_threshold,
+    iou_threshold,
+    expected_result: Optional[np.ndarray],
+    exception: Exception,
+):
+    with exception:
+        result = ConfusionMatrix.from_tensors(
+            predictions=predictions,
+            targets=targets,
+            classes=classes,
+            conf_threshold=conf_threshold,
+            iou_threshold=iou_threshold,
+        )
+
+        assert result.matrix.diagonal().sum() == expected_result.diagonal().sum()
+        assert np.array_equal(result.matrix, expected_result)
+
+
+@pytest.mark.parametrize(
+    "predictions, targets, num_classes, conf_threshold, iou_threshold, expected_result, exception",
+    [
+        (
+            DETECTION_TENSORS[0],
+            CERTAIN_DETECTION_TENSORS[0],
+            NUM_CLASSES,
+            0.2,
+            0.5,
+            IDEAL_CONF_MATRIX,
+            DoesNotRaise(),
+        )
+    ],
+)
+def test_evaluate_detection_batch(
+    predictions,
+    targets,
+    num_classes,
+    conf_threshold,
+    iou_threshold,
+    expected_result: Optional[np.ndarray],
+    exception: Exception,
+):
+    with exception:
+        result = ConfusionMatrix.evaluate_detection_batch(
+            predictions=predictions,
+            targets=targets,
+            num_classes=num_classes,
+            conf_threshold=conf_threshold,
+            iou_threshold=iou_threshold,
+        )
+
+        assert result.diagonal().sum() == result.sum()
+        assert np.array_equal(result, expected_result)
+
+
+@pytest.mark.parametrize(
+    "matches, expected_result, exception",
+    [
+        (
+            IDEAL_MATCHES,
+            IDEAL_MATCHES,
+            DoesNotRaise(),
+        )
+    ],
+)
+def test_drop_extra_matches(
+    matches,
+    expected_result: Optional[np.ndarray],
+    exception: Exception,
+):
+    with exception:
+        result = ConfusionMatrix._drop_extra_matches(matches)
+
+        assert np.array_equal(result, expected_result)

test/utils.py

@@ -2,18 +2,22 @@ from typing import List
 
 import numpy as np
 
-from supervision import Detections
+from supervision.detection.core import Detections
 
 
 def mock_detections(
     xyxy: List[List[float]],
     confidence: List[float] = None,
     class_id: List[int] = None,
-    tracker_id: List[int] = None
+    tracker_id: List[int] = None,
 ) -> Detections:
     return Detections(
         xyxy=np.array(xyxy, dtype=np.float32),
-        confidence=confidence if confidence is None else np.array(confidence, dtype=np.float32),
+        confidence=confidence
+        if confidence is None
+        else np.array(confidence, dtype=np.float32),
         class_id=class_id if class_id is None else np.array(class_id, dtype=int),
-        tracker_id=tracker_id if tracker_id is None else np.array(tracker_id, dtype=int)
+        tracker_id=tracker_id
+        if tracker_id is None
+        else np.array(tracker_id, dtype=int),
     )