diff --git a/.github/workflows/docs.yml b/.github/workflows/publish-dev-docs.yml similarity index 100% rename from .github/workflows/docs.yml rename to .github/workflows/publish-dev-docs.yml diff --git a/.github/workflows/publish-release-docs.yml b/.github/workflows/publish-release-docs.yml new file mode 100644 index 00000000..22710033 --- /dev/null +++ b/.github/workflows/publish-release-docs.yml @@ -0,0 +1,55 @@ +name: Supervision Release Documentation Workflow πŸ“š +on: + workflow_dispatch: + +concurrency: + group: ${{ github.workflow }}-${{ github.event_name == 'push' && github.ref}} + cancel-in-progress: true + +permissions: + contents: write + pages: write + pull-requests: write + + +jobs: + doc-build-deploy: + runs-on: ubuntu-latest + strategy: + matrix: + python-version: ["3.10"] + steps: + - name: πŸ›ŽοΈ Checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + ref: ${{ github.head_ref }} + + - name: 🐍 Set up Python + uses: actions/setup-python@v5 + with: + python-version: '3.10' + - name: πŸ“¦ Install mkdocs-material + run: pip install "mkdocs-material" + - name: πŸ“¦ Install mkdocstrings[python] + run: pip install "mkdocstrings[python]" + - name: πŸ“¦ Install mkdocs-material[imaging] + run: pip install "mkdocs-material[imaging]" + - name: πŸ“¦ Install mike + run: pip install "mike" + - name: πŸ“¦ Install mkdocs-git-revision-date-localized-plugin + run: pip install "mkdocs-git-revision-date-localized-plugin" + - name: πŸ“¦ Install JupyterLab + run: pip install jupyterlab + - name: πŸ“¦ Install mkdocs-jupyter + run: pip install mkdocs-jupyter + - name: πŸ“¦ Install mkdocs-git-committers-plugin-2 + run: pip install mkdocs-git-committers-plugin-2 + - name: βš™οΈ Configure git for github-actions πŸ‘· + run: | + git config --global user.name "github-actions[bot]" + git config --global user.email "41898282+github-actions[bot]@users.noreply.github.com" + - name: πŸš€ Deploy MkDoc-Material πŸ“š + run: | + latest_tag=$(git describe --tags `git rev-list --tags --max-count=1`) + MKDOCS_GIT_COMMITTERS_APIKEY=${{ secrets.GITHUB_TOKEN }} mike deploy --push --update-aliases $latest_tag latest diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index 4c2b1a7e..c0903f3a 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -45,7 +45,7 @@ repos: - repo: https://github.com/astral-sh/ruff-pre-commit - rev: v0.3.5 + rev: v0.4.2 hooks: - id: ruff args: [--fix, --exit-non-zero-on-fix] diff --git a/README.md b/README.md index 7d280b57..0894a6a4 100644 --- a/README.md +++ b/README.md @@ -71,16 +71,15 @@ len(detections) ```python import cv2 import supervision as sv - from inference.models.utils import get_roboflow_model + from inference import get_model image = cv2.imread(...) - model = get_roboflow_model(model_id="yolov8s-640", api_key=) + model = get_model(model_id="yolov8s-640", api_key=) result = model.infer(image)[0] detections = sv.Detections.from_inference(result) len(detections) - #Β 5 - + # 5 ``` @@ -217,19 +216,23 @@ len(dataset) ## 🎬 tutorials -

-Speed Estimation & Vehicle Tracking | Computer Vision | Open Source -Speed Estimation & Vehicle Tracking | Computer Vision | Open Source -

Created: 11 Jan 2024 | Updated: 11 Jan 2024
-
Learn how to track and estimate the speed of vehicles using YOLO, ByteTrack, and Roboflow Inference. This comprehensive tutorial covers object detection, multi-object tracking, filtering detections, perspective transformation, speed estimation, visualization improvements, and more.

+Want to learn how to use Supervision? Explore our [how-to guides](https://supervision.roboflow.com/develop/how_to/detect_and_annotate/), [end-to-end examples](https://github.com/roboflow/supervision/tree/develop/examples), and [cookbooks](https://supervision.roboflow.com/develop/cookbooks/)!

-Traffic Analysis with YOLOv8 and ByteTrack - Vehicle Detection and Tracking -Traffic Analysis with YOLOv8 and ByteTrack - Vehicle Detection and Tracking -

Created: 6 Sep 2023 | Updated: 6 Sep 2023
-
In this video, we explore real-time traffic analysis using YOLOv8 and ByteTrack to detect and track vehicles on aerial images. Harnessing the power of Python and Supervision, we delve deep into assigning cars to specific entry zones and understanding their direction of movement. By visualizing their paths, we gain insights into traffic flow across bustling roundabouts...

+Dwell Time Analysis with Computer Vision | Real-Time Stream Processing +Dwell Time Analysis with Computer Vision | Real-Time Stream Processing +
Created: 5 Apr 2024
+
Learn how to use computer vision to analyze wait times and optimize processes. This tutorial covers object detection, tracking, and calculating time spent in designated zones. Use these techniques to improve customer experience in retail, traffic management, or other scenarios.

+ +
+ +

+Speed Estimation & Vehicle Tracking | Computer Vision | Open Source +Speed Estimation & Vehicle Tracking | Computer Vision | Open Source +

Created: 11 Jan 2024
+
Learn how to track and estimate the speed of vehicles using YOLO, ByteTrack, and Roboflow Inference. This comprehensive tutorial covers object detection, multi-object tracking, filtering detections, perspective transformation, speed estimation, visualization improvements, and more.

## πŸ’œ built with supervision diff --git a/docs/assets.md b/docs/assets.md index 7e0d7dff..3fd293ee 100644 --- a/docs/assets.md +++ b/docs/assets.md @@ -19,13 +19,13 @@ as an extra within the Supervision package. ```
-

download_assets

+

download_assets

:::supervision.assets.downloader.download_assets
-

VideoAssets

+

VideoAssets

:::supervision.assets.list.VideoAssets diff --git a/docs/changelog.md b/docs/changelog.md index 2c5d7ae1..47d160aa 100644 --- a/docs/changelog.md +++ b/docs/changelog.md @@ -1,3 +1,68 @@ +### 0.20.0 April 24, 2024 + +- Added [#1128](https://github.com/roboflow/supervision/pull/1128): [`sv.KeyPoints`](/0.20.0/keypoint/core/#supervision.keypoint.core.KeyPoints) to provide initial support for pose estimation and broader keypoint detection models. + +- Added [#1128](https://github.com/roboflow/supervision/pull/1128): [`sv.EdgeAnnotator`](/0.20.0/keypoint/annotators/#supervision.keypoint.annotators.EdgeAnnotator) and [`sv.VertexAnnotator`](/0.20.0/keypoint/annotators/#supervision.keypoint.annotators.VertexAnnotator) to enable rendering of results from keypoint detection models. + +```python +import cv2 +import supervision as sv +from ultralytics import YOLO + +image = cv2.imread() +model = YOLO('yolov8l-pose') + +result = model(image, verbose=False)[0] +keypoints = sv.KeyPoints.from_ultralytics(result) + +edge_annotators = sv.EdgeAnnotator(color=sv.Color.GREEN, thickness=5) +annotated_image = edge_annotators.annotate(image.copy(), keypoints) +``` + +- Changed [#1037](https://github.com/roboflow/supervision/pull/1037): [`sv.LabelAnnotator`](/0.20.0/annotators/#supervision.annotators.core.LabelAnnotator) by adding an additional `corner_radius` argument that allows for rounding the corners of the bounding box. + +- Changed [#1109](https://github.com/roboflow/supervision/pull/1109): [`sv.PolygonZone`](/0.20.0/detection/tools/polygon_zone/#supervision.detection.tools.polygon_zone.PolygonZone) such that the `frame_resolution_wh` argument is no longer required to initialize `sv.PolygonZone`. + +!!! failure "Deprecated" + + The `frame_resolution_wh` parameter in `sv.PolygonZone` is deprecated and will be removed in `supervision-0.24.0`. + +- Changed [#1084](https://github.com/roboflow/supervision/pull/1084): [`sv.get_polygon_center`](/0.20.0/utils/geometry/#supervision.geometry.core.utils.get_polygon_center) to calculate a more accurate polygon centroid. + +- Changed [#1069](https://github.com/roboflow/supervision/pull/1069): [`sv.Detections.from_transformers`](/0.20.0/detection/core/#supervision.detection.core.Detections.from_transformers) by adding support for Transformers segmentation models and extract class names values. + +```python +import torch +import supervision as sv +from PIL import Image +from transformers import DetrImageProcessor, DetrForSegmentation + +processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50-panoptic") +model = DetrForSegmentation.from_pretrained("facebook/detr-resnet-50-panoptic") + +image = Image.open() +inputs = processor(images=image, return_tensors="pt") + +with torch.no_grad(): + outputs = model(**inputs) + +width, height = image.size +target_size = torch.tensor([[height, width]]) +results = processor.post_process_segmentation( + outputs=outputs, target_sizes=target_size)[0] +detections = sv.Detections.from_transformers(results, id2label=model.config.id2label) + +mask_annotator = sv.MaskAnnotator() +label_annotator = sv.LabelAnnotator(text_position=sv.Position.CENTER) + +annotated_image = mask_annotator.annotate( + scene=image, detections=detections) +annotated_image = label_annotator.annotate( + scene=annotated_image, detections=detections) +``` + +- Fixed [#787](https://github.com/roboflow/supervision/pull/787): [`sv.ByteTrack.update_with_detections`](/0.20.0/trackers/#supervision.tracker.byte_tracker.core.ByteTrack.update_with_detections) which was removing segmentation masks while tracking. Now, `ByteTrack` can be used alongside segmentation models. + ### 0.19.0 March 15, 2024 - Added [#818](https://github.com/roboflow/supervision/pull/818): [`sv.CSVSink`](/0.19.0/detection/tools/save_detections/#supervision.detection.tools.csv_sink.CSVSink) allowing for the straightforward saving of image, video, or stream inference results in a `.csv` file. diff --git a/docs/deprecated.md b/docs/deprecated.md index 35c332e4..5834b05f 100644 --- a/docs/deprecated.md +++ b/docs/deprecated.md @@ -12,7 +12,8 @@ These features are phased out due to better alternatives or potential issues in - The method `Color.green()` is deprecated and will be removed in `supervision-0.22.0`. Use the constant `Color.GREEN` instead. - The method `Color.blue()` is deprecated and will be removed in `supervision-0.22.0`. Use the constant `Color.BLUE` instead. - The method [`ColorPalette.default()`](draw/color.md/#supervision.draw.color.ColorPalette.default) is deprecated and will be removed in `supervision-0.22.0`. Use the constant [`ColorPalette.DEFAULT`](draw/color.md/#supervision.draw.color.ColorPalette.DEFAULT) instead. -- `BoxAnnotator` is deprecated and will be removed in `supervision-0.22.0`. Use [`BoundingBoxAnnotator`](annotators.md/#supervision.annotators.core.BoundingBoxAnnotator) and [`LabelAnnotator`](annotators.md/#supervision.annotators.core.LabelAnnotator) instead. +- `BoxAnnotator` is deprecated and will be removed in `supervision-0.22.0`. Use [`BoundingBoxAnnotator`](detection/annotators.md/#supervision.annotators.core.BoundingBoxAnnotator) and [`LabelAnnotator`](detection/annotators.md/#supervision.annotators.core.LabelAnnotator) instead. - The method [`FPSMonitor.__call__`](utils/video.md/#supervision.utils.video.FPSMonitor.__call__) is deprecated and will be removed in `supervision-0.22.0`. Use the attribute [`FPSMonitor.fps`](utils/video.md/#supervision.utils.video.FPSMonitor.fps) instead. - The `track_buffer`, `track_thresh`, and `match_thresh` parameters in [`ByterTrack`](trackers.md/#supervision.tracker.byte_tracker.core.ByteTrack) are deprecated and will be removed in `supervision-0.23.0`. Use `lost_track_buffer,` `track_activation_threshold`, and `minimum_matching_threshold` instead. - The `triggering_position ` parameter in [`sv.PolygonZone`](detection/tools/polygon_zone.md/#supervision.detection.tools.polygon_zone.PolygonZone) is deprecated and will be removed in `supervision-0.23.0`. Use `triggering_anchors ` instead. +- The `frame_resolution_wh ` parameter in [`sv.PolygonZone`](detection/tools/polygon_zone.md/#supervision.detection.tools.polygon_zone.PolygonZone) is deprecated and will be removed in `supervision-0.24.0`. diff --git a/docs/annotators.md b/docs/detection/annotators.md similarity index 100% rename from docs/annotators.md rename to docs/detection/annotators.md diff --git a/docs/detection/metrics.md b/docs/detection/metrics.md new file mode 100644 index 00000000..a68f0f96 --- /dev/null +++ b/docs/detection/metrics.md @@ -0,0 +1,17 @@ +--- +comments: true +--- + +# Metrics + +
+

ConfusionMatrix

+
+ +:::supervision.metrics.detection.ConfusionMatrix + +
+

MeanAveragePrecision

+
+ +:::supervision.metrics.detection.MeanAveragePrecision diff --git a/docs/detection/utils.md b/docs/detection/utils.md index cc4eff5d..abacdc21 100644 --- a/docs/detection/utils.md +++ b/docs/detection/utils.md @@ -6,67 +6,67 @@ status: new # Detection Utils
-

box_iou_batch

+

box_iou_batch

:::supervision.detection.utils.box_iou_batch
-

mask_iou_batch

+

mask_iou_batch

:::supervision.detection.utils.mask_iou_batch
-

box_non_max_suppression

+

box_non_max_suppression

:::supervision.detection.utils.box_non_max_suppression
-

mask_non_max_suppression

+

mask_non_max_suppression

:::supervision.detection.utils.mask_non_max_suppression
-

polygon_to_mask

+

polygon_to_mask

:::supervision.detection.utils.polygon_to_mask
-

mask_to_xyxy

+

mask_to_xyxy

:::supervision.detection.utils.mask_to_xyxy
-

mask_to_polygons

+

mask_to_polygons

:::supervision.detection.utils.mask_to_polygons
-

polygon_to_xyxy

+

polygon_to_xyxy

:::supervision.detection.utils.polygon_to_xyxy
-

filter_polygons_by_area

+

filter_polygons_by_area

:::supervision.detection.utils.filter_polygons_by_area
-

move_boxes

+

move_boxes

:::supervision.detection.utils.move_boxes
-

scale_boxes

+

scale_boxes

:::supervision.detection.utils.scale_boxes diff --git a/docs/draw/color.md b/docs/draw/color.md deleted file mode 100644 index c702814a..00000000 --- a/docs/draw/color.md +++ /dev/null @@ -1,13 +0,0 @@ ---- -comments: true ---- - -# Color - -:::supervision.draw.color.Color - -
-

ColorPalette

-
- -:::supervision.draw.color.ColorPalette diff --git a/docs/draw/utils.md b/docs/draw/utils.md deleted file mode 100644 index 7975952c..00000000 --- a/docs/draw/utils.md +++ /dev/null @@ -1,53 +0,0 @@ ---- -comments: true ---- - -# Draw Utils - -
-

