supervision - supervision-0.26.1

🔧 Fixed

• Fixed error in sv.MeanAveragePrecision where the area used for size-specific evaluation (small / medium / large) was always zero unless explicitly provided in sv.Detections.data. (https://github.com/roboflow/supervision/pull/1894)
• Fixed ID=0 bug in sv.MeanAveragePrecision where objects were getting 0.0 mAP despite perfect IoU matches due to a bug in annotation ID assignment. (https://github.com/roboflow/supervision/pull/1895)
• Fixed issue where sv.MeanAveragePrecision could return negative values when certain object size categories have no data. (https://github.com/roboflow/supervision/pull/1898)
• Fixed match_metric support for sv.Detections.with_nms. (https://github.com/roboflow/supervision/pull/1901)
• Fixed border_thickness parameter usage for sv.PercentageBarAnnotator. (https://github.com/roboflow/supervision/pull/1906)

🏆 Contributors

@balthazur (Balthasar Huber), @onuralpszr (Onuralp SEZER), @rafaelpadilla (Rafael Padilla), @soumik12345 (Soumik Rakshit), @SkalskiP (Piotr Skalski)

- Python
Published by soumik12345 7 months ago

supervision - supervision-0.26.0

[!WARNING]
supervision-0.26.0 drops python3.8 support and upgrade all codes to python3.9 syntax style.

[!TIP] Our docs page now has a fresh look that is consistent with the documentations of all Roboflow open-source projects. (#1858)

🚀 Added

• Added support for creating sv.KeyPoints objects from ViTPose and ViTPose++ inference results via sv.KeyPoints.from_transformers. (#1788)

  https://github.com/user-attachments/assets/f1917032-29d8-4b88-b871-65c2e28a756e

• Added support for the IOS (Intersection over Smallest) overlap metric that measures how much of the smaller object is covered by the larger one in sv.Detections.with_nms, sv.Detections.with_nmm, sv.box_iou_batch, and sv.mask_iou_batch. (#1774)

  ```python import numpy as np import supervision as sv

  boxestrue = np.array([ [100, 100, 200, 200], [300, 300, 400, 400] ]) boxesdetection = np.array([ [150, 150, 250, 250], [320, 320, 420, 420] ])

  sv.boxioubatch( boxestrue=boxestrue, boxesdetection=boxesdetection, overlap_metric=sv.OverlapMetric.IOU )

  array([[0.14285714, 0. ],

  [0. , 0.47058824]])

  sv.boxioubatch( boxestrue=boxestrue, boxesdetection=boxesdetection, overlap_metric=sv.OverlapMetric.IOS )

  array([[0.25, 0. ],

  [0. , 0.64]])

  ```

• Added sv.box_iou that efficiently computes the Intersection over Union (IoU) between two individual bounding boxes. (#1874)

• Added support for frame limitations and progress bar in sv.process_video. (#1816)

• Added sv.xyxy_to_xcycarh function to convert bounding box coordinates from (x_min, y_min, x_max, y_max) into measurement space to format (center x, center y, aspect ratio, height), where the aspect ratio is width / height. (#1823)

• Added sv.xyxy_to_xywh function to convert bounding box coordinates from (x_min, y_min, x_max, y_max) format to (x, y, width, height) format. (#1788)

🌱 Changed

• sv.LabelAnnotator now supports the smart_position parameter to automatically keep labels within frame boundaries, and the max_line_length parameter to control text wrapping for long or multi-line labels. (#1820)

  https://github.com/user-attachments/assets/361c17c7-0810-466d-907d-c752e91bc6f7

  

• sv.LabelAnnotator now supports non-string labels. (#1825)

• sv.Detections.from_vlm now supports parsing bounding boxes and segmentation masks from responses generated by Google Gemini models. You can test Gemini prompting, result parsing, and visualization with Supervision using this example notebook. (#1792)

```python import supervision as sv

gemini_response_text = """```json
    [
        {"box_2d": [543, 40, 728, 200], "label": "cat", "id": 1},
        {"box_2d": [653, 352, 820, 522], "label": "dog", "id": 2}
    ]
```"""

detections = sv.Detections.from_vlm(
    sv.VLM.GOOGLE_GEMINI_2_5,
    gemini_response_text,
    resolution_wh=(1000, 1000),
    classes=['cat', 'dog'],
)

detections.xyxy
# array([[543., 40., 728., 200.], [653., 352., 820., 522.]])