draw_line

-
- -:::supervision.draw.utils.draw_line - -
-

draw_rectangle

-
- -:::supervision.draw.utils.draw_rectangle - -
-

draw_filled_rectangle

-
- -:::supervision.draw.utils.draw_filled_rectangle - -
-

draw_polygon

-
- -:::supervision.draw.utils.draw_polygon - -
-

draw_text

-
- -:::supervision.draw.utils.draw_text - -
-

draw_image

-
- -:::supervision.draw.utils.draw_image - -
-

calculate_optimal_font_scale

-
- -:::supervision.draw.utils.calculate_optimal_text_scale - -
-

calculate_optimal_line_thickness

-
- -:::supervision.draw.utils.calculate_optimal_line_thickness diff --git a/docs/geometry/core.md b/docs/geometry/core.md deleted file mode 100644 index ca99b626..00000000 --- a/docs/geometry/core.md +++ /dev/null @@ -1,7 +0,0 @@ ---- -comments: true ---- - -# Position - -:::supervision.geometry.core.Position diff --git a/docs/how_to/detect_and_annotate.md b/docs/how_to/detect_and_annotate.md index 221d9ca1..a9a4405e 100644 --- a/docs/how_to/detect_and_annotate.md +++ b/docs/how_to/detect_and_annotate.md @@ -15,7 +15,7 @@ source image. ![basic-annotation](https://media.roboflow.com/supervision_detect_and_annotate_example_1.png) -## Run Inference +## Run Detection First, you'll need to obtain predictions from your object detection or segmentation model. @@ -27,7 +27,7 @@ model. from inference import get_model model = get_model(model_id="yolov8n-640") - image = cv2.imread() + image = cv2.imread() results = model.infer(image)[0] ``` @@ -38,7 +38,7 @@ model. from ultralytics import YOLO model = YOLO("yolov8n.pt") - image = cv2.imread() + image = cv2.imread() results = model(image)[0] ``` @@ -52,7 +52,7 @@ model. processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50") model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50") - image = Image.open() + image = Image.open() inputs = processor(images=image, return_tensors="pt") with torch.no_grad(): @@ -78,7 +78,7 @@ Now that we have predictions from a model, we can load them into Supervision. from inference import get_model model = get_model(model_id="yolov8n-640") - image = cv2.imread() + image = cv2.imread() results = model.infer(image)[0] detections = sv.Detections.from_inference(results) ``` @@ -93,7 +93,7 @@ Now that we have predictions from a model, we can load them into Supervision. from ultralytics import YOLO model = YOLO("yolov8n.pt") - image = cv2.imread() + image = cv2.imread() results = model(image)[0] detections = sv.Detections.from_ultralytics(results) ``` @@ -111,7 +111,7 @@ Now that we have predictions from a model, we can load them into Supervision. processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50") model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50") - image = Image.open() + image = Image.open() inputs = processor(images=image, return_tensors="pt") with torch.no_grad(): @@ -146,7 +146,7 @@ Finally, we can annotate the image with the predictions. Since we are working wi from inference import get_model model = get_model(model_id="yolov8n-640") - image = cv2.imread() + image = cv2.imread() results = model.infer(image)[0] detections = sv.Detections.from_inference(results) @@ -167,7 +167,7 @@ Finally, we can annotate the image with the predictions. Since we are working wi from ultralytics import YOLO model = YOLO("yolov8n.pt") - image = cv2.imread() + image = cv2.imread() results = model(image)[0] detections = sv.Detections.from_ultralytics(results) @@ -191,7 +191,7 @@ Finally, we can annotate the image with the predictions. Since we are working wi processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50") model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50") - image = Image.open() + image = Image.open() inputs = processor(images=image, return_tensors="pt") with torch.no_grad(): @@ -230,7 +230,7 @@ override this behavior by passing a list of custom `labels` to the `annotate` me from inference import get_model model = get_model(model_id="yolov8n-640") - image = cv2.imread() + image = cv2.imread() results = model.infer(image)[0] detections = sv.Detections.from_inference(results) @@ -257,7 +257,7 @@ override this behavior by passing a list of custom `labels` to the `annotate` me from ultralytics import YOLO model = YOLO("yolov8n.pt") - image = cv2.imread() + image = cv2.imread() results = model(image)[0] detections = sv.Detections.from_ultralytics(results) @@ -287,7 +287,7 @@ override this behavior by passing a list of custom `labels` to the `annotate` me processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50") model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50") - image = Image.open() + image = Image.open() inputs = processor(images=image, return_tensors="pt") with torch.no_grad(): @@ -334,7 +334,7 @@ that will allow you to draw masks instead of boxes. from inference import get_model model = get_model(model_id="yolov8n-seg-640") - image = cv2.imread() + image = cv2.imread() results = model.infer(image)[0] detections = sv.Detections.from_inference(results) @@ -355,7 +355,7 @@ that will allow you to draw masks instead of boxes. from ultralytics import YOLO model = YOLO("yolov8n-seg.pt") - image = cv2.imread() + image = cv2.imread() results = model(image)[0] detections = sv.Detections.from_ultralytics(results) diff --git a/docs/how_to/detect_small_objects.md b/docs/how_to/detect_small_objects.md index 9f35a96c..e2d02328 100644 --- a/docs/how_to/detect_small_objects.md +++ b/docs/how_to/detect_small_objects.md @@ -28,7 +28,7 @@ size relative to the image resolution. from inference import get_model model = get_model(model_id="yolov8x-640") - image = cv2.imread() + image = cv2.imread() results = model.infer(image)[0] detections = sv.Detections.from_inference(results) @@ -49,7 +49,7 @@ size relative to the image resolution. from ultralytics import YOLO model = YOLO("yolov8x.pt") - image = cv2.imread() + image = cv2.imread() results = model(image)[0] detections = sv.Detections.from_ultralytics(results) @@ -73,7 +73,7 @@ size relative to the image resolution. processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50") model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50") - image = Image.open() + image = Image.open() inputs = processor(images=image, return_tensors="pt") with torch.no_grad(): @@ -116,7 +116,7 @@ is less effective for ultra-high-resolution images (4K and above). from inference import get_model model = get_model(model_id="yolov8x-1280") - image = cv2.imread() + image = cv2.imread() results = model.infer(image)[0] detections = sv.Detections.from_inference(results) @@ -137,7 +137,7 @@ is less effective for ultra-high-resolution images (4K and above). from ultralytics import YOLO model = YOLO("yolov8x.pt") - image = cv2.imread() + image = cv2.imread() results = model(image, imgsz=1280)[0] detections = sv.Detections.from_ultralytics(results) @@ -171,7 +171,7 @@ objects within each, and aggregating the results. from inference import get_model model = get_model(model_id="yolov8x-640") - image = cv2.imread() + image = cv2.imread() def callback(image_slice: np.ndarray) -> sv.Detections: results = model.infer(image_slice)[0] @@ -198,7 +198,7 @@ objects within each, and aggregating the results. from ultralytics import YOLO model = YOLO("yolov8x.pt") - image = cv2.imread() + image = cv2.imread() def callback(image_slice: np.ndarray) -> sv.Detections: result = model(image_slice)[0] @@ -229,7 +229,7 @@ objects within each, and aggregating the results. processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50") model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50") - image = cv2.imread() + image = cv2.imread() def callback(image_slice: np.ndarray) -> sv.Detections: image_slice = cv2.cvtColor(image_slice, cv2.COLOR_BGR2RGB) diff --git a/docs/how_to/save_detections.md b/docs/how_to/save_detections.md new file mode 100644 index 00000000..94de6c61 --- /dev/null +++ b/docs/how_to/save_detections.md @@ -0,0 +1,299 @@ +--- +comments: true +status: new +--- + +# Save Detections + +Supervision enables an easy way to save detections in .CSV and .JSON files for offline +processing. This guide demonstrates how to perform video inference using the +[Inference](https://github.com/roboflow/inference), +[Ultralytics](https://github.com/ultralytics/ultralytics) or +[Transformers](https://github.com/huggingface/transformers) packages and save their results with +[`sv.CSVSink`](/latest/detection/tools/save_detections/#supervision.detection.tools.csv_sink.CSVSink) and +[`sv.JSONSink`](/latest/detection/tools/save_detections/#supervision.detection.tools.csv_sink.JSONSink). + +## Run Detection + +First, you'll need to obtain predictions from your object detection or segmentation +model. You can learn more on this topic in our +[How to Detect and Annotate](/latest/how_to/detect_and_annotate.md) guide. + +=== "Inference" + + ```python + import supervision as sv + from inference import get_model + + model = get_model(model_id="yolov8n-640") + frames_generator = sv.get_video_frames_generator() + + for frame in frames_generator: + + results = model.infer(image)[0] + detections = sv.Detections.from_inference(results) + ``` + +=== "Ultralytics" + + ```python + import supervision as sv + from ultralytics import YOLO + + model = YOLO("yolov8n.pt") + frames_generator = sv.get_video_frames_generator() + + for frame in frames_generator: + + results = model(frame)[0] + detections = sv.Detections.from_ultralytics(results) + ``` + +=== "Transformers" + + ```python + import torch + import supervision as sv + from transformers import DetrImageProcessor, DetrForObjectDetection + + processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50") + model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50") + frames_generator = sv.get_video_frames_generator() + + for frame in frames_generator: + + frame = sv.cv2_to_pillow(frame) + inputs = processor(images=frame, return_tensors="pt") + + with torch.no_grad(): + outputs = model(**inputs) + + width, height = frame.size + target_size = torch.tensor([[height, width]]) + results = processor.post_process_object_detection( + outputs=outputs, target_sizes=target_size)[0] + detections = sv.Detections.from_transformers(results) + ``` + +## Save Detections as CSV + +To save detections to a `.CSV` file, open our +[`sv.CSVSink`](/latest/detection/tools/save_detections/#supervision.detection.tools.csv_sink.CSVSink) +and then pass the +[`sv.Detections`](/latest/detection/core/#supervision.detection.core.Detections) +object resulting from the inference to it. Its fields are parsed and saved on disk. + +=== "Inference" + + ```{ .py hl_lines="7 12" } + import supervision as sv + from inference import get_model + + model = get_model(model_id="yolov8n-640") + frames_generator = sv.get_video_frames_generator() + + with sv.CSVSink() as sink: + for frame in frames_generator: + + results = model.infer(image)[0] + detections = sv.Detections.from_inference(results) + sink.append(detections, {}) + ``` + +=== "Ultralytics" + + ```{ .py hl_lines="7 12" } + import supervision as sv + from ultralytics import YOLO + + model = YOLO("yolov8n.pt") + frames_generator = sv.get_video_frames_generator() + + with sv.CSVSink() as sink: + for frame in frames_generator: + + results = model(frame)[0] + detections = sv.Detections.from_ultralytics(results) + sink.append(detections, {}) + ``` + +=== "Transformers" + + ```{ .py hl_lines="9 23" } + import torch + import supervision as sv + from transformers import DetrImageProcessor, DetrForObjectDetection + + processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50") + model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50") + frames_generator = sv.get_video_frames_generator() + + with sv.CSVSink() as sink: + for frame in frames_generator: + + frame = sv.cv2_to_pillow(frame) + inputs = processor(images=frame, return_tensors="pt") + + with torch.no_grad(): + outputs = model(**inputs) + + width, height = frame.size + target_size = torch.tensor([[height, width]]) + results = processor.post_process_object_detection( + outputs=outputs, target_sizes=target_size)[0] + detections = sv.Detections.from_transformers(results) + sink.append(detections, {}) + ``` + +| x_min | y_min | x_max | y_max | class_id | confidence | tracker_id | class_name | +|---------|----------|---------|----------|----------|------------|------------|------------| +| 2941.14 | 1269.31 | 3220.77 | 1500.67 | 2 | 0.8517 | | car | +| 944.889 | 899.641 | 1235.42 | 1308.80 | 7 | 0.6752 | | truck | +| 1439.78 | 1077.79 | 1621.27 | 1231.40 | 2 | 0.6450 | | car | + +## Custom Fields + +Besides regular fields in +[`sv.Detections`](/latest/detection/core/#supervision.detection.core.Detections), +[`sv.CSVSink`](/latest/detection/tools/save_detections/#supervision.detection.tools.csv_sink.CSVSink) +also allows you to add custom information to each row, which can be passed via the +`custom_data` dictionary. Let's utilize this feature to save information about the +frame index from which the detections originate. + +=== "Inference" + + ```{ .py hl_lines="8 12" } + import supervision as sv + from inference import get_model + + model = get_model(model_id="yolov8n-640") + frames_generator = sv.get_video_frames_generator() + + with sv.CSVSink() as sink: + for frame_index, frame in enumerate(frames_generator): + + results = model.infer(image)[0] + detections = sv.Detections.from_inference(results) + sink.append(detections, {"frame_index": frame_index}) + ``` + +=== "Ultralytics" + + ```{ .py hl_lines="8 12" } + import supervision as sv + from ultralytics import YOLO + + model = YOLO("yolov8n.pt") + frames_generator = sv.get_video_frames_generator() + + with sv.CSVSink() as sink: + for frame_index, frame in enumerate(frames_generator): + + results = model(frame)[0] + detections = sv.Detections.from_ultralytics(results) + sink.append(detections, {"frame_index": frame_index}) + ``` + +=== "Transformers" + + ```{ .py hl_lines="10 23" } + import torch + import supervision as sv + from transformers import DetrImageProcessor, DetrForObjectDetection + + processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50") + model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50") + frames_generator = sv.get_video_frames_generator() + + with sv.CSVSink() as sink: + for frame_index, frame in enumerate(frames_generator): + + frame = sv.cv2_to_pillow(frame) + inputs = processor(images=frame, return_tensors="pt") + + with torch.no_grad(): + outputs = model(**inputs) + + width, height = frame.size + target_size = torch.tensor([[height, width]]) + results = processor.post_process_object_detection( + outputs=outputs, target_sizes=target_size)[0] + detections = sv.Detections.from_transformers(results) + sink.append(detections, {"frame_index": frame_index}) + ``` + +| x_min | y_min | x_max | y_max | class_id | confidence | tracker_id | class_name | frame_index | +|---------|----------|---------|----------|----------|------------|------------|------------|-------------| +| 2941.14 | 1269.31 | 3220.77 | 1500.67 | 2 | 0.8517 | | car | 0 | +| 944.889 | 899.641 | 1235.42 | 1308.80 | 7 | 0.6752 | | truck | 0 | +| 1439.78 | 1077.79 | 1621.27 | 1231.40 | 2 | 0.6450 | | car | 0 | + +## Save Detections as JSON + +If you prefer to save the result in a `.JSON` file instead of a `.CSV` file, all you +need to do is replace +[`sv.CSVSink`](/latest/detection/tools/save_detections/#supervision.detection.tools.csv_sink.CSVSink) +with +[`sv.JSONSink`](/latest/detection/tools/save_detections/#supervision.detection.tools.csv_sink.JSONSink). + +=== "Inference" + + ```{ .py hl_lines="7" } + import supervision as sv + from inference import get_model + + model = get_model(model_id="yolov8n-640") + frames_generator = sv.get_video_frames_generator() + + with sv.JSONSink() as sink: + for frame_index, frame in enumerate(frames_generator): + + results = model.infer(image)[0] + detections = sv.Detections.from_inference(results) + sink.append(detections, {"frame_index": frame_index}) + ``` + +=== "Ultralytics" + + ```{ .py hl_lines="7" } + import supervision as sv + from ultralytics import YOLO + + model = YOLO("yolov8n.pt") + frames_generator = sv.get_video_frames_generator() + + with sv.JSONSink() as sink: + for frame_index, frame in enumerate(frames_generator): + + results = model(frame)[0] + detections = sv.Detections.from_ultralytics(results) + sink.append(detections, {"frame_index": frame_index}) + ``` + +=== "Transformers" + + ```{ .py hl_lines="9" } + import torch + import supervision as sv + from transformers import DetrImageProcessor, DetrForObjectDetection + + processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50") + model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50") + frames_generator = sv.get_video_frames_generator() + + with sv.JSONSink() as sink: + for frame_index, frame in enumerate(frames_generator): + + frame = sv.cv2_to_pillow(frame) + inputs = processor(images=frame, return_tensors="pt") + + with torch.no_grad(): + outputs = model(**inputs) + + width, height = frame.size + target_size = torch.tensor([[height, width]]) + results = processor.post_process_object_detection( + outputs=outputs, target_sizes=target_size)[0] + detections = sv.Detections.from_transformers(results) + sink.append(detections, {"frame_index": frame_index}) + ``` diff --git a/docs/keypoint/annotators.md b/docs/keypoint/annotators.md new file mode 100644 index 00000000..b5f998bc --- /dev/null +++ b/docs/keypoint/annotators.md @@ -0,0 +1,60 @@ +--- +comments: true +status: new +--- + +# Annotators + +=== "VertexAnnotator" + + ```python + import supervision as sv + + image = ... + key_points = sv.KeyPoints(...) + + vertex_annotator = sv.VertexAnnotator(color=sv.Color.GREEN, radius=10) + annotated_frame = vertex_annotator.annotate( + scene=image.copy(), + key_points=key_points + ) + ``` + +
+ + ![vertex-annotator-example](https://media.roboflow.com/supervision-annotator-examples/vertex-annotator-example.png){ align=center width="800" } + +
+ +=== "EdgeAnnotator" + + ```python + import supervision as sv + + image = ... + key_points = sv.KeyPoints(...) + + edge_annotator = sv.EdgeAnnotator(color=sv.Color.GREEN, thickness=5) + annotated_frame = edge_annotator.annotate( + scene=image.copy(), + key_points=key_points + ) + ``` + +
+ + ![edge-annotator-example](https://media.roboflow.com/supervision-annotator-examples/edge-annotator-example.png){ align=center width="800" } + +
+ +
+

VertexAnnotator

+
+ +:::supervision.keypoint.annotators.VertexAnnotator + +
+

EdgeAnnotator

+
+ +:::supervision.keypoint.annotators.EdgeAnnotator diff --git a/docs/keypoint/core.md b/docs/keypoint/core.md new file mode 100644 index 00000000..7354baba --- /dev/null +++ b/docs/keypoint/core.md @@ -0,0 +1,8 @@ +--- +comments: true +status: new +--- + +# Keypoint Detection + +:::supervision.keypoint.core.KeyPoints diff --git a/docs/metrics/detection.md b/docs/metrics/detection.md deleted file mode 100644 index a953ba9b..00000000 --- a/docs/metrics/detection.md +++ /dev/null @@ -1,22 +0,0 @@ ---- -comments: true ---- - -# Β Detection Metrics - -!!! 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 - -
-

MeanAveragePrecision

-
- -:::supervision.metrics.detection.MeanAveragePrecision diff --git a/docs/utils/draw.md b/docs/utils/draw.md new file mode 100644 index 00000000..84758e06 --- /dev/null +++ b/docs/utils/draw.md @@ -0,0 +1,65 @@ +--- +comments: true +--- + +# Draw Utils + +
+

draw_line

+
+ +:::supervision.draw.utils.draw_line + +
+

draw_rectangle

+
+ +:::supervision.draw.utils.draw_rectangle + +
+

draw_filled_rectangle

+
+ +:::supervision.draw.utils.draw_filled_rectangle + +
+

draw_polygon

+
+ +:::supervision.draw.utils.draw_polygon + +
+

draw_text

+
+ +:::supervision.draw.utils.draw_text + +
+

draw_image

+
+ +:::supervision.draw.utils.draw_image + +
+

calculate_optimal_font_scale

+
+ +:::supervision.draw.utils.calculate_optimal_text_scale + +
+

calculate_optimal_line_thickness

+
+ +:::supervision.draw.utils.calculate_optimal_line_thickness + +
+

Color

+
+ +:::supervision.draw.color.Color + +
+

ColorPalette

+
+ +:::supervision.draw.color.ColorPalette diff --git a/docs/utils/file.md b/docs/utils/file.md index 2ba5a015..a2a08185 100644 --- a/docs/utils/file.md +++ b/docs/utils/file.md @@ -5,7 +5,7 @@ comments: true # File Utils
-

list_files_with_extensions

+

list_files_with_extensions

:::supervision.utils.file.list_files_with_extensions diff --git a/docs/utils/geometry.md b/docs/utils/geometry.md new file mode 100644 index 00000000..d79bcfeb --- /dev/null +++ b/docs/utils/geometry.md @@ -0,0 +1,15 @@ +--- +comments: true +--- + +
+

get_polygon_center

+
+ +:::supervision.geometry.utils.get_polygon_center + +
+

Position

+
+ +:::supervision.geometry.core.Position diff --git a/docs/utils/image.md b/docs/utils/image.md index 087aebd7..8f170d35 100644 --- a/docs/utils/image.md +++ b/docs/utils/image.md @@ -6,31 +6,37 @@ status: new # Image Utils
-

ImageSink

-
- -:::supervision.utils.image.ImageSink - -
-

crop_image

+

crop_image

:::supervision.utils.image.crop_image
-

letterbox_image

+

crop_image

-:::supervision.utils.image.letterbox_image +:::supervision.utils.image.scale_image
-

resize_image

+

resize_image

:::supervision.utils.image.resize_image
-

place_image

+

letterbox_image

-:::supervision.utils.image.place_image +:::supervision.utils.image.letterbox_image + +
+

overlay_image

+
+ +:::supervision.utils.image.overlay_image + +
+

ImageSink

+
+ +:::supervision.utils.image.ImageSink diff --git a/docs/utils/iterables.md b/docs/utils/iterables.md index 3ccf98e5..b65cd954 100644 --- a/docs/utils/iterables.md +++ b/docs/utils/iterables.md @@ -6,13 +6,13 @@ status: new # Iterables Utils
-

create_batches

+

create_batches

:::supervision.utils.iterables.create_batches
-

fill

+

fill

:::supervision.utils.iterables.fill diff --git a/docs/utils/notebook.md b/docs/utils/notebook.md index d09b9bbd..3eab046a 100644 --- a/docs/utils/notebook.md +++ b/docs/utils/notebook.md @@ -5,14 +5,13 @@ comments: true # Notebooks Utils
-

plot_image

+

plot_image

:::supervision.utils.notebook.plot_image
-

plot_images_grid -

+

plot_images_grid

:::supervision.utils.notebook.plot_images_grid diff --git a/docs/utils/video.md b/docs/utils/video.md index 1f58450f..f9a5821d 100644 --- a/docs/utils/video.md +++ b/docs/utils/video.md @@ -5,31 +5,31 @@ comments: true # Video Utils
-

VideoInfo

+

VideoInfo

:::supervision.utils.video.VideoInfo
-

VideoSink

+

VideoSink

:::supervision.utils.video.VideoSink
-

FPSMonitor

+

FPSMonitor

:::supervision.utils.video.FPSMonitor
-

get_video_frames_generator

+

get_video_frames_generator

:::supervision.utils.video.get_video_frames_generator
-

process_video

+

process_video

:::supervision.utils.video.process_video diff --git a/examples/README.md b/examples/README.md index 81c8054b..b723a247 100644 --- a/examples/README.md +++ b/examples/README.md @@ -1,8 +1,8 @@ # Examples -This repository is packed with real-world use-cases, provided through Python scripts or -interactive notebooks. Browse through to understand how the Supervision library -interfaces with diverse applications. +Here, you'll find end-to-end examples that show how to solve common computer vision problems using Supervision. + +For more information and examples, visit our [documentation](https://supervision.roboflow.com/develop/annotators/) and explore our [how-to guides](https://supervision.roboflow.com/develop/how_to/detect_and_annotate/) and [cookbooks](https://supervision.roboflow.com/develop/cookbooks/). Join our [Discord](https://discord.com/invite/GbfgXGJ8Bk) and meet other Supervision power users! - [tracking](./tracking) by [@SkalskiP](https://github.com/SkalskiP) - [count people in zone](./count_people_in_zone) by [@SkalskiP](https://github.com/SkalskiP) @@ -10,23 +10,3 @@ interfaces with diverse applications. - [speed estimation](./speed_estimation) by [@SkalskiP](https://github.com/SkalskiP) - [time in zone](./time_in_zone) by [@SkalskiP](https://github.com/SkalskiP) - [heatmap and track](./heatmap_and_track/) by [@HinePo](https://github.com/HinePo) - -## Contributing - -We welcome contributions from the community in the form of examples, applications, and -guides. To contribute, please follow these steps: - -1. Create a pull request (PR) with the `[Example]` prefix in the title, adding your -project folder to the `examples/` directory in the repository. -2. Confirm your project aligns with the following standards: - - Incorporates the `supervision` package. - - Provides a `README.md` file, detailing the instructions to execute the project. - - Showcases visual results, demonstrating the app's functionality. - - Avoids adding large assets or dependencies unless absolutely necessary. - - The contributor is expected to provide support for issues related to their -examples. - - In case the presented model has licensing complications, kindly specify them to -circumvent potential misunderstandings. - -For inquiries or concerns about these prerequisites, feel free to raise a PR. We are -committed to assist and guide you. diff --git a/examples/count_people_in_zone/README.md b/examples/count_people_in_zone/README.md index 2e14a80b..d9d3cdb2 100644 --- a/examples/count_people_in_zone/README.md +++ b/examples/count_people_in_zone/README.md @@ -1,5 +1,8 @@ # count people in zone +[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-detect-and-count-objects-in-polygon-zone.ipynb) +[![YouTube](https://badges.aleen42.com/src/youtube.svg)](https://www.youtube.com/watch?v=l_kf9CfZ_8M) + ## πŸ‘‹ hello This demo is a video analysis tool that counts and highlights objects in specific zones diff --git a/examples/count_people_in_zone/inference_example.py b/examples/count_people_in_zone/inference_example.py index 6fd0f340..c5086806 100644 --- a/examples/count_people_in_zone/inference_example.py +++ b/examples/count_people_in_zone/inference_example.py @@ -38,15 +38,15 @@ def initiate_annotators( ) -> Tuple[ List[sv.PolygonZone], List[sv.PolygonZoneAnnotator], List[sv.BoundingBoxAnnotator] ]: - line_thickness = sv.calculate_dynamic_line_thickness(resolution_wh=resolution_wh) - text_scale = sv.calculate_dynamic_text_scale(resolution_wh=resolution_wh) + line_thickness = sv.calculate_optimal_line_thickness(resolution_wh=resolution_wh) + text_scale = sv.calculate_optimal_text_scale(resolution_wh=resolution_wh) zones = [] zone_annotators = [] box_annotators = [] for index, polygon in enumerate(polygons): - zone = sv.PolygonZone(polygon=polygon, frame_resolution_wh=resolution_wh) + zone = sv.PolygonZone(polygon=polygon) zone_annotator = sv.PolygonZoneAnnotator( zone=zone, color=COLORS.by_idx(index), diff --git a/examples/count_people_in_zone/requirements.txt b/examples/count_people_in_zone/requirements.txt index d9e27264..1cd58655 100644 --- a/examples/count_people_in_zone/requirements.txt +++ b/examples/count_people_in_zone/requirements.txt @@ -1,5 +1,5 @@ gdown -inference -supervision==0.19.0 +inference==0.9.17 +supervision>=0.20.0 tqdm ultralytics diff --git a/examples/count_people_in_zone/ultralytics_example.py b/examples/count_people_in_zone/ultralytics_example.py index cfd37bcc..c17e4d7b 100644 --- a/examples/count_people_in_zone/ultralytics_example.py +++ b/examples/count_people_in_zone/ultralytics_example.py @@ -36,15 +36,15 @@ def initiate_annotators( ) -> Tuple[ List[sv.PolygonZone], List[sv.PolygonZoneAnnotator], List[sv.BoundingBoxAnnotator] ]: - line_thickness = sv.calculate_dynamic_line_thickness(resolution_wh=resolution_wh) - text_scale = sv.calculate_dynamic_text_scale(resolution_wh=resolution_wh) + line_thickness = sv.calculate_optimal_line_thickness(resolution_wh=resolution_wh) + text_scale = sv.calculate_optimal_text_scale(resolution_wh=resolution_wh) zones = [] zone_annotators = [] box_annotators = [] for index, polygon in enumerate(polygons): - zone = sv.PolygonZone(polygon=polygon, frame_resolution_wh=resolution_wh) + zone = sv.PolygonZone(polygon=polygon) zone_annotator = sv.PolygonZoneAnnotator( zone=zone, color=COLORS.by_idx(index), diff --git a/examples/speed_estimation/inference_example.py b/examples/speed_estimation/inference_example.py index b0ff84dd..e715d88e 100644 --- a/examples/speed_estimation/inference_example.py +++ b/examples/speed_estimation/inference_example.py @@ -98,10 +98,10 @@ if __name__ == "__main__": frame_rate=video_info.fps, track_thresh=args.confidence_threshold ) - thickness = sv.calculate_dynamic_line_thickness( + thickness = sv.calculate_optimal_line_thickness( resolution_wh=video_info.resolution_wh ) - text_scale = sv.calculate_dynamic_text_scale(resolution_wh=video_info.resolution_wh) + text_scale = sv.calculate_optimal_text_scale(resolution_wh=video_info.resolution_wh) bounding_box_annotator = sv.BoundingBoxAnnotator(thickness=thickness) label_annotator = sv.LabelAnnotator( text_scale=text_scale, @@ -116,9 +116,7 @@ if __name__ == "__main__": frame_generator = sv.get_video_frames_generator(source_path=args.source_video_path) - polygon_zone = sv.PolygonZone( - polygon=SOURCE, frame_resolution_wh=video_info.resolution_wh - ) + polygon_zone = sv.PolygonZone(polygon=SOURCE) view_transformer = ViewTransformer(source=SOURCE, target=TARGET) coordinates = defaultdict(lambda: deque(maxlen=video_info.fps)) diff --git a/examples/speed_estimation/requirements.txt b/examples/speed_estimation/requirements.txt index 36de970d..343a687d 100644 --- a/examples/speed_estimation/requirements.txt +++ b/examples/speed_estimation/requirements.txt @@ -1,6 +1,6 @@ -supervision==0.19.0 -tqdm==4.66.1 +supervision>=0.20.0 +tqdm==4.66.3 requests ultralytics==8.0.237 super-gradients==3.5.0 -inference==0.9.8 +inference==0.9.17 diff --git a/examples/speed_estimation/ultralytics_example.py b/examples/speed_estimation/ultralytics_example.py index 4b0436a0..4440d4d9 100644 --- a/examples/speed_estimation/ultralytics_example.py +++ b/examples/speed_estimation/ultralytics_example.py @@ -76,10 +76,10 @@ if __name__ == "__main__": frame_rate=video_info.fps, track_thresh=args.confidence_threshold ) - thickness = sv.calculate_dynamic_line_thickness( + thickness = sv.calculate_optimal_line_thickness( resolution_wh=video_info.resolution_wh ) - text_scale = sv.calculate_dynamic_text_scale(resolution_wh=video_info.resolution_wh) + text_scale = sv.calculate_optimal_text_scale(resolution_wh=video_info.resolution_wh) bounding_box_annotator = sv.BoundingBoxAnnotator(thickness=thickness) label_annotator = sv.LabelAnnotator( text_scale=text_scale, @@ -94,9 +94,7 @@ if __name__ == "__main__": frame_generator = sv.get_video_frames_generator(source_path=args.source_video_path) - polygon_zone = sv.PolygonZone( - polygon=SOURCE, frame_resolution_wh=video_info.resolution_wh - ) + polygon_zone = sv.PolygonZone(polygon=SOURCE) view_transformer = ViewTransformer(source=SOURCE, target=TARGET) coordinates = defaultdict(lambda: deque(maxlen=video_info.fps)) diff --git a/examples/speed_estimation/yolo_nas_example.py b/examples/speed_estimation/yolo_nas_example.py index 77f1fd0f..4bb1d960 100644 --- a/examples/speed_estimation/yolo_nas_example.py +++ b/examples/speed_estimation/yolo_nas_example.py @@ -77,10 +77,10 @@ if __name__ == "__main__": frame_rate=video_info.fps, track_thresh=args.confidence_threshold ) - thickness = sv.calculate_dynamic_line_thickness( + thickness = sv.calculate_optimal_line_thickness( resolution_wh=video_info.resolution_wh ) - text_scale = sv.calculate_dynamic_text_scale(resolution_wh=video_info.resolution_wh) + text_scale = sv.calculate_optimal_text_scale(resolution_wh=video_info.resolution_wh) bounding_box_annotator = sv.BoundingBoxAnnotator(thickness=thickness) label_annotator = sv.LabelAnnotator( text_scale=text_scale, @@ -95,9 +95,7 @@ if __name__ == "__main__": frame_generator = sv.get_video_frames_generator(source_path=args.source_video_path) - polygon_zone = sv.PolygonZone( - polygon=SOURCE, frame_resolution_wh=video_info.resolution_wh - ) + polygon_zone = sv.PolygonZone(polygon=SOURCE) view_transformer = ViewTransformer(source=SOURCE, target=TARGET) coordinates = defaultdict(lambda: deque(maxlen=video_info.fps)) diff --git a/examples/time_in_zone/README.md b/examples/time_in_zone/README.md index 2bfd6c7a..98587999 100644 --- a/examples/time_in_zone/README.md +++ b/examples/time_in_zone/README.md @@ -1,5 +1,7 @@ # time in zone +[![YouTube](https://badges.aleen42.com/src/youtube.svg)](https://www.youtube.com/watch?v=hAWpsIuem10) + ## πŸ‘‹ hello Practical demonstration on leveraging computer vision for analyzing wait times and diff --git a/examples/time_in_zone/inference_file_example.py b/examples/time_in_zone/inference_file_example.py index 5feb1d83..f4955464 100644 --- a/examples/time_in_zone/inference_file_example.py +++ b/examples/time_in_zone/inference_file_example.py @@ -29,14 +29,10 @@ def main( video_info = sv.VideoInfo.from_video_path(video_path=source_video_path) frames_generator = sv.get_video_frames_generator(source_video_path) - frame = next(frames_generator) - resolution_wh = frame.shape[1], frame.shape[0] - polygons = load_zones_config(file_path=zone_configuration_path) zones = [ sv.PolygonZone( polygon=polygon, - frame_resolution_wh=resolution_wh, triggering_anchors=(sv.Position.CENTER,), ) for polygon in polygons diff --git a/examples/time_in_zone/inference_naive_stream_example.py b/examples/time_in_zone/inference_naive_stream_example.py index dd2d68a5..21880269 100644 --- a/examples/time_in_zone/inference_naive_stream_example.py +++ b/examples/time_in_zone/inference_naive_stream_example.py @@ -29,14 +29,10 @@ def main( frames_generator = get_stream_frames_generator(rtsp_url=rtsp_url) fps_monitor = sv.FPSMonitor() - frame = next(frames_generator) - resolution_wh = frame.shape[1], frame.shape[0] - polygons = load_zones_config(file_path=zone_configuration_path) zones = [ sv.PolygonZone( polygon=polygon, - frame_resolution_wh=resolution_wh, triggering_anchors=(sv.Position.CENTER,), ) for polygon in polygons diff --git a/examples/time_in_zone/inference_stream_example.py b/examples/time_in_zone/inference_stream_example.py index e1fae57f..0dfdf660 100644 --- a/examples/time_in_zone/inference_stream_example.py +++ b/examples/time_in_zone/inference_stream_example.py @@ -24,20 +24,15 @@ class CustomSink: self.fps_monitor = sv.FPSMonitor() self.polygons = load_zones_config(file_path=zone_configuration_path) self.timers = [ClockBasedTimer() for _ in self.polygons] - self.zones = None + self.zones = [ + sv.PolygonZone( + polygon=polygon, + triggering_anchors=(sv.Position.CENTER,), + ) + for polygon in self.polygons + ] def on_prediction(self, result: dict, frame: VideoFrame) -> None: - if self.zones is None: - resolution_wh = frame.image.shape[1], frame.image.shape[0] - self.zones = [ - sv.PolygonZone( - polygon=polygon, - frame_resolution_wh=resolution_wh, - triggering_anchors=(sv.Position.CENTER,), - ) - for polygon in self.polygons - ] - self.fps_monitor.tick() fps = self.fps_monitor.fps diff --git a/examples/time_in_zone/requirements.txt b/examples/time_in_zone/requirements.txt index fa17b986..6154c3eb 100644 --- a/examples/time_in_zone/requirements.txt +++ b/examples/time_in_zone/requirements.txt @@ -1,5 +1,5 @@ opencv-python -supervision +supervision>=0.20.0 ultralytics -inference +inference==0.9.17 pytube diff --git a/examples/time_in_zone/ultralytics_file_example.py b/examples/time_in_zone/ultralytics_file_example.py index fe8ce58d..b470b7a3 100644 --- a/examples/time_in_zone/ultralytics_file_example.py +++ b/examples/time_in_zone/ultralytics_file_example.py @@ -30,14 +30,10 @@ def main( video_info = sv.VideoInfo.from_video_path(video_path=source_video_path) frames_generator = sv.get_video_frames_generator(source_video_path) - frame = next(frames_generator) - resolution_wh = frame.shape[1], frame.shape[0] - polygons = load_zones_config(file_path=zone_configuration_path) zones = [ sv.PolygonZone( polygon=polygon, - frame_resolution_wh=resolution_wh, triggering_anchors=(sv.Position.CENTER,), ) for polygon in polygons diff --git a/examples/time_in_zone/ultralytics_naive_stream_example.py b/examples/time_in_zone/ultralytics_naive_stream_example.py index 1cc82b44..d6922143 100644 --- a/examples/time_in_zone/ultralytics_naive_stream_example.py +++ b/examples/time_in_zone/ultralytics_naive_stream_example.py @@ -30,14 +30,10 @@ def main( frames_generator = get_stream_frames_generator(rtsp_url=rtsp_url) fps_monitor = sv.FPSMonitor() - frame = next(frames_generator) - resolution_wh = frame.shape[1], frame.shape[0] - polygons = load_zones_config(file_path=zone_configuration_path) zones = [ sv.PolygonZone( polygon=polygon, - frame_resolution_wh=resolution_wh, triggering_anchors=(sv.Position.CENTER,), ) for polygon in polygons diff --git a/examples/time_in_zone/ultralytics_stream_example.py b/examples/time_in_zone/ultralytics_stream_example.py index 25dc874f..8b8ecd60 100644 --- a/examples/time_in_zone/ultralytics_stream_example.py +++ b/examples/time_in_zone/ultralytics_stream_example.py @@ -25,20 +25,15 @@ class CustomSink: self.fps_monitor = sv.FPSMonitor() self.polygons = load_zones_config(file_path=zone_configuration_path) self.timers = [ClockBasedTimer() for _ in self.polygons] - self.zones = None + self.zones = [ + sv.PolygonZone( + polygon=polygon, + triggering_anchors=(sv.Position.CENTER,), + ) + for polygon in self.polygons + ] def on_prediction(self, detections: sv.Detections, frame: VideoFrame) -> None: - if self.zones is None: - resolution_wh = frame.image.shape[1], frame.image.shape[0] - self.zones = [ - sv.PolygonZone( - polygon=polygon, - frame_resolution_wh=resolution_wh, - triggering_anchors=(sv.Position.CENTER,), - ) - for polygon in self.polygons - ] - self.fps_monitor.tick() fps = self.fps_monitor.fps diff --git a/examples/tracking/requirements.txt b/examples/tracking/requirements.txt index 8d5a9233..a45d9291 100644 --- a/examples/tracking/requirements.txt +++ b/examples/tracking/requirements.txt @@ -1,4 +1,4 @@ -inference +inference==0.9.17 supervision==0.19.0 tqdm ultralytics diff --git a/examples/traffic_analysis/inference_example.py b/examples/traffic_analysis/inference_example.py index 7da5f37c..3cf750ad 100644 --- a/examples/traffic_analysis/inference_example.py +++ b/examples/traffic_analysis/inference_example.py @@ -1,6 +1,6 @@ import argparse import os -from typing import Dict, Iterable, List, Set, Tuple +from typing import Dict, Iterable, List, Set import cv2 import numpy as np @@ -60,13 +60,11 @@ class DetectionsManager: def initiate_polygon_zones( polygons: List[np.ndarray], - frame_resolution_wh: Tuple[int, int], triggering_anchors: Iterable[sv.Position] = [sv.Position.CENTER], ) -> List[sv.PolygonZone]: return [ sv.PolygonZone( polygon=polygon, - frame_resolution_wh=frame_resolution_wh, triggering_anchors=triggering_anchors, ) for polygon in polygons @@ -92,12 +90,8 @@ class VideoProcessor: self.tracker = sv.ByteTrack() self.video_info = sv.VideoInfo.from_video_path(source_video_path) - self.zones_in = initiate_polygon_zones( - ZONE_IN_POLYGONS, self.video_info.resolution_wh, [sv.Position.CENTER] - ) - self.zones_out = initiate_polygon_zones( - ZONE_OUT_POLYGONS, self.video_info.resolution_wh, [sv.Position.CENTER] - ) + self.zones_in = initiate_polygon_zones(ZONE_IN_POLYGONS, [sv.Position.CENTER]) + self.zones_out = initiate_polygon_zones(ZONE_OUT_POLYGONS, [sv.Position.CENTER]) self.bounding_box_annotator = sv.BoundingBoxAnnotator(color=COLORS) self.label_annotator = sv.LabelAnnotator( diff --git a/examples/traffic_analysis/requirements.txt b/examples/traffic_analysis/requirements.txt index 6e72dd55..1cd58655 100644 --- a/examples/traffic_analysis/requirements.txt +++ b/examples/traffic_analysis/requirements.txt @@ -1,5 +1,5 @@ gdown -inference -supervision>=0.19.0 +inference==0.9.17 +supervision>=0.20.0 tqdm ultralytics diff --git a/examples/traffic_analysis/ultralytics_example.py b/examples/traffic_analysis/ultralytics_example.py index 78189d29..16ba6d8c 100644 --- a/examples/traffic_analysis/ultralytics_example.py +++ b/examples/traffic_analysis/ultralytics_example.py @@ -1,5 +1,5 @@ import argparse -from typing import Dict, Iterable, List, Set, Tuple +from typing import Dict, Iterable, List, Set import cv2 import numpy as np @@ -58,13 +58,11 @@ class DetectionsManager: def initiate_polygon_zones( polygons: List[np.ndarray], - frame_resolution_wh: Tuple[int, int], triggering_anchors: Iterable[sv.Position] = [sv.Position.CENTER], ) -> List[sv.PolygonZone]: return [ sv.PolygonZone( polygon=polygon, - frame_resolution_wh=frame_resolution_wh, triggering_anchors=triggering_anchors, ) for polygon in polygons @@ -89,12 +87,8 @@ class VideoProcessor: self.tracker = sv.ByteTrack() self.video_info = sv.VideoInfo.from_video_path(source_video_path) - self.zones_in = initiate_polygon_zones( - ZONE_IN_POLYGONS, self.video_info.resolution_wh, [sv.Position.CENTER] - ) - self.zones_out = initiate_polygon_zones( - ZONE_OUT_POLYGONS, self.video_info.resolution_wh, [sv.Position.CENTER] - ) + self.zones_in = initiate_polygon_zones(ZONE_IN_POLYGONS, [sv.Position.CENTER]) + self.zones_out = initiate_polygon_zones(ZONE_OUT_POLYGONS, [sv.Position.CENTER]) self.bounding_box_annotator = sv.BoundingBoxAnnotator(color=COLORS) self.label_annotator = sv.LabelAnnotator( diff --git a/mkdocs.yml b/mkdocs.yml index 8bae5d76..cf206a82 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -38,16 +38,22 @@ nav: - Home: index.md - How to: - Detect and Annotate: how_to/detect_and_annotate.md + - Save Detections: how_to/save_detections.md + - Filter Detections: how_to/filter_detections.md - Detect Small Objects: how_to/detect_small_objects.md - Track Objects: how_to/track_objects.md - - Filter Detections: how_to/filter_detections.md + - API: - - Annotators: annotators.md - - Classifications: - - Core: classification/core.md - - Detections: + - Detection and Segmentation: - Core: detection/core.md + - Annotators: detection/annotators.md + - Metrics: detection/metrics.md - Utils: detection/utils.md + - Keypoint Detection: + - Core: keypoint/core.md + - Annotators: keypoint/annotators.md + - Classification: + - Core: classification/core.md - Tools: - Line Zone: detection/tools/line_zone.md - Polygon Zone: detection/tools/polygon_zone.md @@ -56,19 +62,14 @@ nav: - Save Detections: detection/tools/save_detections.md - Trackers: trackers.md - Datasets: datasets.md - - Metrics: - - Object Detection: metrics/detection.md - - Draw: - - Color: draw/color.md - - Utils: draw/utils.md - - Geometry: - - Position: geometry/core.md - Utils: - Video: utils/video.md - Image: utils/image.md - Iterables: utils/iterables.md - Notebook: utils/notebook.md - File: utils/file.md + - Draw: utils/draw.md + - Geometry: utils/geometry.md - Assets: assets.md - Cookbooks: cookbooks.md - Contribute: diff --git a/poetry.lock b/poetry.lock index 65a9122f..178fda0d 100644 --- a/poetry.lock +++ b/poetry.lock @@ -1122,13 +1122,13 @@ license = ["ukkonen"] [[package]] name = "idna" -version = "3.6" +version = "3.7" description = "Internationalized Domain Names in Applications (IDNA)" optional = false python-versions = ">=3.5" files = [ - {file = "idna-3.6-py3-none-any.whl", hash = "sha256:c05567e9c24a6b9faaa835c4821bad0590fbb9d5779e7caa6e1cc4978e7eb24f"}, - {file = "idna-3.6.tar.gz", hash = "sha256:9ecdbbd083b06798ae1e86adcbfe8ab1479cf864e4ee30fe4e46a003d12491ca"}, + {file = "idna-3.7-py3-none-any.whl", hash = "sha256:82fee1fc78add43492d3a1898bfa6d8a904cc97d8427f683ed8e798d07761aa0"}, + {file = "idna-3.7.tar.gz", hash = "sha256:028ff3aadf0609c1fd278d8ea3089299412a7a8b9bd005dd08b9f8285bcb5cfc"}, ] [[package]] @@ -1648,13 +1648,13 @@ files = [ [[package]] name = "jupytext" -version = "1.16.1" +version = "1.16.2" description = "Jupyter notebooks as Markdown documents, Julia, Python or R scripts" optional = false python-versions = ">=3.8" files = [ - {file = "jupytext-1.16.1-py3-none-any.whl", hash = "sha256:796ec4f68ada663569e5d38d4ef03738a01284bfe21c943c485bc36433898bd0"}, - {file = "jupytext-1.16.1.tar.gz", hash = "sha256:68c7b68685e870e80e60fda8286fbd6269e9c74dc1df4316df6fe46eabc94c99"}, + {file = "jupytext-1.16.2-py3-none-any.whl", hash = "sha256:197a43fef31dca612b68b311e01b8abd54441c7e637810b16b6cb8f2ab66065e"}, + {file = "jupytext-1.16.2.tar.gz", hash = "sha256:8627dd9becbbebd79cc4a4ed4727d89d78e606b4b464eab72357b3b029023a14"}, ] [package.dependencies] @@ -1663,16 +1663,16 @@ mdit-py-plugins = "*" nbformat = "*" packaging = "*" pyyaml = "*" -toml = "*" +tomli = {version = "*", markers = "python_version < \"3.11\""} [package.extras] -dev = ["jupytext[test-cov,test-external]"] +dev = ["autopep8", "black", "flake8", "gitpython", "ipykernel", "isort", "jupyter-fs (<0.4.0)", "jupyter-server (!