detections.data
# {'class_name': array(['cat', 'dog'], dtype='<U26')}

detections.class_id
# array([0, 1])
```

• sv.Detections.from_vlm now supports parsing bounding boxes from responses generated by Moondream. (#1878)

  ```python import supervision as sv

  moondreamresult = { 'objects': [ { 'xmin': 0.5704046934843063, 'ymin': 0.20069346576929092, 'xmax': 0.7049859315156937, 'ymax': 0.3012596592307091 }, { 'xmin': 0.6210969910025597, 'ymin': 0.3300672620534897, 'xmax': 0.8417936339974403, 'y_max': 0.4961046129465103 } ] }

  detections = sv.Detections.fromvlm( sv.VLM.MOONDREAM, moondreamresult, resolution_wh=(1000, 1000), )

  detections.xyxy

  array([[1752.28, 818.82, 2165.72, 1229.14],

  [1908.01, 1346.67, 2585.99, 2024.11]])

  ```

• sv.Detections.from_vlm now supports parsing bounding boxes from responses generated by Qwen-2.5 VL. You can test Qwen2.5-VL prompting, result parsing, and visualization with Supervision using this example notebook. (#1709)

  ```python import supervision as sv

  qwen25vlresult = """json [ {"bbox_2d": [139, 768, 315, 954], "label": "cat"}, {"bbox_2d": [366, 679, 536, 849], "label": "dog"} ] """

  detections = sv.Detections.fromvlm( sv.VLM.QWEN25VL, qwen25vlresult, inputwh=(1000, 1000), resolutionwh=(1000, 1000), classes=['cat', 'dog'], )

  detections.xyxy

  array([[139., 768., 315., 954.], [366., 679., 536., 849.]])

  detections.class_id

  array([0, 1])

  detections.data

  {'class_name': array(['cat', 'dog'], dtype='<U10')}

  detections.class_id

  array([0, 1])

  ```

• Significantly improved the speed of HSV color mapping in sv.HeatMapAnnotator, achieving approximately 28x faster performance on 1920x1080 frames. (#1786)

🔧 Fixed

• Supervision’s sv.MeanAveragePrecision is now fully aligned with pycocotools, the official COCO evaluation tool, ensuring accurate and standardized metrics. (#1834)

  ```python import supervision as sv from supervision.metrics import MeanAveragePrecision

  predictions = sv.Detections(...) targets = sv.Detections(...)

  mapmetric = MeanAveragePrecision() mapmetric.update(predictions, targets).compute()

  Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.464

  Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.637

  Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.203

  Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.284

  Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.497

  Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.629

  ```

[!TIP] The updated mAP implementation enabled us to build an updated version of the Computer Vision Model Leaderboard.

• Fix #1767: Fixed losing sv.Detections.data when detections filtering.

⚠️ Deprecated

• sv.LMM enum is deprecated and will be removed in supervision-0.31.0. Use sv.VLM instead.
• sv.Detections.from_lmm property is deprecated and will be removed in supervision-0.31.0. Use sv.Detections.from_vlm instead.

❌ Removed

• The sv.DetectionDataset.images property has been removed in supervision-0.26.0. Please loop over images with for path, image, annotation in dataset:, as that does not require loading all images into memory.
• Cconstructing sv.DetectionDataset with parameter images as Dict[str, np.ndarray] is deprecated and has been removed in supervision-0.26.0. Please pass a list of paths List[str] instead.
• The name sv.BoundingBoxAnnotator is deprecated and has been removed in supervision-0.26.0. It has been renamed to sv.BoxAnnotator.

🏆 Contributors

@onuralpszr (Onuralp SEZER), @SkalskiP (Piotr Skalski), @SunHao-AI (Hao Sun), @rafaelpadilla Rafael Padilla, @Ashp116 (Ashp116), @capjamesg (James Gallagher), @blakeburch (Blake Burch), @hidara2000 (hidara2000), @Armaggheddon (Alessandro Brunello), @soumik12345 (Soumik Rakshit).

- Python
Published by soumik12345 7 months ago

supervision - supervision-0.25.0

Supervision 0.25.0 is here! Featuring a more robust LineZone crossing counter, support for tracking KeyPoints, Python 3.13 compatibility, and 3 new metrics: Precision, Recall and Mean Average Recall. The update also includes smart label positioning, improved Oriented Bounding Box support, and refined error handling. Thank you to all contributors - especially those who answered the call of Hacktoberfest!

Changelog

🚀 Added

• Essential update to the LineZone: when computing line crossings, detections that jitter might be counted twice (or more!). This can now be solved with the minimum_crossing_threshold argument. If you set it to 2 or more, extra frames will be used to confirm the crossing, improving the accuracy significantly. (#1540)

https://github.com/user-attachments/assets/89ca2ee6-93c9-41e6-a432-e16c4c69c695

• It is now possible to track objects detected as KeyPoints. See the complete step-by-step guide in the Object Tracking Guide. (#1658)