=2.11)", "nbconvert", "pre-commit", "pytest", "pytest-cov (>=2.6.1)", "pytest-randomly", "pytest-xdist", "sphinx-gallery (<0.8)"] docs = ["myst-parser", "sphinx", "sphinx-copybutton", "sphinx-rtd-theme"] test = ["pytest", "pytest-randomly", "pytest-xdist"] -test-cov = ["jupytext[test-integration]", "pytest-cov (>=2.6.1)"] -test-external = ["autopep8", "black", "flake8", "gitpython", "isort", "jupyter-fs (<0.4.0)", "jupytext[test-integration]", "pre-commit", "sphinx-gallery (<0.8)"] -test-functional = ["jupytext[test]"] -test-integration = ["ipykernel", "jupyter-server (!=2.11)", "jupytext[test-functional]", "nbconvert"] +test-cov = ["ipykernel", "jupyter-server (!=2.11)", "nbconvert", "pytest", "pytest-cov (>=2.6.1)", "pytest-randomly", "pytest-xdist"] +test-external = ["autopep8", "black", "flake8", "gitpython", "ipykernel", "isort", "jupyter-fs (<0.4.0)", "jupyter-server (!=2.11)", "nbconvert", "pre-commit", "pytest", "pytest-randomly", "pytest-xdist", "sphinx-gallery (<0.8)"] +test-functional = ["pytest", "pytest-randomly", "pytest-xdist"] +test-integration = ["ipykernel", "jupyter-server (!=2.11)", "nbconvert", "pytest", "pytest-randomly", "pytest-xdist"] test-ui = ["calysto-bash"] [[package]] @@ -2048,13 +2048,13 @@ files = [ [[package]] name = "mike" -version = "2.0.0" +version = "2.1.1" description = "Manage multiple versions of your MkDocs-powered documentation" optional = false python-versions = "*" files = [ - {file = "mike-2.0.0-py3-none-any.whl", hash = "sha256:87f496a65900f93ba92d72940242b65c86f3f2f82871bc60ebdcffc91fad1d9e"}, - {file = "mike-2.0.0.tar.gz", hash = "sha256:566f1cab1a58cc50b106fb79ea2f1f56e7bfc8b25a051e95e6eaee9fba0922de"}, + {file = "mike-2.1.1-py3-none-any.whl", hash = "sha256:0b1d01a397a423284593eeb1b5f3194e37169488f929b860c9bfe95c0d5efb79"}, + {file = "mike-2.1.1.tar.gz", hash = "sha256:f39ed39f3737da83ad0adc33e9f885092ed27f8c9e7ff0523add0480352a2c22"}, ] [package.dependencies] @@ -2064,6 +2064,7 @@ jinja2 = ">=2.7" mkdocs = ">=1.0" pyparsing = ">=3.0" pyyaml = ">=5.1" +pyyaml-env-tag = "*" verspec = "*" [package.extras] @@ -2083,34 +2084,34 @@ files = [ [[package]] name = "mkdocs" -version = "1.5.3" +version = "1.6.0" description = "Project documentation with Markdown." optional = false -python-versions = ">=3.7" +python-versions = ">=3.8" files = [ - {file = "mkdocs-1.5.3-py3-none-any.whl", hash = "sha256:3b3a78e736b31158d64dbb2f8ba29bd46a379d0c6e324c2246c3bc3d2189cfc1"}, - {file = "mkdocs-1.5.3.tar.gz", hash = "sha256:eb7c99214dcb945313ba30426c2451b735992c73c2e10838f76d09e39ff4d0e2"}, + {file = "mkdocs-1.6.0-py3-none-any.whl", hash = "sha256:1eb5cb7676b7d89323e62b56235010216319217d4af5ddc543a91beb8d125ea7"}, + {file = "mkdocs-1.6.0.tar.gz", hash = "sha256:a73f735824ef83a4f3bcb7a231dcab23f5a838f88b7efc54a0eef5fbdbc3c512"}, ] [package.dependencies] click = ">=7.0" colorama = {version = ">=0.4", markers = "platform_system == \"Windows\""} ghp-import = ">=1.0" -importlib-metadata = {version = ">=4.3", markers = "python_version < \"3.10\""} +importlib-metadata = {version = ">=4.4", markers = "python_version < \"3.10\""} jinja2 = ">=2.11.1" -markdown = ">=3.2.1" +markdown = ">=3.3.6" markupsafe = ">=2.0.1" mergedeep = ">=1.3.4" +mkdocs-get-deps = ">=0.2.0" packaging = ">=20.5" pathspec = ">=0.11.1" -platformdirs = ">=2.2.0" pyyaml = ">=5.1" pyyaml-env-tag = ">=0.1" watchdog = ">=2.0" [package.extras] i18n = ["babel (>=2.9.0)"] -min-versions = ["babel (==2.9.0)", "click (==7.0)", "colorama (==0.4)", "ghp-import (==1.0)", "importlib-metadata (==4.3)", "jinja2 (==2.11.1)", "markdown (==3.2.1)", "markupsafe (==2.0.1)", "mergedeep (==1.3.4)", "packaging (==20.5)", "pathspec (==0.11.1)", "platformdirs (==2.2.0)", "pyyaml (==5.1)", "pyyaml-env-tag (==0.1)", "typing-extensions (==3.10)", "watchdog (==2.0)"] +min-versions = ["babel (==2.9.0)", "click (==7.0)", "colorama (==0.4)", "ghp-import (==1.0)", "importlib-metadata (==4.4)", "jinja2 (==2.11.1)", "markdown (==3.3.6)", "markupsafe (==2.0.1)", "mergedeep (==1.3.4)", "mkdocs-get-deps (==0.2.0)", "packaging (==20.5)", "pathspec (==0.11.1)", "pyyaml (==5.1)", "pyyaml-env-tag (==0.1)", "watchdog (==2.0)"] [[package]] name = "mkdocs-autorefs" @@ -2127,6 +2128,23 @@ files = [ Markdown = ">=3.3" mkdocs = ">=1.1" +[[package]] +name = "mkdocs-get-deps" +version = "0.2.0" +description = "MkDocs extension that lists all dependencies according to a mkdocs.yml file" +optional = false +python-versions = ">=3.8" +files = [ + {file = "mkdocs_get_deps-0.2.0-py3-none-any.whl", hash = "sha256:2bf11d0b133e77a0dd036abeeb06dec8775e46efa526dc70667d8863eefc6134"}, + {file = "mkdocs_get_deps-0.2.0.tar.gz", hash = "sha256:162b3d129c7fad9b19abfdcb9c1458a651628e4b1dea628ac68790fb3061c60c"}, +] + +[package.dependencies] +importlib-metadata = {version = ">=4.3", markers = "python_version < \"3.10\""} +mergedeep = ">=1.3.4" +platformdirs = ">=2.2.0" +pyyaml = ">=5.1" + [[package]] name = "mkdocs-git-committers-plugin-2" version = "2.3.0" @@ -2145,13 +2163,13 @@ requests = "*" [[package]] name = "mkdocs-git-revision-date-localized-plugin" -version = "1.2.4" +version = "1.2.5" description = "Mkdocs plugin that enables displaying the localized date of the last git modification of a markdown file." optional = false python-versions = ">=3.8" files = [ - {file = "mkdocs-git-revision-date-localized-plugin-1.2.4.tar.gz", hash = "sha256:08fd0c6f33c8da9e00daf40f7865943113b3879a1c621b2bbf0fa794ffe997d3"}, - {file = "mkdocs_git_revision_date_localized_plugin-1.2.4-py3-none-any.whl", hash = "sha256:1f94eb510862ef94e982a2910404fa17a1657ecf29f45a07b0f438c00767fc85"}, + {file = "mkdocs_git_revision_date_localized_plugin-1.2.5-py3-none-any.whl", hash = "sha256:d796a18b07cfcdb154c133e3ec099d2bb5f38389e4fd54d3eb516a8a736815b8"}, + {file = "mkdocs_git_revision_date_localized_plugin-1.2.5.tar.gz", hash = "sha256:0c439816d9d0dba48e027d9d074b2b9f1d7cd179f74ba46b51e4da7bb3dc4b9b"}, ] [package.dependencies] @@ -2162,13 +2180,12 @@ pytz = "*" [[package]] name = "mkdocs-jupyter" -version = "0.24.3" +version = "0.24.7" description = "Use Jupyter in mkdocs websites" optional = false -python-versions = ">=3.7" +python-versions = ">=3.8" files = [ - {file = "mkdocs_jupyter-0.24.3-py3-none-any.whl", hash = "sha256:904262a8678a5e5920b7c3c03b5010b36301a69d0a38f2fcbf430493adf6879e"}, - {file = "mkdocs_jupyter-0.24.3.tar.gz", hash = "sha256:3d81da9aea27480e93bab22438910c4f0b9630613e74f85b576590d78e0e8b14"}, + {file = "mkdocs_jupyter-0.24.7-py3-none-any.whl", hash = "sha256:893d04bea1e007479a46e4e72852cd4d280c4d358ce4a0445250f3f80c639723"}, ] [package.dependencies] @@ -2179,18 +2196,15 @@ mkdocs-material = ">9.0.0" nbconvert = ">=7.2.9,<8" pygments = ">2.12.0" -[package.extras] -test = ["coverage[toml]", "pymdown-extensions", "pytest", "pytest-cov"] - [[package]] name = "mkdocs-material" -version = "9.5.17" +version = "9.5.21" description = "Documentation that simply works" optional = false python-versions = ">=3.8" files = [ - {file = "mkdocs_material-9.5.17-py3-none-any.whl", hash = "sha256:14a2a60119a785e70e765dd033e6211367aca9fc70230e577c1cf6a326949571"}, - {file = "mkdocs_material-9.5.17.tar.gz", hash = "sha256:06ae1275a72db1989cf6209de9e9ecdfbcfdbc24c58353877b2bb927dbe413e4"}, + {file = "mkdocs_material-9.5.21-py3-none-any.whl", hash = "sha256:210e1f179682cd4be17d5c641b2f4559574b9dea2f589c3f0e7c17c5bd1959bc"}, + {file = "mkdocs_material-9.5.21.tar.gz", hash = "sha256:049f82770f40559d3c2aa2259c562ea7257dbb4aaa9624323b5ef27b2d95a450"}, ] [package.dependencies] @@ -2199,7 +2213,7 @@ cairosvg = {version = ">=2.6,<3.0", optional = true, markers = "extra == \"imagi colorama = ">=0.4,<1.0" jinja2 = ">=3.0,<4.0" markdown = ">=3.2,<4.0" -mkdocs = ">=1.5.3,<1.6.0" +mkdocs = ">=1.6,<2.0" mkdocs-material-extensions = ">=1.3,<2.0" paginate = ">=0.5,<1.0" pillow = {version = ">=10.2,<11.0", optional = true, markers = "extra == \"imaging\""} @@ -2226,13 +2240,13 @@ files = [ [[package]] name = "mkdocstrings" -version = "0.24.3" +version = "0.25.1" description = "Automatic documentation from sources, for MkDocs." optional = false python-versions = ">=3.8" files = [ - {file = "mkdocstrings-0.24.3-py3-none-any.whl", hash = "sha256:5c9cf2a32958cd161d5428699b79c8b0988856b0d4a8c5baf8395fc1bf4087c3"}, - {file = "mkdocstrings-0.24.3.tar.gz", hash = "sha256:f327b234eb8d2551a306735436e157d0a22d45f79963c60a8b585d5f7a94c1d2"}, + {file = "mkdocstrings-0.25.1-py3-none-any.whl", hash = "sha256:da01fcc2670ad61888e8fe5b60afe9fee5781017d67431996832d63e887c2e51"}, + {file = "mkdocstrings-0.25.1.tar.gz", hash = "sha256:c3a2515f31577f311a9ee58d089e4c51fc6046dbd9e9b4c3de4c3194667fe9bf"}, ] [package.dependencies] @@ -2281,38 +2295,38 @@ files = [ [[package]] name = "mypy" -version = "1.9.0" +version = "1.10.0" description = "Optional static typing for Python" optional = false python-versions = ">=3.8" files = [ - {file = "mypy-1.9.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:f8a67616990062232ee4c3952f41c779afac41405806042a8126fe96e098419f"}, - {file = "mypy-1.9.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d357423fa57a489e8c47b7c85dfb96698caba13d66e086b412298a1a0ea3b0ed"}, - {file = "mypy-1.9.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:49c87c15aed320de9b438ae7b00c1ac91cd393c1b854c2ce538e2a72d55df150"}, - {file = "mypy-1.9.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:48533cdd345c3c2e5ef48ba3b0d3880b257b423e7995dada04248725c6f77374"}, - {file = "mypy-1.9.0-cp310-cp310-win_amd64.whl", hash = "sha256:4d3dbd346cfec7cb98e6cbb6e0f3c23618af826316188d587d1c1bc34f0ede03"}, - {file = "mypy-1.9.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:653265f9a2784db65bfca694d1edd23093ce49740b2244cde583aeb134c008f3"}, - {file = "mypy-1.9.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:3a3c007ff3ee90f69cf0a15cbcdf0995749569b86b6d2f327af01fd1b8aee9dc"}, - {file = "mypy-1.9.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2418488264eb41f69cc64a69a745fad4a8f86649af4b1041a4c64ee61fc61129"}, - {file = "mypy-1.9.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:68edad3dc7d70f2f17ae4c6c1b9471a56138ca22722487eebacfd1eb5321d612"}, - {file = "mypy-1.9.0-cp311-cp311-win_amd64.whl", hash = "sha256:85ca5fcc24f0b4aeedc1d02f93707bccc04733f21d41c88334c5482219b1ccb3"}, - {file = "mypy-1.9.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:aceb1db093b04db5cd390821464504111b8ec3e351eb85afd1433490163d60cd"}, - {file = "mypy-1.9.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:0235391f1c6f6ce487b23b9dbd1327b4ec33bb93934aa986efe8a9563d9349e6"}, - {file = "mypy-1.9.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d4d5ddc13421ba3e2e082a6c2d74c2ddb3979c39b582dacd53dd5d9431237185"}, - {file = "mypy-1.9.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:190da1ee69b427d7efa8aa0d5e5ccd67a4fb04038c380237a0d96829cb157913"}, - {file = "mypy-1.9.0-cp312-cp312-win_amd64.whl", hash = "sha256:fe28657de3bfec596bbeef01cb219833ad9d38dd5393fc649f4b366840baefe6"}, - {file = "mypy-1.9.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:e54396d70be04b34f31d2edf3362c1edd023246c82f1730bbf8768c28db5361b"}, - {file = "mypy-1.9.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:5e6061f44f2313b94f920e91b204ec600982961e07a17e0f6cd83371cb23f5c2"}, - {file = "mypy-1.9.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:81a10926e5473c5fc3da8abb04119a1f5811a236dc3a38d92015cb1e6ba4cb9e"}, - {file = "mypy-1.9.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:b685154e22e4e9199fc95f298661deea28aaede5ae16ccc8cbb1045e716b3e04"}, - {file = "mypy-1.9.0-cp38-cp38-win_amd64.whl", hash = "sha256:5d741d3fc7c4da608764073089e5f58ef6352bedc223ff58f2f038c2c4698a89"}, - {file = "mypy-1.9.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:587ce887f75dd9700252a3abbc9c97bbe165a4a630597845c61279cf32dfbf02"}, - {file = "mypy-1.9.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:f88566144752999351725ac623471661c9d1cd8caa0134ff98cceeea181789f4"}, - {file = "mypy-1.9.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:61758fabd58ce4b0720ae1e2fea5cfd4431591d6d590b197775329264f86311d"}, - {file = "mypy-1.9.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:e49499be624dead83927e70c756970a0bc8240e9f769389cdf5714b0784ca6bf"}, - {file = "mypy-1.9.0-cp39-cp39-win_amd64.whl", hash = "sha256:571741dc4194b4f82d344b15e8837e8c5fcc462d66d076748142327626a1b6e9"}, - {file = "mypy-1.9.0-py3-none-any.whl", hash = "sha256:a260627a570559181a9ea5de61ac6297aa5af202f06fd7ab093ce74e7181e43e"}, - {file = "mypy-1.9.0.tar.gz", hash = "sha256:3cc5da0127e6a478cddd906068496a97a7618a21ce9b54bde5bf7e539c7af974"}, + {file = "mypy-1.10.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:da1cbf08fb3b851ab3b9523a884c232774008267b1f83371ace57f412fe308c2"}, + {file = "mypy-1.10.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:12b6bfc1b1a66095ab413160a6e520e1dc076a28f3e22f7fb25ba3b000b4ef99"}, + {file = "mypy-1.10.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9e36fb078cce9904c7989b9693e41cb9711e0600139ce3970c6ef814b6ebc2b2"}, + {file = "mypy-1.10.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:2b0695d605ddcd3eb2f736cd8b4e388288c21e7de85001e9f85df9187f2b50f9"}, + {file = "mypy-1.10.0-cp310-cp310-win_amd64.whl", hash = "sha256:cd777b780312ddb135bceb9bc8722a73ec95e042f911cc279e2ec3c667076051"}, + {file = "mypy-1.10.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:3be66771aa5c97602f382230165b856c231d1277c511c9a8dd058be4784472e1"}, + {file = "mypy-1.10.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:8b2cbaca148d0754a54d44121b5825ae71868c7592a53b7292eeb0f3fdae95ee"}, + {file = "mypy-1.10.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1ec404a7cbe9fc0e92cb0e67f55ce0c025014e26d33e54d9e506a0f2d07fe5de"}, + {file = "mypy-1.10.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e22e1527dc3d4aa94311d246b59e47f6455b8729f4968765ac1eacf9a4760bc7"}, + {file = "mypy-1.10.0-cp311-cp311-win_amd64.whl", hash = "sha256:a87dbfa85971e8d59c9cc1fcf534efe664d8949e4c0b6b44e8ca548e746a8d53"}, + {file = "mypy-1.10.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:a781f6ad4bab20eef8b65174a57e5203f4be627b46291f4589879bf4e257b97b"}, + {file = "mypy-1.10.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:b808e12113505b97d9023b0b5e0c0705a90571c6feefc6f215c1df9381256e30"}, + {file = "mypy-1.10.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8f55583b12156c399dce2df7d16f8a5095291354f1e839c252ec6c0611e86e2e"}, + {file = "mypy-1.10.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:4cf18f9d0efa1b16478c4c129eabec36148032575391095f73cae2e722fcf9d5"}, + {file = "mypy-1.10.0-cp312-cp312-win_amd64.whl", hash = "sha256:bc6ac273b23c6b82da3bb25f4136c4fd42665f17f2cd850771cb600bdd2ebeda"}, + {file = "mypy-1.10.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:9fd50226364cd2737351c79807775136b0abe084433b55b2e29181a4c3c878c0"}, + {file = "mypy-1.10.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:f90cff89eea89273727d8783fef5d4a934be2fdca11b47def50cf5d311aff727"}, + {file = "mypy-1.10.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fcfc70599efde5c67862a07a1aaf50e55bce629ace26bb19dc17cece5dd31ca4"}, + {file = "mypy-1.10.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:075cbf81f3e134eadaf247de187bd604748171d6b79736fa9b6c9685b4083061"}, + {file = "mypy-1.10.0-cp38-cp38-win_amd64.whl", hash = "sha256:3f298531bca95ff615b6e9f2fc0333aae27fa48052903a0ac90215021cdcfa4f"}, + {file = "mypy-1.10.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:fa7ef5244615a2523b56c034becde4e9e3f9b034854c93639adb667ec9ec2976"}, + {file = "mypy-1.10.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3236a4c8f535a0631f85f5fcdffba71c7feeef76a6002fcba7c1a8e57c8be1ec"}, + {file = "mypy-1.10.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4a2b5cdbb5dd35aa08ea9114436e0d79aceb2f38e32c21684dcf8e24e1e92821"}, + {file = "mypy-1.10.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:92f93b21c0fe73dc00abf91022234c79d793318b8a96faac147cd579c1671746"}, + {file = "mypy-1.10.0-cp39-cp39-win_amd64.whl", hash = "sha256:28d0e038361b45f099cc086d9dd99c15ff14d0188f44ac883010e172ce86c38a"}, + {file = "mypy-1.10.0-py3-none-any.whl", hash = "sha256:f8c083976eb530019175aabadb60921e73b4f45736760826aa1689dda8208aee"}, + {file = "mypy-1.10.0.tar.gz", hash = "sha256:3d087fcbec056c4ee34974da493a826ce316947485cef3901f511848e687c131"}, ] [package.dependencies] @@ -2361,13 +2375,13 @@ test = ["flaky", "ipykernel (>=6.19.3)", "ipython", "ipywidgets", "nbconvert (>= [[package]] name = "nbconvert" -version = "7.16.3" +version = "7.16.4" description = "Converting Jupyter Notebooks (.ipynb files) to other formats. Output formats include asciidoc, html, latex, markdown, pdf, py, rst, script. nbconvert can be used both as a Python library (`import nbconvert`) or as a command line tool (invoked as `jupyter nbconvert ...`)." optional = false python-versions = ">=3.8" files = [ - {file = "nbconvert-7.16.3-py3-none-any.whl", hash = "sha256:ddeff14beeeedf3dd0bc506623e41e4507e551736de59df69a91f86700292b3b"}, - {file = "nbconvert-7.16.3.tar.gz", hash = "sha256:a6733b78ce3d47c3f85e504998495b07e6ea9cf9bf6ec1c98dda63ec6ad19142"}, + {file = "nbconvert-7.16.4-py3-none-any.whl", hash = "sha256:05873c620fe520b6322bf8a5ad562692343fe3452abda5765c7a34b7d1aa3eb3"}, + {file = "nbconvert-7.16.4.tar.gz", hash = "sha256:86ca91ba266b0a448dc96fa6c5b9d98affabde2867b363258703536807f9f7f4"}, ] [package.dependencies] @@ -2389,9 +2403,9 @@ tinycss2 = "*" traitlets = ">=5.1" [package.extras] -all = ["nbconvert[docs,qtpdf,serve,test,webpdf]"] +all = ["flaky", "ipykernel", "ipython", "ipywidgets (>=7.5)", "myst-parser", "nbsphinx (>=0.2.12)", "playwright", "pydata-sphinx-theme", "pyqtwebengine (>=5.15)", "pytest (>=7)", "sphinx (==5.0.2)", "sphinxcontrib-spelling", "tornado (>=6.1)"] docs = ["ipykernel", "ipython", "myst-parser", "nbsphinx (>=0.2.12)", "pydata-sphinx-theme", "sphinx (==5.0.2)", "sphinxcontrib-spelling"] -qtpdf = ["nbconvert[qtpng]"] +qtpdf = ["pyqtwebengine (>=5.15)"] qtpng = ["pyqtwebengine (>=5.15)"] serve = ["tornado (>=6.1)"] test = ["flaky", "ipykernel", "ipywidgets (>=7.5)", "pytest (>=7)"] @@ -2470,13 +2484,13 @@ setuptools = "*" [[package]] name = "notebook" -version = "7.1.2" +version = "7.1.3" description = "Jupyter Notebook - A web-based notebook environment for interactive computing" optional = false python-versions = ">=3.8" files = [ - {file = "notebook-7.1.2-py3-none-any.whl", hash = "sha256:fc6c24b9aef18d0cd57157c9c47e95833b9b0bdc599652639acf0bdb61dc7d5f"}, - {file = "notebook-7.1.2.tar.gz", hash = "sha256:efc2c80043909e0faa17fce9e9b37c059c03af0ec99a4d4db84cb21d9d2e936a"}, + {file = "notebook-7.1.3-py3-none-any.whl", hash = "sha256:919b911e59f41f6e3857ce93c9d93535ba66bb090059712770e5968c07e1004d"}, + {file = "notebook-7.1.3.tar.gz", hash = "sha256:41fcebff44cf7bb9377180808bcbae066629b55d8c7722f1ebbe75ca44f9cfc1"}, ] [package.dependencies] @@ -2819,13 +2833,13 @@ test = ["appdirs (==1.4.4)", "covdefaults (>=2.3)", "pytest (>=7.4.3)", "pytest- [[package]] name = "pluggy" -version = "1.4.0" +version = "1.5.0" description = "plugin and hook calling mechanisms for python" optional = false python-versions = ">=3.8" files = [ - {file = "pluggy-1.4.0-py3-none-any.whl", hash = "sha256:7db9f7b503d67d1c5b95f59773ebb58a8c1c288129a88665838012cfb07b8981"}, - {file = "pluggy-1.4.0.tar.gz", hash = "sha256:8c85c2876142a764e5b7548e7d9a0e0ddb46f5185161049a79b7e974454223be"}, + {file = "pluggy-1.5.0-py3-none-any.whl", hash = "sha256:44e1ad92c8ca002de6377e165f3e0f1be63266ab4d554740532335b9d75ea669"}, + {file = "pluggy-1.5.0.tar.gz", hash = "sha256:2cffa88e94fdc978c4c574f15f9e59b7f4201d439195c3715ca9e2486f1d0cf1"}, ] [package.extras] @@ -3024,13 +3038,13 @@ tomli = {version = ">=1.1.0", markers = "python_version < \"3.11\""} [[package]] name = "pytest" -version = "8.1.1" +version = "8.2.0" description = "pytest: simple powerful testing with Python" optional = false python-versions = ">=3.8" files = [ - {file = "pytest-8.1.1-py3-none-any.whl", hash = "sha256:2a8386cfc11fa9d2c50ee7b2a57e7d898ef90470a7a34c4b949ff59662bb78b7"}, - {file = "pytest-8.1.1.tar.gz", hash = "sha256:ac978141a75948948817d360297b7aae0fcb9d6ff6bc9ec6d514b85d5a65c044"}, + {file = "pytest-8.2.0-py3-none-any.whl", hash = "sha256:1733f0620f6cda4095bbf0d9ff8022486e91892245bb9e7d5542c018f612f233"}, + {file = "pytest-8.2.0.tar.gz", hash = "sha256:d507d4482197eac0ba2bae2e9babf0672eb333017bcedaa5fb1a3d42c1174b3f"}, ] [package.dependencies] @@ -3038,11 +3052,11 @@ colorama = {version = "*", markers = "sys_platform == \"win32\""} exceptiongroup = {version = ">=1.0.0rc8", markers = "python_version < \"3.11\""} iniconfig = "*" packaging = "*" -pluggy = ">=1.4,<2.0" +pluggy = ">=1.5,<2.0" tomli = {version = ">=1", markers = "python_version < \"3.11\""} [package.extras] -testing = ["argcomplete", "attrs (>=19.2)", "hypothesis (>=3.56)", "mock", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"] +dev = ["argcomplete", "attrs (>=19.2)", "hypothesis (>=3.56)", "mock", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"] [[package]] name = "python-dateutil" @@ -3647,28 +3661,28 @@ files = [ [[package]] name = "ruff" -version = "0.3.5" +version = "0.4.3" description = "An extremely fast Python linter and code formatter, written in Rust." optional = false python-versions = ">=3.7" files = [ - {file = "ruff-0.3.5-py3-none-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:aef5bd3b89e657007e1be6b16553c8813b221ff6d92c7526b7e0227450981eac"}, - {file = "ruff-0.3.5-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:89b1e92b3bd9fca249153a97d23f29bed3992cff414b222fcd361d763fc53f12"}, - {file = "ruff-0.3.5-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5e55771559c89272c3ebab23326dc23e7f813e492052391fe7950c1a5a139d89"}, - {file = "ruff-0.3.5-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:dabc62195bf54b8a7876add6e789caae0268f34582333cda340497c886111c39"}, - {file = "ruff-0.3.5-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3a05f3793ba25f194f395578579c546ca5d83e0195f992edc32e5907d142bfa3"}, - {file = "ruff-0.3.5-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:dfd3504e881082959b4160ab02f7a205f0fadc0a9619cc481982b6837b2fd4c0"}, - {file = "ruff-0.3.5-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:87258e0d4b04046cf1d6cc1c56fadbf7a880cc3de1f7294938e923234cf9e498"}, - {file = "ruff-0.3.5-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:712e71283fc7d9f95047ed5f793bc019b0b0a29849b14664a60fd66c23b96da1"}, - {file = "ruff-0.3.5-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a532a90b4a18d3f722c124c513ffb5e5eaff0cc4f6d3aa4bda38e691b8600c9f"}, - {file = "ruff-0.3.5-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:122de171a147c76ada00f76df533b54676f6e321e61bd8656ae54be326c10296"}, - {file = "ruff-0.3.5-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:d80a6b18a6c3b6ed25b71b05eba183f37d9bc8b16ace9e3d700997f00b74660b"}, - {file = "ruff-0.3.5-py3-none-musllinux_1_2_i686.whl", hash = "sha256:a7b6e63194c68bca8e71f81de30cfa6f58ff70393cf45aab4c20f158227d5936"}, - {file = "ruff-0.3.5-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:a759d33a20c72f2dfa54dae6e85e1225b8e302e8ac655773aff22e542a300985"}, - {file = "ruff-0.3.5-py3-none-win32.whl", hash = "sha256:9d8605aa990045517c911726d21293ef4baa64f87265896e491a05461cae078d"}, - {file = "ruff-0.3.5-py3-none-win_amd64.whl", hash = "sha256:dc56bb16a63c1303bd47563c60482a1512721053d93231cf7e9e1c6954395a0e"}, - {file = "ruff-0.3.5-py3-none-win_arm64.whl", hash = "sha256:faeeae9905446b975dcf6d4499dc93439b131f1443ee264055c5716dd947af55"}, - {file = "ruff-0.3.5.tar.gz", hash = "sha256:a067daaeb1dc2baf9b82a32dae67d154d95212080c80435eb052d95da647763d"}, + {file = "ruff-0.4.3-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:b70800c290f14ae6fcbb41bbe201cf62dfca024d124a1f373e76371a007454ce"}, + {file = "ruff-0.4.3-py3-none-macosx_11_0_arm64.whl", hash = "sha256:08a0d6a22918ab2552ace96adeaca308833873a4d7d1d587bb1d37bae8728eb3"}, + {file = "ruff-0.4.3-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:eba1f14df3c758dd7de5b55fbae7e1c8af238597961e5fb628f3de446c3c40c5"}, + {file = "ruff-0.4.3-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:819fb06d535cc76dfddbfe8d3068ff602ddeb40e3eacbc90e0d1272bb8d97113"}, + {file = "ruff-0.4.3-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0bfc9e955e6dc6359eb6f82ea150c4f4e82b660e5b58d9a20a0e42ec3bb6342b"}, + {file = "ruff-0.4.3-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:510a67d232d2ebe983fddea324dbf9d69b71c4d2dfeb8a862f4a127536dd4cfb"}, + {file = "ruff-0.4.3-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:dc9ff11cd9a092ee7680a56d21f302bdda14327772cd870d806610a3503d001f"}, + {file = "ruff-0.4.3-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:29efff25bf9ee685c2c8390563a5b5c006a3fee5230d28ea39f4f75f9d0b6f2f"}, + {file = "ruff-0.4.3-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:18b00e0bcccf0fc8d7186ed21e311dffd19761cb632241a6e4fe4477cc80ef6e"}, + {file = "ruff-0.4.3-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:262f5635e2c74d80b7507fbc2fac28fe0d4fef26373bbc62039526f7722bca1b"}, + {file = "ruff-0.4.3-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:7363691198719c26459e08cc17c6a3dac6f592e9ea3d2fa772f4e561b5fe82a3"}, + {file = "ruff-0.4.3-py3-none-musllinux_1_2_i686.whl", hash = "sha256:eeb039f8428fcb6725bb63cbae92ad67b0559e68b5d80f840f11914afd8ddf7f"}, + {file = "ruff-0.4.3-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:927b11c1e4d0727ce1a729eace61cee88a334623ec424c0b1c8fe3e5f9d3c865"}, + {file = "ruff-0.4.3-py3-none-win32.whl", hash = "sha256:25cacda2155778beb0d064e0ec5a3944dcca9c12715f7c4634fd9d93ac33fd30"}, + {file = "ruff-0.4.3-py3-none-win_amd64.whl", hash = "sha256:7a1c3a450bc6539ef00da6c819fb1b76b6b065dec585f91456e7c0d6a0bbc725"}, + {file = "ruff-0.4.3-py3-none-win_arm64.whl", hash = "sha256:71ca5f8ccf1121b95a59649482470c5601c60a416bf189d553955b0338e34614"}, + {file = "ruff-0.4.3.tar.gz", hash = "sha256:ff0a3ef2e3c4b6d133fbedcf9586abfbe38d076041f2dc18ffb2c7e0485d5a07"}, ] [[package]] @@ -3900,17 +3914,6 @@ webencodings = ">=0.4" doc = ["sphinx", "sphinx_rtd_theme"] test = ["flake8", "isort", "pytest"] -[[package]] -name = "toml" -version = "0.10.2" -description = "Python Library for Tom's Obvious, Minimal Language" -optional = false -python-versions = ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*" -files = [ - {file = "toml-0.10.2-py2.py3-none-any.whl", hash = "sha256:806143ae5bfb6a3c6e736a764057db0e6a0e05e338b5630894a5f779cabb4f9b"}, - {file = "toml-0.10.2.tar.gz", hash = "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f"}, -] - [[package]] name = "tomli" version = "2.0.1" @@ -3944,13 +3947,13 @@ files = [ [[package]] name = "tox" -version = "4.14.2" +version = "4.15.0" description = "tox is a generic virtualenv management and test command line tool" optional = false python-versions = ">=3.8" files = [ - {file = "tox-4.14.2-py3-none-any.whl", hash = "sha256:2900c4eb7b716af4a928a7fdc2ed248ad6575294ed7cfae2ea41203937422847"}, - {file = "tox-4.14.2.tar.gz", hash = "sha256:0defb44f6dafd911b61788325741cc6b2e12ea71f987ac025ad4d649f1f1a104"}, + {file = "tox-4.15.0-py3-none-any.whl", hash = "sha256:300055f335d855b2ab1b12c5802de7f62a36d4fd53f30bd2835f6a201dda46ea"}, + {file = "tox-4.15.0.tar.gz", hash = "sha256:7a0beeef166fbe566f54f795b4906c31b428eddafc0102ac00d20998dd1933f6"}, ] [package.dependencies] @@ -3971,13 +3974,13 @@ testing = ["build[virtualenv] (>=1.0.3)", "covdefaults (>=2.3)", "detect-test-po [[package]] name = "tqdm" -version = "4.66.2" +version = "4.66.4" description = "Fast, Extensible Progress Meter" optional = true python-versions = ">=3.7" files = [ - {file = "tqdm-4.66.2-py3-none-any.whl", hash = "sha256:1ee4f8a893eb9bef51c6e35730cebf234d5d0b6bd112b0271e10ed7c24a02bd9"}, - {file = "tqdm-4.66.2.tar.gz", hash = "sha256:6cd52cdf0fef0e0f543299cfc96fec90d7b8a7e88745f411ec33eb44d5ed3531"}, + {file = "tqdm-4.66.4-py3-none-any.whl", hash = "sha256:b75ca56b413b030bc3f00af51fd2c1a1a5eac6a0c1cca83cbb37a5c52abce644"}, + {file = "tqdm-4.66.4.tar.gz", hash = "sha256:e4d936c9de8727928f3be6079590e97d9abfe8d39a590be678eb5919ffc186bb"}, ] [package.dependencies] @@ -4254,4 +4257,4 @@ desktop = ["opencv-python"] [metadata] lock-version = "2.0" python-versions = "^3.8" -content-hash = "56ddae6824a9f28c9954badd4c642c57f687b099c6169f97fa0372e294500c17" +content-hash = "29af5aa06f97e77a2dba94c5a6d77d7d1903448724df07416026a378d3c6a64d" diff --git a/pyproject.toml b/pyproject.toml index 7be53b6c..509c05b9 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "supervision" -version = "0.20.0rc2" +version = "0.21.0rc3" description = "A set of easy-to-use utils that will come in handy in any Computer Vision project" authors = ["Piotr Skalski "] maintainers = ["Piotr Skalski "] @@ -43,7 +43,7 @@ defusedxml = "^0.7.1" opencv-python = { version = ">=4.5.5.64", optional = true } opencv-python-headless = ">=4.5.5.64" requests = { version = ">=2.26.0,<=2.31.0", optional = true } -tqdm = { version = ">=4.62.3,<=4.66.2", optional = true } +tqdm = { version = ">=4.62.3,<=4.66.4", optional = true } pillow = ">=9.4" [tool.poetry.extras] @@ -67,7 +67,7 @@ nbconvert = "^7.14.2" [tool.poetry.group.docs.dependencies] mkdocs-material = {extras = ["imaging"], version = "^9.5.5"} -mkdocstrings = {extras = ["python"], version = ">=0.20,<0.25"} +mkdocstrings = {extras = ["python"], version = ">=0.20,<0.26"} mike = "^2.0.0" # For Documentation Development use Python 3.10 or above #Β Use Latest mkdocs-jupyter min 0.24.6 for Jupyter Notebook Theme support diff --git a/supervision/__init__.py b/supervision/__init__.py index 8c3acc26..bb526514 100644 --- a/supervision/__init__.py +++ b/supervision/__init__.py @@ -69,17 +69,20 @@ from supervision.draw.utils import ( ) from supervision.geometry.core import Point, Position, Rect from supervision.geometry.utils import get_polygon_center +from supervision.keypoint.annotators import EdgeAnnotator, VertexAnnotator +from supervision.keypoint.core import KeyPoints from supervision.metrics.detection import ConfusionMatrix, MeanAveragePrecision from supervision.tracker.byte_tracker.core import ByteTrack +from supervision.utils.conversion import cv2_to_pillow, pillow_to_cv2 from supervision.utils.file import list_files_with_extensions from supervision.utils.image import ( ImageSink, create_tiles, crop_image, letterbox_image, - place_image, + overlay_image, resize_image, - resize_image_keeping_aspect_ratio, + scale_image, ) from supervision.utils.notebook import plot_image, plot_images_grid from supervision.utils.video import ( diff --git a/supervision/annotators/core.py b/supervision/annotators/core.py index 9f6cdb36..ac901862 100644 --- a/supervision/annotators/core.py +++ b/supervision/annotators/core.py @@ -13,7 +13,7 @@ from supervision.draw.color import Color, ColorPalette from supervision.draw.utils import draw_polygon from supervision.geometry.core import Position from supervision.utils.conversion import convert_for_annotation_method -from supervision.utils.image import crop_image, place_image, resize_image +from supervision.utils.image import crop_image, overlay_image, scale_image class BoundingBoxAnnotator(BaseAnnotator): @@ -1965,7 +1965,7 @@ class CropAnnotator(BaseAnnotator): crop_image(image=scene, xyxy=xyxy) for xyxy in detections.xyxy.astype(int) ] resized_crops = [ - resize_image(image=crop, scale_factor=self.scale_factor) for crop in crops + scale_image(image=crop, scale_factor=self.scale_factor) for crop in crops ] anchors = detections.get_anchors_coordinates(anchor=self.position).astype(int) @@ -1974,7 +1974,9 @@ class CropAnnotator(BaseAnnotator): (x1, y1), (x2, y2) = self.calculate_crop_coordinates( anchor=anchor, crop_wh=crop_wh, position=self.position ) - scene = place_image(scene=scene, image=resized_crop, anchor=(x1, y1)) + scene = overlay_image( + scene=scene, inserted_image=resized_crop, anchor=(x1, y1) + ) color = resolve_color( color=self.border_color, detections=detections, diff --git a/supervision/assets/list.py b/supervision/assets/list.py index 83518cdb..8a01b758 100644 --- a/supervision/assets/list.py +++ b/supervision/assets/list.py @@ -18,6 +18,8 @@ class VideoAssets(Enum): | `SUBWAY` | `subway.mp4` | [Link](https://media.roboflow.com/supervision/video-examples/subway.mp4) | | `MARKET_SQUARE` | `market-square.mp4` | [Link](https://media.roboflow.com/supervision/video-examples/market-square.mp4) | | `PEOPLE_WALKING` | `people-walking.mp4` | [Link](https://media.roboflow.com/supervision/video-examples/people-walking.mp4) | + | `BEACH` | `beach-1.mp4` | [Link](https://media.roboflow.com/supervision/video-examples/beach-1.mp4) | + | `BASKETBALL` | `basketball-1.mp4` | [Link](https://media.roboflow.com/supervision/video-examples/basketball-1.mp4) | """ # noqa: E501 // docs VEHICLES = "vehicles.mp4" @@ -27,6 +29,8 @@ class VideoAssets(Enum): SUBWAY = "subway.mp4" MARKET_SQUARE = "market-square.mp4" PEOPLE_WALKING = "people-walking.mp4" + BEACH = "beach-1.mp4" + BASKETBALL = "basketball-1.mp4" @classmethod def list(cls): @@ -62,4 +66,12 @@ VIDEO_ASSETS: Dict[str, Tuple[str, str]] = { f"{BASE_VIDEO_URL}{VideoAssets.PEOPLE_WALKING.value}", "0574c053c8686c3f1dc0aa3743e45cb9", ), + VideoAssets.BEACH.value: ( + f"{BASE_VIDEO_URL}{VideoAssets.BEACH.value}", + "4175d42fec4d450ed081523fd39e0cf8", + ), + VideoAssets.BASKETBALL.value: ( + f"{BASE_VIDEO_URL}{VideoAssets.BASKETBALL.value}", + "60d94a3c7c47d16f09d342b088012ecc", + ), } diff --git a/supervision/detection/annotate.py b/supervision/detection/annotate.py index f32c7344..f496b248 100644 --- a/supervision/detection/annotate.py +++ b/supervision/detection/annotate.py @@ -9,10 +9,6 @@ from supervision.utils.conversion import convert_for_annotation_method from supervision.utils.internal import deprecated -@deprecated( - "`BoxAnnotator` is deprecated and will be removed in " - "`supervision-0.22.0`. Use `BoundingBoxAnnotator` and `LabelAnnotator` instead" -) class BoxAnnotator: """ A class for drawing bounding boxes on an image using detections provided. @@ -46,6 +42,10 @@ class BoxAnnotator: self.text_thickness: int = text_thickness self.text_padding: int = text_padding + @deprecated( + "`BoxAnnotator` is deprecated and will be removed in " + "`supervision-0.22.0`. Use `BoundingBoxAnnotator` and `LabelAnnotator` instead" + ) @convert_for_annotation_method def annotate( self, diff --git a/supervision/detection/core.py b/supervision/detection/core.py index a9a4ee92..b60e3363 100644 --- a/supervision/detection/core.py +++ b/supervision/detection/core.py @@ -20,11 +20,11 @@ from supervision.detection.utils import ( merge_data, non_max_merge, process_roboflow_result, - validate_detections_fields, xywh_to_xyxy, ) from supervision.geometry.core import Position from supervision.utils.internal import deprecated +from supervision.validators import validate_detections_fields def _merge_object_detection_pair(det1: Detections, det2: Detections) -> Detections: @@ -92,34 +92,71 @@ def _merge_object_detection_pair(det1: Detections, det2: Detections) -> Detectio @dataclass class Detections: """ - The `sv.Detections` allows you to convert results from a variety of object detection - and segmentation models into a single, unified format. The `sv.Detections` class - enables easy data manipulation and filtering, and provides a consistent API for - Supervision's tools like trackers, annotators, and zones. + The `sv.Detections` class in the Supervision library standardizes results from + various object detection and segmentation models into a consistent format. This + class simplifies data manipulation and filtering, providing a uniform API for + integration with Supervision [trackers](/trackers/), [annotators](/detection/annotators/), and [tools](/detection/tools/line_zone/). - ```python - import cv2 - import supervision as sv - from ultralytics import YOLO + === "Inference" - image = cv2.imread() - model = YOLO('yolov8s.pt') - annotator = sv.BoundingBoxAnnotator() + Use [`sv.Detections.from_inference`](/detection/core/#supervision.detection.core.Detections.from_inference) + method, which accepts model results from both detection and segmentation models. - result = model(image)[0] - detections = sv.Detections.from_ultralytics(result) + ```python + import cv2 + import supervision as sv + from inference import get_model - annotated_image = annotator.annotate(image, detections) - ``` + model = get_model(model_id="yolov8n-640") + image = cv2.imread() + results = model.infer(image)[0] + detections = sv.Detections.from_inference(results) + ``` - !!! tip + === "Ultralytics" - In `sv.Detections`, detection data is categorized into two main field types: - fixed and custom. The fixed fields include `xyxy`, `mask`, `confidence`, - `class_id`, and `tracker_id`. For any additional data requirements, custom - fields come into play, stored in the data field. These custom fields are easily - accessible using the `detections[]` syntax, providing flexibility - for diverse data handling needs. + Use [`sv.Detections.from_ultralytics`](/detection/core/#supervision.detection.core.Detections.from_ultralytics) + method, which accepts model results from both detection and segmentation models. + + ```python + import cv2 + import supervision as sv + from ultralytics import YOLO + + model = YOLO("yolov8n.pt") + image = cv2.imread() + results = model(image)[0] + detections = sv.Detections.from_ultralytics(results) + ``` + + === "Transformers" + + Use [`sv.Detections.from_transformers`](/detection/core/#supervision.detection.core.Detections.from_transformers) + method, which accepts model results from both detection and segmentation models. + + ```python + import torch + import supervision as sv + from PIL import Image + from transformers import DetrImageProcessor, DetrForObjectDetection + + processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50") + model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50") + + image = Image.open() + inputs = processor(images=image, return_tensors="pt") + + with torch.no_grad(): + outputs = model(**inputs) + + width, height = image.size + target_size = torch.tensor([[height, width]]) + results = processor.post_process_object_detection( + outputs=outputs, target_sizes=target_size)[0] + detections = sv.Detections.from_transformers( + transformers_results=results, + id2label=model.config.id2label) + ``` Attributes: xyxy (np.ndarray): An array of shape `(n, 4)` containing @@ -135,15 +172,7 @@ class Detections: data (Dict[str, Union[np.ndarray, List]]): A dictionary containing additional data where each key is a string representing the data type, and the value is either a NumPy array or a list of corresponding data. - - !!! warning - - The `data` field in the `sv.Detections` class is currently in an experimental - phase. Please be aware that its API and functionality are subject to change in - future updates as we continue to refine and improve its capabilities. - We encourage users to experiment with this feature and provide feedback, but - also to be prepared for potential modifications in upcoming releases. - """ + """ # noqa: E501 // docs xyxy: np.ndarray mask: Optional[np.ndarray] = None @@ -242,8 +271,8 @@ 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 `sv.Detections` instance from a + [YOLOv8](https://github.com/ultralytics/ultralytics) inference result. !!! Note @@ -267,10 +296,13 @@ class Detections: image = cv2.imread() model = YOLO('yolov8s.pt') - - result = model(image)[0] - detections = sv.Detections.from_ultralytics(result) + results = model(image)[0] + detections = sv.Detections.from_ultralytics(results) ``` + + !!! tip + + Class names values can be accessed using `detections["class_name"]`. """ # noqa: E501 // docs if "obb" in ultralytics_results and ultralytics_results.obb is not None: @@ -461,11 +493,6 @@ class Detections: Creates a Detections instance from object detection or segmentation [Transformer](https://github.com/huggingface/transformers) inference result. - !!! note - - Class names can be accessed using the key `class_name` in the returned - object's data attribute. - Args: transformers_results (dict): The output of Transformers model inference. A dictionary containing the `scores`, `labels`, `boxes` and `masks` keys. @@ -502,6 +529,10 @@ class Detections: id2label=model.config.id2label ) ``` + + !!! tip + + Class names values can be accessed using `detections["class_name"]`. """ # noqa: E501 // docs class_ids = transformers_results["labels"].cpu().detach().numpy().astype(int) @@ -575,17 +606,12 @@ class Detections: @classmethod def from_inference(cls, roboflow_result: Union[dict, Any]) -> Detections: """ - Create a Detections object from the [Roboflow](https://roboflow.com/) + Create a `sv.Detections` object from the [Roboflow](https://roboflow.com/) API inference result or the [Inference](https://inference.roboflow.com/) package results. This method extracts bounding boxes, class IDs, confidences, and class names from the Roboflow API result and encapsulates them into a Detections object. - !!! note - - Class names can be accessed using the key `class_name` in the returned - object's data attribute. - Args: roboflow_result (dict, any): The result from the Roboflow API or Inference package containing predictions. @@ -598,14 +624,18 @@ class Detections: ```python import cv2 import supervision as sv - from inference.models.utils import get_roboflow_model + from inference import get_model image = cv2.imread() - model = get_roboflow_model(model_id="yolov8s-640") + model = get_model(model_id="yolov8s-640") result = model.infer(image)[0] detections = sv.Detections.from_inference(result) ``` + + !!! tip + + Class names values can be accessed using `detections["class_name"]`. """ with suppress(AttributeError): roboflow_result = roboflow_result.dict(exclude_none=True, by_alias=True) @@ -655,10 +685,10 @@ class Detections: ```python import cv2 import supervision as sv - from inference.models.utils import get_roboflow_model + from inference import get_model image = cv2.imread() - model = get_roboflow_model(model_id="yolov8s-640") + model = get_model(model_id="yolov8s-640") result = model.infer(image)[0] detections = sv.Detections.from_roboflow(result) diff --git a/supervision/detection/tools/polygon_zone.py b/supervision/detection/tools/polygon_zone.py index 00b746aa..a1997212 100644 --- a/supervision/detection/tools/polygon_zone.py +++ b/supervision/detection/tools/polygon_zone.py @@ -1,3 +1,4 @@ +import warnings from dataclasses import replace from typing import Iterable, Optional, Tuple @@ -11,7 +12,7 @@ from supervision.draw.color import Color from supervision.draw.utils import draw_polygon, draw_text from supervision.geometry.core import Position from supervision.geometry.utils import get_polygon_center -from supervision.utils.internal import deprecated_parameter +from supervision.utils.internal import SupervisionWarnings, deprecated_parameter class PolygonZone: @@ -21,7 +22,6 @@ class PolygonZone: Attributes: 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_anchors (Iterable[sv.Position]): A list of positions specifying which anchors of the detections bounding box to consider when deciding on whether the detection fits within the PolygonZone @@ -41,18 +41,26 @@ class PolygonZone: def __init__( self, polygon: npt.NDArray[np.int64], - frame_resolution_wh: Tuple[int, int], + frame_resolution_wh: Optional[Tuple[int, int]] = None, triggering_anchors: Iterable[Position] = (Position.BOTTOM_CENTER,), ): + if frame_resolution_wh is not None: + warnings.warn( + "The `frame_resolution_wh` parameter is no longer required and will be " + "dropped in version supervision-0.24.0. The mask resolution is now " + "calculated automatically based on the polygon coordinates.", + category=SupervisionWarnings, + ) + self.polygon = polygon.astype(int) - self.frame_resolution_wh = frame_resolution_wh self.triggering_anchors = triggering_anchors self.current_count = 0 - width, height = frame_resolution_wh + x_max, y_max = np.max(polygon, axis=0) + self.frame_resolution_wh = (x_max + 1, y_max + 1) self.mask = polygon_to_mask( - polygon=polygon, resolution_wh=(width + 1, height + 1) + polygon=polygon, resolution_wh=(x_max + 2, y_max + 2) ) def trigger(self, detections: Detections) -> npt.NDArray[np.bool_]: diff --git a/supervision/detection/utils.py b/supervision/detection/utils.py index 9e732aeb..ec086036 100644 --- a/supervision/detection/utils.py +++ b/supervision/detection/utils.py @@ -1,5 +1,5 @@ from itertools import chain -from typing import Any, Dict, List, Optional, Tuple, Union +from typing import Dict, List, Optional, Tuple, Union import cv2 import numpy as np @@ -787,102 +787,6 @@ def calculate_masks_centroids(masks: np.ndarray) -> np.ndarray: return np.column_stack((centroid_x, centroid_y)).astype(int) -def validate_xyxy(xyxy: Any) -> None: - expected_shape = "(_, 4)" - actual_shape = str(getattr(xyxy, "shape", None)) - is_valid = isinstance(xyxy, np.ndarray) and xyxy.ndim == 2 and xyxy.shape[1] == 4 - if not is_valid: - raise ValueError( - f"xyxy must be a 2D np.ndarray with shape {expected_shape}, but got shape " - f"{actual_shape}" - ) - - -def validate_mask(mask: Any, n: int) -> None: - expected_shape = f"({n}, H, W)" - actual_shape = str(getattr(mask, "shape", None)) - is_valid = mask is None or ( - isinstance(mask, np.ndarray) and len(mask.shape) == 3 and mask.shape[0] == n - ) - if not is_valid: - raise ValueError( - f"mask must be a 3D np.ndarray with shape {expected_shape}, but got shape " - f"{actual_shape}" - ) - - -def validate_class_id(class_id: Any, n: int) -> None: - expected_shape = f"({n},)" - actual_shape = str(getattr(class_id, "shape", None)) - is_valid = class_id is None or ( - isinstance(class_id, np.ndarray) and class_id.shape == (n,) - ) - if not is_valid: - raise ValueError( - f"class_id must be a 1D np.ndarray with shape {expected_shape}, but got " - f"shape {actual_shape}" - ) - - -def validate_confidence(confidence: Any, n: int) -> None: - expected_shape = f"({n},)" - actual_shape = str(getattr(confidence, "shape", None)) - is_valid = confidence is None or ( - isinstance(confidence, np.ndarray) and confidence.shape == (n,) - ) - if not is_valid: - raise ValueError( - f"confidence must be a 1D np.ndarray with shape {expected_shape}, but got " - f"shape {actual_shape}" - ) - - -def validate_tracker_id(tracker_id: Any, n: int) -> None: - expected_shape = f"({n},)" - actual_shape = str(getattr(tracker_id, "shape", None)) - is_valid = tracker_id is None or ( - isinstance(tracker_id, np.ndarray) and tracker_id.shape == (n,) - ) - if not is_valid: - raise ValueError( - f"tracker_id must be a 1D np.ndarray with shape {expected_shape}, but got " - f"shape {actual_shape}" - ) - - -def validate_data(data: Dict[str, Any], n: int) -> None: - for key, value in data.items(): - if isinstance(value, list): - if len(value) != n: - raise ValueError(f"Length of list for key '{key}' must be {n}") - elif isinstance(value, np.ndarray): - if value.ndim == 1 and value.shape[0] != n: - raise ValueError(f"Shape of np.ndarray for key '{key}' must be ({n},)") - elif value.ndim > 1 and value.shape[0] != n: - raise ValueError( - f"First dimension of np.ndarray for key '{key}' must have size {n}" - ) - else: - raise ValueError(f"Value for key '{key}' must be a list or np.ndarray") - - -def validate_detections_fields( - xyxy: Any, - mask: Any, - class_id: Any, - confidence: Any, - tracker_id: Any, - data: Dict[str, Any], -) -> None: - validate_xyxy(xyxy) - n = len(xyxy) - validate_mask(mask, n) - validate_class_id(class_id, n) - validate_confidence(confidence, n) - validate_tracker_id(tracker_id, n) - validate_data(data, n) - - def is_data_equal(data_a: Dict[str, np.ndarray], data_b: Dict[str, np.ndarray]) -> bool: """ Compares the data payloads of two Detections instances. diff --git a/supervision/draw/color.py b/supervision/draw/color.py index debb46f3..b195cffe 100644 --- a/supervision/draw/color.py +++ b/supervision/draw/color.py @@ -1,7 +1,7 @@ from __future__ import annotations from dataclasses import dataclass -from typing import List, Tuple +from typing import List, Tuple, Union import matplotlib.pyplot as plt @@ -448,3 +448,19 @@ class ColorPalette: raise ValueError("idx argument should not be negative") idx = idx % len(self.colors) return self.colors[idx] + + +def unify_to_bgr(color: Union[Tuple[int, int, int], Color]) -> Tuple[int, int, int]: + """ + Converts a color input in multiple formats to a standardized BGR format. + + Args: + color (Union[Tuple[int, int, int], Color]): The color input to be converted, + which can be either a tuple of RGB values or an instance of a Color class. + + Returns: + Tuple[int, int, int]: The color in BGR format as a tuple of three integers. + """ + if issubclass(type(color), Color): + return color.as_bgr() + return color diff --git a/supervision/geometry/utils.py b/supervision/geometry/utils.py index 9cf717e4..8a0ca35c 100644 --- a/supervision/geometry/utils.py +++ b/supervision/geometry/utils.py @@ -5,12 +5,7 @@ from supervision.geometry.core import Point 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 center + Calculate the center of a polygon. The center is calculated as the center of the solid figure formed by the points of the polygon Parameters: @@ -23,12 +18,12 @@ def get_polygon_center(polygon: np.ndarray) -> Point: Examples: ```python - from supervision.geometry.utils import get_polygon_center import numpy as np + import supervision as sv - vertices = np.array([[0, 0], [0, 2], [2, 2], [2, 0]]) - get_polygon_center(vertices) - Point(x=1, y=1) + polygon = np.array([[0, 0], [0, 2], [2, 2], [2, 0]]) + sv.get_polygon_center(polygon=polygon) + # Point(x=1, y=1) ``` """ diff --git a/supervision/keypoint/__init__.py b/supervision/keypoint/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/supervision/keypoint/annotators.py b/supervision/keypoint/annotators.py new file mode 100644 index 00000000..4b43765c --- /dev/null +++ b/supervision/keypoint/annotators.py @@ -0,0 +1,177 @@ +from abc import ABC, abstractmethod +from logging import warn +from typing import List, Optional, Tuple + +import cv2 +import numpy as np + +from supervision.annotators.base import ImageType +from supervision.draw.color import Color +from supervision.keypoint.core import KeyPoints +from supervision.keypoint.skeletons import SKELETONS_BY_VERTEX_COUNT +from supervision.utils.conversion import convert_for_annotation_method + + +class BaseKeyPointAnnotator(ABC): + @abstractmethod + def annotate(self, scene: ImageType, key_points: KeyPoints) -> ImageType: + pass + + +class VertexAnnotator(BaseKeyPointAnnotator): + """ + A class that specializes in drawing skeleton vertices on images. It uses + specified key points to determine the locations where the vertices should be + drawn. + """ + + def __init__( + self, + color: Color = Color.ROBOFLOW, + radius: int = 4, + ) -> None: + """ + Args: + color (Color, optional): The color to use for annotating key points. + radius (int, optional): The radius of the circles used to represent the key + points. + """ + self.color = color + self.radius = radius + + @convert_for_annotation_method + def annotate(self, scene: ImageType, key_points: KeyPoints) -> ImageType: + """ + Annotates the given scene with skeleton vertices based on the provided key + points. It draws circles at each key point location. + + Args: + scene (ImageType): The image where bounding boxes will be drawn. `ImageType` + is a flexible type, accepting either `numpy.ndarray` or + `PIL.Image.Image`. + key_points (KeyPoints): A collection of key points where each key point + consists of x and y coordinates. + + Returns: + The annotated image, matching the type of `scene` (`numpy.ndarray` + or `PIL.Image.Image`) + + Example: + ```python + import supervision as sv + + image = ... + key_points = sv.KeyPoints(...) + + vertex_annotator = sv.VertexAnnotator(color=sv.Color.GREEN, radius=10) + annotated_frame = vertex_annotator.annotate( + scene=image.copy(), + key_points=key_points + ) + ``` + + ![vertex-annotator-example](https://media.roboflow.com/ + supervision-annotator-examples/vertex-annotator-example.png) + """ + if len(key_points) == 0: + return scene + + for xy in key_points.xy: + for x, y in xy: + cv2.circle( + img=scene, + center=(int(x), int(y)), + radius=self.radius, + color=self.color.as_bgr(), + thickness=-1, + ) + + return scene + + +class EdgeAnnotator(BaseKeyPointAnnotator): + """ + A class that specializes in drawing skeleton edges on images using specified key + points. It connects key points with lines to form the skeleton structure. + """ + + def __init__( + self, + color: Color = Color.ROBOFLOW, + thickness: int = 2, + edges: Optional[List[Tuple[int, int]]] = None, + ) -> None: + """ + Args: + color (Color, optional): The color to use for the edges. + thickness (int, optional): The thickness of the edges. + edges (Optional[List[Tuple[int, int]]]): The edges to draw. + If set to `None`, will attempt to select automatically. + """ + self.color = color + self.thickness = thickness + self.edges = edges + + @convert_for_annotation_method + def annotate(self, scene: ImageType, key_points: KeyPoints) -> ImageType: + """ + Annotates the given scene by drawing lines between specified key points to form + edges. + + Args: + scene (ImageType): The image where bounding boxes will be drawn. `ImageType` + is a flexible type, accepting either `numpy.ndarray` or + `PIL.Image.Image`. + key_points (KeyPoints): A collection of key points where each key point + consists of x and y coordinates. + + Returns: + Returns: + The annotated image, matching the type of `scene` (`numpy.ndarray` + or `PIL.Image.Image`) + + Example: + ```python + import supervision as sv + + image = ... + key_points = sv.KeyPoints(...) + + edge_annotator = sv.EdgeAnnotator(color=sv.Color.GREEN, thickness=5) + annotated_frame = edge_annotator.annotate( + scene=image.copy(), + key_points=key_points + ) + ``` + + ![edge-annotator-example](https://media.roboflow.com/ + supervision-annotator-examples/edge-annotator-example.png) + """ + if len(key_points) == 0: + return scene + + for xy in key_points.xy: + edges = self.edges + if not edges: + edges = SKELETONS_BY_VERTEX_COUNT.get(len(xy)) + if not edges: + warn(f"No skeleton found with {len(xy)} vertices") + return scene + + for class_a, class_b in edges: + xy_a = xy[class_a - 1] + xy_b = xy[class_b - 1] + missing_a = np.allclose(xy_a, 0) + missing_b = np.allclose(xy_b, 0) + if missing_a or missing_b: + continue + + cv2.line( + img=scene, + pt1=(int(xy_a[0]), int(xy_a[1])), + pt2=(int(xy_b[0]), int(xy_b[1])), + color=self.color.as_bgr(), + thickness=self.thickness, + ) + + return scene diff --git a/supervision/keypoint/core.py b/supervision/keypoint/core.py new file mode 100644 index 00000000..87ad9579 --- /dev/null +++ b/supervision/keypoint/core.py @@ -0,0 +1,375 @@ +from __future__ import annotations + +from contextlib import suppress +from dataclasses import dataclass, field +from typing import Any, Dict, Iterator, List, Optional, Tuple, Union + +import numpy as np +import numpy.typing as npt + +from supervision.config import CLASS_NAME_DATA_FIELD +from supervision.detection.utils import get_data_item, is_data_equal +from supervision.validators import validate_keypoints_fields + + +@dataclass +class KeyPoints: + """ + The `sv.KeyPoints` class in the Supervision library standardizes results from + various keypoint detection and pose estimation models into a consistent format. This + class simplifies data manipulation and filtering, providing a uniform API for + integration with Supervision annotators. + + === "Ultralytics" + + Use [`sv.KeyPoints.from_ultralytics`](/keypoint/core/#supervision.keypoint.core.KeyPoints.from_ultralytics) + method, which accepts model results. + + ```python + import cv2 + import supervision as sv + from ultralytics import YOLO + + image = cv2.imread() + model = YOLO('yolov8s-pose.pt') + result = model(image)[0] + key_points = sv.KeyPoints.from_ultralytics(result) + ``` + + Attributes: + xy (np.ndarray): An array of shape `(n, 2)` containing + the bounding boxes coordinates in format `[x1, y1]` + confidence (Optional[np.ndarray]): An array of shape + `(n,)` containing the confidence scores of the keypoint keypoints. + class_id (Optional[np.ndarray]): An array of shape + `(n,)` containing the class ids of the keypoint keypoints. + data (Dict[str, Union[np.ndarray, List]]): A dictionary containing additional + data where each key is a string representing the data type, and the value + is either a NumPy array or a list of corresponding data. + """ # noqa: E501 // docs + + xy: npt.NDArray[np.float32] + class_id: Optional[npt.NDArray[np.int_]] = None + confidence: Optional[npt.NDArray[np.float32]] = None + data: Dict[str, Union[npt.NDArray[Any], List]] = field(default_factory=dict) + + def __post_init__(self): + validate_keypoints_fields( + xy=self.xy, + confidence=self.confidence, + class_id=self.class_id, + data=self.data, + ) + + def __len__(self) -> int: + """ + Returns the number of keypoints in the keypoints object. + """ + return len(self.xy) + + def __iter__( + self, + ) -> Iterator[ + Tuple[ + np.ndarray, + Optional[np.ndarray], + Optional[float], + Optional[int], + Optional[int], + Dict[str, Union[np.ndarray, List]], + ] + ]: + """ + Iterates over the Keypoint object and yield a tuple of + `(xy, confidence, class_id, data)` for each keypoint detection. + """ + for i in range(len(self.xy)): + yield ( + self.xy[i], + self.confidence[i] if self.confidence is not None else None, + self.class_id[i] if self.class_id is not None else None, + get_data_item(self.data, i), + ) + + def __eq__(self, other: KeyPoints) -> bool: + return all( + [ + np.array_equal(self.xy, other.xy), + np.array_equal(self.class_id, other.class_id), + np.array_equal(self.confidence, other.confidence), + is_data_equal(self.data, other.data), + ] + ) + + @classmethod + def from_inference(cls, inference_result: Union[dict, Any]) -> KeyPoints: + """ + Create a `sv.KeyPoints` object from the [Roboflow](https://roboflow.com/) + API inference result or the [Inference](https://inference.roboflow.com/) + package results. When a keypoint detection model is used, this method + extracts the keypoint coordinates, class IDs, confidences, and class names. + + Args: + inference_result (dict, any): The result from the + Roboflow API or Inference package containing predictions with keypoints. + + Returns: + (KeyPoints): A KeyPoints object containing the keypoint coordinates, + class IDs, and confidences of each keypoint. + + Example: + ```python + import cv2 + import supervision as sv + from inference import get_model + + image = cv2.imread() + model = get_model(model_id=, api_key=) + + result = model.infer(image)[0] + key_points = sv.KeyPoints.from_inference(result) + ``` + + ```python + import cv2 + import supervision as sv + from inference_sdk import InferenceHTTPClient + + image = cv2.imread() + client = InferenceHTTPClient( + api_url="https://detect.roboflow.com", + api_key= + ) + + result = client.infer(image, model_id=) + key_points = sv.KeyPoints.from_inference(result) + ``` + """ + if isinstance(inference_result, list): + raise ValueError( + "from_inference() operates on a single result at a time." + "You can retrieve it like so: inference_result = model.infer(image)[0]" + ) + + # Unpack the result if received from inference.get_model, + # rather than inference_sdk.InferenceHTTPClient + with suppress(AttributeError): + inference_result = inference_result.dict(exclude_none=True, by_alias=True) + + if not inference_result.get("predictions"): + return cls.empty() + + xy = [] + confidence = [] + class_id = [] + class_names = [] + + for prediction in inference_result["predictions"]: + prediction_xy = [] + prediction_confidence = [] + for keypoint in prediction["keypoints"]: + prediction_xy.append([keypoint["x"], keypoint["y"]]) + prediction_confidence.append(keypoint["confidence"]) + xy.append(prediction_xy) + confidence.append(prediction_confidence) + + class_id.append(prediction["class_id"]) + class_names.append(prediction["class"]) + + data = {CLASS_NAME_DATA_FIELD: np.array(class_names)} + + return cls( + xy=np.array(xy, dtype=np.float32), + confidence=np.array(confidence, dtype=np.float32), + class_id=np.array(class_id, dtype=int), + data=data, + ) + + @classmethod + def from_ultralytics(cls, ultralytics_results) -> KeyPoints: + """ + Creates a KeyPoints instance from a + [YOLOv8](https://github.com/ultralytics/ultralytics) inference result. + + Args: + ultralytics_results (ultralytics.engine.results.Keypoints): + The output Results instance from YOLOv8 + + Returns: + KeyPoints: A new KeyPoints object. + + Example: + ```python + import cv2 + import supervision as sv + from ultralytics import YOLO + + image = cv2.imread() + model = YOLO('yolov8s-pose.pt') + result = model(image)[0] + keypoints = sv.KeyPoints.from_ultralytics(result) + ``` + """ + if ultralytics_results.keypoints.xy.numel() == 0: + return cls.empty() + + xy = ultralytics_results.keypoints.xy.cpu().numpy() + class_id = ultralytics_results.boxes.cls.cpu().numpy().astype(int) + class_names = np.array([ultralytics_results.names[i] for i in class_id]) + + confidence = ultralytics_results.keypoints.conf.cpu().numpy() + data = {CLASS_NAME_DATA_FIELD: class_names} + return cls(xy, class_id, confidence, data) + + @classmethod + def from_yolo_nas(cls, yolo_nas_results) -> KeyPoints: + """ + Create a KeyPoints instance from a YOLO NAS results. + + Args: + yolo_nas_results (ImagePoseEstimationPrediction): + The output object from YOLO NAS. + + Returns: + KeyPoints: A new KeyPoints object. + + Example: + ```python + import cv2 + import torch + import supervision as sv + import super_gradients + + image = cv2.imread() + + device = "cuda" if torch.cuda.is_available() else "cpu" + yolo_nas = super_gradients.training.models.get( + "yolo_nas_pose_s", pretrained_weights="coco_pose").to(device) + + results = yolo_nas.predict(image, conf=0.1) + keypoints = sv.KeyPoints.from_yolo_nas(results) + ``` + """ + if len(yolo_nas_results.prediction.poses) == 0: + return cls.empty() + + xy = yolo_nas_results.prediction.poses[:, :, :2] + confidence = yolo_nas_results.prediction.poses[:, :, 2] + + # yolo_nas_results treats params differently. + # prediction.labels may not exist, whereas class_names might be None + if hasattr(yolo_nas_results.prediction, "labels"): + class_id = yolo_nas_results.prediction.labels # np.array[int] + else: + class_id = None + + data = {} + if class_id is not None and yolo_nas_results.class_names is not None: + class_names = [] + for c_id in class_id: + name = yolo_nas_results.class_names[c_id] # tuple[str] + class_names.append(name) + data[CLASS_NAME_DATA_FIELD] = class_names + + return cls( + xy=xy, + confidence=confidence, + class_id=class_id, + data=data, + ) + + def __getitem__( + self, index: Union[int, slice, List[int], np.ndarray, str] + ) -> Union[KeyPoints, List, np.ndarray, None]: + """ + Get a subset of the KeyPoints object or access an item from its data field. + + When provided with an integer, slice, list of integers, or a numpy array, this + method returns a new KeyPoints object that represents a subset of the original + keypoints. When provided with a string, it accesses the corresponding item in + the data dictionary. + + Args: + index (Union[int, slice, List[int], np.ndarray, str]): The index, indices, + or key to access a subset of the KeyPoints or an item from the data. + + Returns: + Union[KeyPoints, Any]: A subset of the KeyPoints object or an item from + the data field. + + Example: + ```python + import supervision as sv + + keypoints = sv.KeyPoints() + + first_detection = keypoints[0] + first_10_keypoints = keypoints[0:10] + some_keypoints = keypoints[[0, 2, 4]] + class_0_keypoints = keypoints[keypoints.class_id == 0] + high_confidence_keypoints = keypoints[keypoints.confidence > 0.5] + + feature_vector = keypoints['feature_vector'] + ``` + """ + if isinstance(index, str): + return self.data.get(index) + if isinstance(index, int): + index = [index] + return KeyPoints( + xy=self.xy[index], + confidence=self.confidence[index] if self.confidence is not None else None, + class_id=self.class_id[index] if self.class_id is not None else None, + data=get_data_item(self.data, index), + ) + + def __setitem__(self, key: str, value: Union[np.ndarray, List]): + """ + Set a value in the data dictionary of the KeyPoints object. + + Args: + key (str): The key in the data dictionary to set. + value (Union[np.ndarray, List]): The value to set for the key. + + Example: + ```python + import cv2 + import supervision as sv + from ultralytics import YOLO + + image = cv2.imread() + model = YOLO('yolov8s.pt') + + result = model(image)[0] + keypoints = sv.KeyPoints.from_ultralytics(result) + + keypoints['names'] = [ + model.model.names[class_id] + for class_id + in keypoints.class_id + ] + ``` + """ + if not isinstance(value, (np.ndarray, list)): + raise TypeError("Value must be a np.ndarray or a list") + + if isinstance(value, list): + value = np.array(value) + + self.data[key] = value + + @classmethod + def empty(cls) -> KeyPoints: + """ + Create an empty Keypoints object with no keypoints. + + Returns: + (KeyPoints): An empty Keypoints object. + + Example: + ```python + from supervision import Keypoints + empty_keypoints = Keypoints.empty() + ``` + """ + return cls(xy=np.empty((0, 0, 2), dtype=np.float32)) diff --git a/supervision/keypoint/skeletons.py b/supervision/keypoint/skeletons.py new file mode 100644 index 00000000..6c110854 --- /dev/null +++ b/supervision/keypoint/skeletons.py @@ -0,0 +1,36 @@ +from enum import Enum +from typing import Dict, List, Tuple + +Edges = List[Tuple[int, int]] + + +class Skeleton(Enum): + COCO = [ + (1, 2), + (1, 3), + (2, 3), + (2, 4), + (3, 5), + (6, 12), + (6, 7), + (6, 8), + (7, 13), + (7, 9), + (8, 10), + (9, 11), + (12, 13), + (14, 12), + (15, 13), + (16, 14), + (17, 15), + ] + + +SKELETONS_BY_EDGE_COUNT: Dict[int, Edges] = {} +SKELETONS_BY_VERTEX_COUNT: Dict[int, Edges] = {} + +for skeleton in Skeleton: + SKELETONS_BY_EDGE_COUNT[len(skeleton.value)] = skeleton.value + + unique_vertices = set(vertex for edge in skeleton.value for vertex in edge) + SKELETONS_BY_VERTEX_COUNT[len(unique_vertices)] = skeleton.value diff --git a/supervision/tracker/byte_tracker/core.py b/supervision/tracker/byte_tracker/core.py index c77878cf..55db6293 100644 --- a/supervision/tracker/byte_tracker/core.py +++ b/supervision/tracker/byte_tracker/core.py @@ -12,8 +12,9 @@ from supervision.utils.internal import deprecated_parameter class STrack(BaseTrack): shared_kalman = KalmanFilter() + _external_count = 0 - def __init__(self, tlwh, score, class_ids): + def __init__(self, tlwh, score, class_ids, minimum_consecutive_frames): # wait activate self._tlwh = np.asarray(tlwh, dtype=np.float32) self.kalman_filter = None @@ -24,6 +25,10 @@ class STrack(BaseTrack): self.class_ids = class_ids self.tracklet_len = 0 + self.external_track_id = -1 + + self.minimum_consecutive_frames = minimum_consecutive_frames + def predict(self): mean_state = self.mean.copy() if self.state != TrackState.Tracked: @@ -53,7 +58,7 @@ class STrack(BaseTrack): def activate(self, kalman_filter, frame_id): """Start a new tracklet""" self.kalman_filter = kalman_filter - self.track_id = self.next_id() + self.internal_track_id = self.next_id() self.mean, self.covariance = self.kalman_filter.initiate( self.tlwh_to_xyah(self._tlwh) ) @@ -62,6 +67,10 @@ class STrack(BaseTrack): self.state = TrackState.Tracked if frame_id == 1: self.is_activated = True + + if self.minimum_consecutive_frames == 1: + self.external_track_id = self.next_external_id() + self.frame_id = frame_id self.start_frame = frame_id @@ -71,10 +80,10 @@ class STrack(BaseTrack): ) self.tracklet_len = 0 self.state = TrackState.Tracked - self.is_activated = True + self.frame_id = frame_id if new_id: - self.track_id = self.next_id() + self.internal_track_id = self.next_id() self.score = new_track.score def update(self, new_track, frame_id): @@ -93,7 +102,10 @@ class STrack(BaseTrack): self.mean, self.covariance, self.tlwh_to_xyah(new_tlwh) ) self.state = TrackState.Tracked - self.is_activated = True + if self.tracklet_len == self.minimum_consecutive_frames: + self.is_activated = True + if self.external_track_id == -1: + self.external_track_id = self.next_external_id() self.score = new_track.score @@ -131,6 +143,15 @@ class STrack(BaseTrack): def to_xyah(self): return self.tlwh_to_xyah(self.tlwh) + @staticmethod + def next_external_id(): + STrack._external_count += 1 + return STrack._external_count + + @staticmethod + def reset_external_counter(): + STrack._external_count = 0 + @staticmethod def tlbr_to_tlwh(tlbr): ret = np.asarray(tlbr).copy() @@ -144,7 +165,9 @@ class STrack(BaseTrack): return ret def __repr__(self): - return "OT_{}_({}-{})".format(self.track_id, self.start_frame, self.end_frame) + return "OT_{}_({}-{})".format( + self.internal_track_id, self.start_frame, self.end_frame + ) def detections2boxes(detections: Detections) -> np.ndarray: @@ -186,6 +209,10 @@ class ByteTrack: Increasing minimum_matching_threshold improves accuracy but risks fragmentation. Decreasing it improves completeness but risks false positives and drift. frame_rate (int, optional): The frame rate of the video. + minimum_consecutive_frames (int, optional): Number of consecutive frames that an object must + be tracked before it is considered a 'valid' track. + Increasing minimum_consecutive_frames prevents the creation of accidental tracks from + false detection or double detection, but risks missing shorter tracks. """ # noqa: E501 // docs @deprecated_parameter( @@ -218,6 +245,7 @@ class ByteTrack: lost_track_buffer: int = 30, minimum_matching_threshold: float = 0.8, frame_rate: int = 30, + minimum_consecutive_frames: int = 1, ): self.track_activation_threshold = track_activation_threshold self.minimum_matching_threshold = minimum_matching_threshold @@ -225,6 +253,7 @@ class ByteTrack: self.frame_id = 0 self.det_thresh = self.track_activation_threshold + 0.1 self.max_time_lost = int(frame_rate / 30.0 * lost_track_buffer) + self.minimum_consecutive_frames = minimum_consecutive_frames self.kalman_filter = KalmanFilter() self.tracked_tracks: List[STrack] = [] @@ -285,11 +314,14 @@ class ByteTrack: matches, _, _ = matching.linear_assignment(iou_costs, 0.5) detections.tracker_id = np.full(len(detections), -1, dtype=int) for i_detection, i_track in matches: - detections.tracker_id[i_detection] = int(tracks[i_track].track_id) + detections.tracker_id[i_detection] = int( + tracks[i_track].external_track_id + ) return detections[detections.tracker_id != -1] else: + detections = Detections.empty() detections.tracker_id = np.array([], dtype=int) return detections @@ -308,6 +340,7 @@ class ByteTrack: self.lost_tracks: List[STrack] = [] self.removed_tracks: List[STrack] = [] BaseTrack.reset_counter() + STrack.reset_external_counter() def update_with_tensors(self, tensors: np.ndarray) -> List[STrack]: """ @@ -345,7 +378,7 @@ class ByteTrack: if len(dets) > 0: """Detections""" detections = [ - STrack(STrack.tlbr_to_tlwh(tlbr), s, c) + STrack(STrack.tlbr_to_tlwh(tlbr), s, c, self.minimum_consecutive_frames) for (tlbr, s, c) in zip(dets, scores_keep, class_ids_keep) ] else: @@ -387,7 +420,7 @@ class ByteTrack: if len(dets_second) > 0: """Detections""" detections_second = [ - STrack(STrack.tlbr_to_tlwh(tlbr), s, c) + STrack(STrack.tlbr_to_tlwh(tlbr), s, c, self.minimum_consecutive_frames) for (tlbr, s, c) in zip(dets_second, scores_second, class_ids_second) ] else: @@ -468,22 +501,22 @@ def joint_tracks( ) -> List[STrack]: """ Joins two lists of tracks, ensuring that the resulting list does not - contain tracks with duplicate track_id values. + contain tracks with duplicate internal_track_id values. Parameters: - track_list_a: First list of tracks (with track_id attribute). - track_list_b: Second list of tracks (with track_id attribute). + track_list_a: First list of tracks (with internal_track_id attribute). + track_list_b: Second list of tracks (with internal_track_id attribute). Returns: Combined list of tracks from track_list_a and track_list_b - without duplicate track_id values. + without duplicate internal_track_id values. """ seen_track_ids = set() result = [] for track in track_list_a + track_list_b: - if track.track_id not in seen_track_ids: - seen_track_ids.add(track.track_id) + if track.internal_track_id not in seen_track_ids: + seen_track_ids.add(track.internal_track_id) result.append(track) return result @@ -492,17 +525,17 @@ def joint_tracks( def sub_tracks(track_list_a: List, track_list_b: List) -> List[int]: """ Returns a list of tracks from track_list_a after removing any tracks - that share the same track_id with tracks in track_list_b. + that share the same internal_track_id with tracks in track_list_b. Parameters: - track_list_a: List of tracks (with track_id attribute). - track_list_b: List of tracks (with track_id attribute) to + track_list_a: List of tracks (with internal_track_id attribute). + track_list_b: List of tracks (with internal_track_id attribute) to be subtracted from track_list_a. Returns: List of remaining tracks from track_list_a after subtraction. """ - tracks = {track.track_id: track for track in track_list_a} - track_ids_b = {track.track_id for track in track_list_b} + tracks = {track.internal_track_id: track for track in track_list_a} + track_ids_b = {track.internal_track_id for track in track_list_b} for track_id in track_ids_b: tracks.pop(track_id, None) diff --git a/supervision/utils/conversion.py b/supervision/utils/conversion.py index 608104bc..8ddce969 100644 --- a/supervision/utils/conversion.py +++ b/supervision/utils/conversion.py @@ -81,7 +81,7 @@ def pillow_to_cv2(image: Image.Image) -> np.ndarray: image (Image.Image): Pillow image (in RGB format). Returns: - np.ndarray: Input image converted to OpenCV format. + (np.ndarray): Input image converted to OpenCV format. """ scene = np.array(image) scene = cv2.cvtColor(scene, cv2.COLOR_RGB2BGR) @@ -97,7 +97,7 @@ def cv2_to_pillow(image: np.ndarray) -> Image.Image: image (np.ndarray): OpenCV image (in BGR format). Returns: - Image.Image: Input image converted to Pillow format. + (Image.Image): Input image converted to Pillow format. """ image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) return Image.fromarray(image) diff --git a/supervision/utils/image.py b/supervision/utils/image.py index 4e0ba5d7..9f2e1783 100644 --- a/supervision/utils/image.py +++ b/supervision/utils/image.py @@ -7,9 +7,10 @@ from typing import Callable, List, Literal, Optional, Tuple, Union import cv2 import numpy as np +import numpy.typing as npt from supervision.annotators.base import ImageType -from supervision.draw.color import Color +from supervision.draw.color import Color, unify_to_bgr from supervision.draw.utils import calculate_optimal_text_scale, draw_text from supervision.geometry.core import Point from supervision.utils.conversion import ( @@ -25,103 +26,326 @@ MAX_COLUMNS_FOR_SINGLE_ROW_GRID = 3 @convert_for_image_processing -def crop_image(image: np.ndarray, xyxy: np.ndarray) -> np.ndarray: +def crop_image( + image: ImageType, + xyxy: Union[npt.NDArray[int], List[int], Tuple[int, int, int, int]], +) -> ImageType: """ 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). + image (ImageType): The image to be cropped. `ImageType` is a flexible type, + accepting either `numpy.ndarray` or `PIL.Image.Image`. + xyxy (Union[np.ndarray, List[int], Tuple[int, int, int, int]]): A bounding box + coordinates in the format `(x_min, y_min, x_max, y_max)`, accepted as either + a `numpy.ndarray`, a `list`, or a `tuple`. Returns: - (np.ndarray): The cropped image as a numpy array. + (ImageType): The cropped image. The type is determined by the input type and + may be either a `numpy.ndarray` or `PIL.Image.Image`. + + === "OpenCV" - Examples: ```python + import cv2 import supervision as sv - 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=image, xyxy=xyxy) - sink.save_image(image=cropped_image) - ``` - """ + image = cv2.imread() + image.shape + # (1080, 1920, 3) + xyxy = [200, 400, 600, 800] + cropped_image = sv.crop_image(image=image, xyxy=xyxy) + cropped_image.shape + # (400, 400, 3) + ``` + + === "Pillow" + + ```python + from PIL import Image + import supervision as sv + + image = Image.open() + image.size + # (1920, 1080) + + xyxy = [200, 400, 600, 800] + cropped_image = sv.crop_image(image=image, xyxy=xyxy) + cropped_image.size + # (400, 400) + ``` + + ![crop_image](https://media.roboflow.com/supervision-docs/crop-image.png){ align=center width="800" } + """ # noqa E501 // docs + + if isinstance(xyxy, (list, tuple)): + xyxy = np.array(xyxy) xyxy = np.round(xyxy).astype(int) - x1, y1, x2, y2 = xyxy - return image[y1:y2, x1:x2] + x_min, y_min, x_max, y_max = xyxy.flatten() + return image[y_min:y_max, x_min:x_max] @convert_for_image_processing -def resize_image(image: np.ndarray, scale_factor: float) -> np.ndarray: +def scale_image(image: ImageType, scale_factor: float) -> ImageType: """ - Resizes an image by a given scale factor using cv2.INTER_LINEAR interpolation. + Scales the given image based on the given scale factor. Args: - image (np.ndarray): The input image to be resized. + image (ImageType): The image to be scaled. `ImageType` is a flexible type, + accepting either `numpy.ndarray` or `PIL.Image.Image`. scale_factor (float): The factor by which the image will be scaled. Scale - factor > 1.0 zooms in, < 1.0 zooms out. + factor > `1.0` zooms in, < `1.0` zooms out. Returns: - np.ndarray: The resized image. + (ImageType): The scaled image. The type is determined by the input type and + may be either a `numpy.ndarray` or `PIL.Image.Image`. Raises: ValueError: If the scale factor is non-positive. + + === "OpenCV" + + ```python + import cv2 + import supervision as sv + + image = cv2.imread() + image.shape + # (1080, 1920, 3) + + scaled_image = sv.scale_image(image=image, scale_factor=0.5) + scaled_image.shape + # (540, 960, 3) + ``` + + === "Pillow" + + ```python + from PIL import Image + import supervision as sv + + image = Image.open() + image.size + # (1920, 1080) + + scaled_image = sv.scale_image(image=image, scale_factor=0.5) + scaled_image.size + # (960, 540) + ``` """ if scale_factor <= 0: raise ValueError("Scale factor must be positive.") - old_width, old_height = image.shape[1], image.shape[0] - nwe_width = int(old_width * scale_factor) - new_height = int(old_height * scale_factor) - - return cv2.resize(image, (nwe_width, new_height), interpolation=cv2.INTER_LINEAR) + width_old, height_old = image.shape[1], image.shape[0] + width_new = int(width_old * scale_factor) + height_new = int(height_old * scale_factor) + return cv2.resize(image, (width_new, height_new), interpolation=cv2.INTER_LINEAR) -def place_image( - scene: np.ndarray, image: np.ndarray, anchor: Tuple[int, int] -) -> np.ndarray: +@convert_for_image_processing +def resize_image( + image: ImageType, + resolution_wh: Tuple[int, int], + keep_aspect_ratio: bool = False, +) -> ImageType: + """ + Resizes the given image to a specified resolution. Can maintain the original aspect + ratio or resize directly to the desired dimensions. + + Args: + image (ImageType): The image to be resized. `ImageType` is a flexible type, + accepting either `numpy.ndarray` or `PIL.Image.Image`. + resolution_wh (Tuple[int, int]): The target resolution as + `(width, height)`. + keep_aspect_ratio (bool, optional): Flag to maintain the image's original + aspect ratio. Defaults to `False`. + + Returns: + (ImageType): The resized image. The type is determined by the input type and + may be either a `numpy.ndarray` or `PIL.Image.Image`. + + === "OpenCV" + + ```python + import cv2 + import supervision as sv + + image = cv2.imread() + image.shape + # (1080, 1920, 3) + + resized_image = sv.resize_image( + image=image, resolution_wh=(1000, 1000), keep_aspect_ratio=True + ) + resized_image.shape + # (562, 1000, 3) + ``` + + === "Pillow" + + ```python + from PIL import Image + import supervision as sv + + image = Image.open() + image.size + # (1920, 1080) + + resized_image = sv.resize_image( + image=image, resolution_wh=(1000, 1000), keep_aspect_ratio=True + ) + resized_image.size + # (1000, 562) + ``` + + ![resize_image](https://media.roboflow.com/supervision-docs/resize-image.png){ align=center width="800" } + """ # noqa E501 // docs + if keep_aspect_ratio: + image_ratio = image.shape[1] / image.shape[0] + target_ratio = resolution_wh[0] / resolution_wh[1] + if image_ratio >= target_ratio: + width_new = resolution_wh[0] + height_new = int(resolution_wh[0] / image_ratio) + else: + height_new = resolution_wh[1] + width_new = int(resolution_wh[1] * image_ratio) + else: + width_new, height_new = resolution_wh + + return cv2.resize(image, (width_new, height_new), interpolation=cv2.INTER_LINEAR) + + +@convert_for_image_processing +def letterbox_image( + image: ImageType, + resolution_wh: Tuple[int, int], + color: Union[Tuple[int, int, int], Color] = Color.BLACK, +) -> ImageType: + """ + Resizes and pads an image to a specified resolution with a given color, maintaining + the original aspect ratio. + + Args: + image (ImageType): The image to be resized. `ImageType` is a flexible type, + accepting either `numpy.ndarray` or `PIL.Image.Image`. + resolution_wh (Tuple[int, int]): The target resolution as + `(width, height)`. + color (Union[Tuple[int, int, int], Color]): The color to pad with. If tuple + provided it should be in BGR format. + + Returns: + (ImageType): The resized image. The type is determined by the input type and + may be either a `numpy.ndarray` or `PIL.Image.Image`. + + === "OpenCV" + + ```python + import cv2 + import supervision as sv + + image = cv2.imread() + image.shape + # (1080, 1920, 3) + + letterboxed_image = sv.letterbox_image(image=image, resolution_wh=(1000, 1000)) + letterboxed_image.shape + # (1000, 1000, 3) + ``` + + === "Pillow" + + ```python + from PIL import Image + import supervision as sv + + image = Image.open() + image.size + # (1920, 1080) + + letterboxed_image = sv.letterbox_image(image=image, resolution_wh=(1000, 1000)) + letterboxed_image.size + # (1000, 1000) + ``` + + ![letterbox_image](https://media.roboflow.com/supervision-docs/letterbox-image.png){ align=center width="800" } + """ # noqa E501 // docs + color = unify_to_bgr(color=color) + resized_image = resize_image( + image=image, resolution_wh=resolution_wh, keep_aspect_ratio=True + ) + height_new, width_new = resized_image.shape[:2] + padding_top = (resolution_wh[1] - height_new) // 2 + padding_bottom = resolution_wh[1] - height_new - padding_top + padding_left = (resolution_wh[0] - width_new) // 2 + padding_right = resolution_wh[0] - width_new - padding_left + return cv2.copyMakeBorder( + resized_image, + padding_top, + padding_bottom, + padding_left, + padding_right, + cv2.BORDER_CONSTANT, + value=color, + ) + + +def overlay_image( + image: npt.NDArray[np.uint8], + overlay: npt.NDArray[np.uint8], + anchor: Tuple[int, int], +) -> npt.NDArray[np.uint8]: """ Places an image onto a scene at a given anchor point, handling cases where the image's position is partially or completely outside the scene's bounds. Args: - scene (np.ndarray): The background scene onto which the image is placed. - image (np.ndarray): The image to be placed onto the scene. - anchor (Tuple[int, int]): The (x, y) coordinates in the scene where the + image (np.ndarray): The background scene onto which the image is placed. + overlay (np.ndarray): The image to be placed onto the scene. + anchor (Tuple[int, int]): The `(x, y)` coordinates in the scene where the top-left corner of the image will be placed. Returns: - np.ndarray: The modified scene with the image placed at the anchor point, - or unchanged if the image placement is completely outside the scene. - """ - scene_height, scene_width = scene.shape[:2] - image_height, image_width = image.shape[:2] + (np.ndarray): The result image with overlay. + + Examples: + ```python + import cv2 + import numpy as np + import supervision as sv + + image = cv2.imread() + overlay = np.zeros((400, 400, 3), dtype=np.uint8) + result_image = sv.overlay_image(image=image, overlay=overlay, anchor=(200, 400)) + ``` + + ![overlay_image](https://media.roboflow.com/supervision-docs/overlay-image.png){ align=center width="800" } + """ # noqa E501 // docs + scene_height, scene_width = image.shape[:2] + image_height, image_width = overlay.shape[:2] anchor_x, anchor_y = anchor is_out_horizontally = anchor_x + image_width <= 0 or anchor_x >= scene_width is_out_vertically = anchor_y + image_height <= 0 or anchor_y >= scene_height if is_out_horizontally or is_out_vertically: - return scene + return image - start_y = max(anchor_y, 0) - start_x = max(anchor_x, 0) - end_y = min(scene_height, anchor_y + image_height) - end_x = min(scene_width, anchor_x + image_width) + x_min = max(anchor_x, 0) + y_min = max(anchor_y, 0) + x_max = min(scene_width, anchor_x + image_width) + y_max = min(scene_height, anchor_y + image_height) - crop_start_y = max(-anchor_y, 0) - crop_start_x = max(-anchor_x, 0) - crop_end_y = image_height - max((anchor_y + image_height) - scene_height, 0) - crop_end_x = image_width - max((anchor_x + image_width) - scene_width, 0) + crop_x_min = max(-anchor_x, 0) + crop_y_min = max(-anchor_y, 0) + crop_x_max = image_width - max((anchor_x + image_width) - scene_width, 0) + crop_y_max = image_height - max((anchor_y + image_height) - scene_height, 0) - scene[start_y:end_y, start_x:end_x] = image[ - crop_start_y:crop_end_y, crop_start_x:crop_end_x + image[y_min:y_max, x_min:x_max] = overlay[ + crop_y_min:crop_y_max, crop_x_min:crop_x_max ] - return scene + return image class ImageSink: @@ -145,13 +369,13 @@ class ImageSink: ```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): + frames_generator = sv.get_video_frames_generator(, stride=2) + + with sv.ImageSink(target_dir_path=) as sink: + for image in frames_generator: sink.save_image(image=image) ``` - """ + """ # noqa E501 // docs self.target_dir_path = target_dir_path self.overwrite = overwrite @@ -285,14 +509,14 @@ def create_tiles( raise ValueError("Could not create image tiles from empty list of images.") if return_type == "auto": return_type = _negotiate_tiles_format(images=images) - tile_padding_color = _color_to_bgr(color=tile_padding_color) - tile_margin_color = _color_to_bgr(color=tile_margin_color) + tile_padding_color = unify_to_bgr(color=tile_padding_color) + tile_margin_color = unify_to_bgr(color=tile_margin_color) images = images_to_cv2(images=images) if single_tile_size is None: single_tile_size = _aggregate_images_shape(images=images, mode=tile_scaling) resized_images = [ letterbox_image( - image=i, desired_size=single_tile_size, color=tile_padding_color + image=i, resolution_wh=single_tile_size, color=tile_padding_color ) for i in images ] @@ -311,8 +535,8 @@ def create_tiles( titles_anchors = fill( sequence=titles_anchors, desired_size=len(images), content=None ) - titles_color = _color_to_bgr(color=titles_color) - titles_background_color = _color_to_bgr(color=titles_background_color) + titles_color = unify_to_bgr(color=titles_color) + titles_background_color = unify_to_bgr(color=titles_background_color) tiles = _generate_tiles( images=resized_images, grid_size=grid_size, @@ -542,92 +766,3 @@ def _generate_color_image( shape: Tuple[int, int], color: Tuple[int, int, int] ) -> np.ndarray: return np.ones(shape[::-1] + (3,), dtype=np.uint8) * color - - -@convert_for_image_processing -def letterbox_image( - image: np.ndarray, - desired_size: Tuple[int, int], - color: Union[Tuple[int, int, int], Color] = (0, 0, 0), -) -> np.ndarray: - """ - Resize and pad image to fit the desired size, preserving its aspect - ratio, adding padding of given color if needed to maintain aspect ratio. - - Args: - image (np.ndarray): Input image (type will be adjusted by decorator, - you can provide PIL.Image) - desired_size (Tuple[int, int]): image size (width, height) representing - the target dimensions. - color (Union[Tuple[int, int, int], Color]): the color to pad with - If - tuple provided - should be BGR. - - Returns: - np.ndarray: letterboxed image (type may be adjusted to PIL.Image by - decorator if function was called with PIL.Image) - """ - color = _color_to_bgr(color=color) - resized_img = resize_image_keeping_aspect_ratio( - image=image, - desired_size=desired_size, - ) - new_height, new_width = resized_img.shape[:2] - top_padding = (desired_size[1] - new_height) // 2 - bottom_padding = desired_size[1] - new_height - top_padding - left_padding = (desired_size[0] - new_width) // 2 - right_padding = desired_size[0] - new_width - left_padding - return cv2.copyMakeBorder( - resized_img, - top_padding, - bottom_padding, - left_padding, - right_padding, - cv2.BORDER_CONSTANT, - value=color, - ) - - -@convert_for_image_processing -def resize_image_keeping_aspect_ratio( - image: np.ndarray, - desired_size: Tuple[int, int], -) -> np.ndarray: - """ - Resize and pad image preserving its aspect ratio. - - For example: input image is (640, 480) and we want to resize into - (1024, 1024). If this rectangular image is just resized naively - to square-shape output - aspect ratio would be altered. If we do not - want this to happen - we may resize bigger dimension (640) to 1024. - Ratio of change is 1.6. This ratio is later on used to calculate scaling - in the other dimension. As a result we have (1024, 768) image. - - Parameters: - - image (np.ndarray): Input image (type will be adjusted by decorator, - you can provide PIL.Image) - - desired_size (Tuple[int, int]): image size (width, height) representing the - target dimensions. Parameter will be used to dictate maximum size of - output image. Output size may be smaller - to preserve aspect ratio of original - image. - - Returns: - np.ndarray: resized image (type may be adjusted to PIL.Image by decorator - if function was called with PIL.Image) - """ - if image.shape[:2] == desired_size[::-1]: - return image - img_ratio = image.shape[1] / image.shape[0] - desired_ratio = desired_size[0] / desired_size[1] - if img_ratio >= desired_ratio: - new_width = desired_size[0] - new_height = int(desired_size[0] / img_ratio) - else: - new_height = desired_size[1] - new_width = int(desired_size[1] * img_ratio) - return cv2.resize(image, (new_width, new_height)) - - -def _color_to_bgr(color: Union[Tuple[int, int, int], Color]) -> Tuple[int, int, int]: - if issubclass(type(color), Color): - return color.as_bgr() - return color diff --git a/supervision/utils/iterables.py b/supervision/utils/iterables.py index ad570379..52bfbeb6 100644 --- a/supervision/utils/iterables.py +++ b/supervision/utils/iterables.py @@ -16,7 +16,7 @@ def create_batches( batch_size (int): The expected size of a batch. Returns: - Generator[List[V], None, None]: A generator that yields chunks + (Generator[List[V], None, None]): A generator that yields chunks of `sequence` of size `batch_size`, up to the length of the input `sequence`. @@ -54,7 +54,7 @@ def fill(sequence: List[V], desired_size: int, content: V) -> List[V]: `sequence` as padding. Returns: - List[V]: A padded version of the input `sequence` (if needed). + (List[V]): A padded version of the input `sequence` (if needed). Examples: ```python diff --git a/supervision/validators/__init__.py b/supervision/validators/__init__.py new file mode 100644 index 00000000..9a9fca8c --- /dev/null +++ b/supervision/validators/__init__.py @@ -0,0 +1,141 @@ +from typing import Any, Dict + +import numpy as np + + +def validate_xyxy(xyxy: Any) -> None: + expected_shape = "(_, 4)" + actual_shape = str(getattr(xyxy, "shape", None)) + is_valid = isinstance(xyxy, np.ndarray) and xyxy.ndim == 2 and xyxy.shape[1] == 4 + if not is_valid: + raise ValueError( + f"xyxy must be a 2D np.ndarray with shape {expected_shape}, but got shape " + f"{actual_shape}" + ) + + +def validate_mask(mask: Any, n: int) -> None: + expected_shape = f"({n}, H, W)" + actual_shape = str(getattr(mask, "shape", None)) + is_valid = mask is None or ( + isinstance(mask, np.ndarray) and len(mask.shape) == 3 and mask.shape[0] == n + ) + if not is_valid: + raise ValueError( + f"mask must be a 3D np.ndarray with shape {expected_shape}, but got shape " + f"{actual_shape}" + ) + + +def validate_class_id(class_id: Any, n: int) -> None: + expected_shape = f"({n},)" + actual_shape = str(getattr(class_id, "shape", None)) + is_valid = class_id is None or ( + isinstance(class_id, np.ndarray) and class_id.shape == (n,) + ) + if not is_valid: + raise ValueError( + f"class_id must be a 1D np.ndarray with shape {expected_shape}, but got " + f"shape {actual_shape}" + ) + + +def validate_confidence(confidence: Any, n: int) -> None: + expected_shape = f"({n},)" + actual_shape = str(getattr(confidence, "shape", None)) + is_valid = confidence is None or ( + isinstance(confidence, np.ndarray) and confidence.shape == (n,) + ) + if not is_valid: + raise ValueError( + f"confidence must be a 1D np.ndarray with shape {expected_shape}, but got " + f"shape {actual_shape}" + ) + + +def validate_keypoint_confidence(confidence: Any, n: int, m: int) -> None: + expected_shape = f"({n,m})" + actual_shape = str(getattr(confidence, "shape", None)) + + if confidence is not None: + is_valid = isinstance(confidence, np.ndarray) and confidence.shape == (n, m) + if not is_valid: + raise ValueError( + f"confidence must be a 1D np.ndarray with shape {expected_shape}, but " + "got" + f"shape {actual_shape}" + ) + + +def validate_tracker_id(tracker_id: Any, n: int) -> None: + expected_shape = f"({n},)" + actual_shape = str(getattr(tracker_id, "shape", None)) + is_valid = tracker_id is None or ( + isinstance(tracker_id, np.ndarray) and tracker_id.shape == (n,) + ) + if not is_valid: + raise ValueError( + f"tracker_id must be a 1D np.ndarray with shape {expected_shape}, but got " + f"shape {actual_shape}" + ) + + +def validate_data(data: Dict[str, Any], n: int) -> None: + for key, value in data.items(): + if isinstance(value, list): + if len(value) != n: + raise ValueError(f"Length of list for key '{key}' must be {n}") + elif isinstance(value, np.ndarray): + if value.ndim == 1 and value.shape[0] != n: + raise ValueError(f"Shape of np.ndarray for key '{key}' must be ({n},)") + elif value.ndim > 1 and value.shape[0] != n: + raise ValueError( + f"First dimension of np.ndarray for key '{key}' must have size {n}" + ) + else: + raise ValueError(f"Value for key '{key}' must be a list or np.ndarray") + + +def validate_xy(xy: Any, n: int, m: int) -> None: + expected_shape = f"({n, m},)" + actual_shape = str(getattr(xy, "shape", None)) + + is_valid = isinstance(xy, np.ndarray) and ( + xy.shape == (n, m, 2) or xy.shape == (n, m, 3) + ) + if not is_valid: + raise ValueError( + f"xy must be a 2D np.ndarray with shape {expected_shape}, but got shape " + f"{actual_shape}" + ) + + +def validate_detections_fields( + xyxy: Any, + mask: Any, + class_id: Any, + confidence: Any, + tracker_id: Any, + data: Dict[str, Any], +) -> None: + validate_xyxy(xyxy) + n = len(xyxy) + validate_mask(mask, n) + validate_class_id(class_id, n) + validate_confidence(confidence, n) + validate_tracker_id(tracker_id, n) + validate_data(data, n) + + +def validate_keypoints_fields( + xy: Any, + class_id: Any, + confidence: Any, + data: Dict[str, Any], +) -> None: + n = len(xy) + m = len(xy[0]) if len(xy) > 0 else 0 + validate_xy(xy, n, m) + validate_class_id(class_id, n) + validate_keypoint_confidence(confidence, n, m) + validate_data(data, n) diff --git a/test/test_utils.py b/test/test_utils.py index b8ef9231..b676cb54 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -3,6 +3,7 @@ from typing import Any, Dict, List, Optional import numpy as np from supervision.detection.core import Detections +from supervision.keypoint.core import KeyPoints def mock_detections( @@ -30,5 +31,24 @@ def mock_detections( ) +def mock_keypoints( + xy: List[List[float]], + confidence: Optional[List[float]] = None, + class_id: Optional[List[int]] = None, + data: Optional[Dict[str, List[Any]]] = None, +) -> KeyPoints: + def convert_data(data: Dict[str, List[Any]]): + return {k: np.array(v) for k, v in data.items()} + + return KeyPoints( + xy=np.array(xy, 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)), + data=convert_data(data) if data else {}, + ) + + def assert_almost_equal(actual, expected, tolerance=1e-5): assert abs(actual - expected) < tolerance, f"Expected {expected}, but got {actual}." diff --git a/test/utils/test_image.py b/test/utils/test_image.py index e50f2e57..487434ae 100644 --- a/test/utils/test_image.py +++ b/test/utils/test_image.py @@ -5,22 +5,19 @@ import pytest from PIL import Image, ImageChops from supervision import Color, Point -from supervision.utils.image import ( - create_tiles, - letterbox_image, - resize_image_keeping_aspect_ratio, -) +from supervision.utils.image import create_tiles, letterbox_image, resize_image -def test_resize_image_keeping_aspect_ratio_for_opencv_image() -> None: +def test_resize_image_for_opencv_image() -> None: # given image = np.zeros((480, 640, 3), dtype=np.uint8) expected_result = np.zeros((768, 1024, 3), dtype=np.uint8) # when - result = resize_image_keeping_aspect_ratio( + result = resize_image( image=image, - desired_size=(1024, 1024), + resolution_wh=(1024, 1024), + keep_aspect_ratio=True, ) # then @@ -29,15 +26,16 @@ def test_resize_image_keeping_aspect_ratio_for_opencv_image() -> None: ), "Expected output shape to be (w, h): (1024, 768)" -def test_resize_image_keeping_aspect_ratio_for_pillow_image() -> None: +def test_resize_image_for_pillow_image() -> None: # given image = Image.new(mode="RGB", size=(640, 480), color=(0, 0, 0)) expected_result = Image.new(mode="RGB", size=(1024, 768), color=(0, 0, 0)) # when - result = resize_image_keeping_aspect_ratio( + result = resize_image( image=image, - desired_size=(1024, 1024), + resolution_wh=(1024, 1024), + keep_aspect_ratio=True, ) # then @@ -62,7 +60,7 @@ def test_letterbox_image_for_opencv_image() -> None: # when result = letterbox_image( - image=image, desired_size=(1024, 1024), color=(255, 255, 255) + image=image, resolution_wh=(1024, 1024), color=(255, 255, 255) ) # then @@ -88,7 +86,7 @@ def test_letterbox_image_for_pillow_image() -> None: # when result = letterbox_image( - image=image, desired_size=(1024, 1024), color=(255, 255, 255) + image=image, resolution_wh=(1024, 1024), color=(255, 255, 255) ) # then