```python import numpy as np import supervision as sv from ultralytics import YOLO

model = YOLO("yolov8m-pose.pt") tracker = sv.ByteTrack() trace_annotator = sv.TraceAnnotator()

def callback(frame: np.ndarray, : int) -> np.ndarray: results = model(frame)[0] keypoints = sv.KeyPoints.from_ultralytics(results)

detections = key_points.as_detections()
detections = tracker.update_with_detections(detections)

annotated_image = trace_annotator.annotate(frame.copy(), detections)
return annotated_image

sv.processvideo( sourcepath="inputvideo.mp4", targetpath="output_video.mp4", callback=callback ) ```

https://github.com/user-attachments/assets/4c3bdf54-391e-4633-9164-f15878ddfb33

<sup>See the guide for the full code used to make the video</sup>

• Added is_empty method to KeyPoints to check if there are any keypoints in the object. (#1658)

• Added as_detections method to KeyPoints that converts KeyPoints to Detections. (#1658)

• Added a new video to supervision[assets]. (#1657)

```python from supervision.assets import download_assets, VideoAssets

pathtovideo = download_assets(VideoAssets.SKIING) ```

• Supervision can now be used with Python 3.13. The most renowned update is the ability to run Python without Global Interpreter Lock (GIL). We expect support for this among our dependencies to be inconsistent, but if you do attempt it - let us know the results! (#1595)

• Added Mean Average Recall mAR metric, which returns a recall score, averaged over IoU thresholds, detected object classes, and limits imposed on maximum considered detections. (#1661)

```python import supervision as sv from supervision.metrics import MeanAverageRecall

predictions = sv.Detections(...) targets = sv.Detections(...)

mapmetric = MeanAverageRecall() mapresult = map_metric.update(predictions, targets).compute()

map_result.plot() ```

• Added Precision and Recall metrics, providing a baseline for comparing model outputs to ground truth or another model (#1609)

```python import supervision as sv from supervision.metrics import Recall

predictions = sv.Detections(...) targets = sv.Detections(...)

recallmetric = Recall() recallresult = recall_metric.update(predictions, targets).compute()

recall_result.plot() ```

• All Metrics now support Oriented Bounding Boxes (OBB) (#1593)

```python import supervision as sv from supervision.metrics import F1_Score

predictions = sv.Detections(...) targets = sv.Detections(...)

f1metric = MeanAverageRecall(metrictarget=sv.MetricTarget.ORIENTEDBOUNDINGBOXES) f1result = f1metric.update(predictions, targets).compute() ```

• Introducing Smart Labels! When smart_position is set for LabelAnnotator, RichLabelAnnotator or VertexLabelAnnotator, the labels will move around to avoid overlapping others. (#1625)

```python import supervision as sv from ultralytics import YOLO

image = cv2.imread("image.jpg")

labelannotator = sv.LabelAnnotator(smartposition=True)

model = YOLO("yolo11m.pt") results = model(image)[0] detections = sv.Detections.from_ultralytics(results)

annotatedframe = labelannotator.annotate(firstframe.copy(), detections) sv.plotimage(annotated_frame) ```

https://github.com/user-attachments/assets/ef768db4-867d-4305-b905-80e690bb1ea7

• Added the metadata variable to Detections. It allows you to store custom data per-image, rather than per-detected-object as was possible with data variable. For example, metadata could be used to store the source video path, camera model or camera parameters. (#1589)

```python import supervision as sv from ultralytics import YOLO

model = YOLO("yolov8m")

result = model("image.png")[0] detections = sv.Detections.from_ultralytics(result)

Items in data must match length of detections

objectids = [num for num in range(len(detections))] detections.data["objectnumber"] = object_ids

Items in metadata can be of any length.

detections.metadata["camera_model"] = "Luxonis OAK-D" ```

• Added a py.typed type hints metafile. It should provide a stronger signal to type annotators and IDEs that type support is available. (#1586)

🌱 Changed

• ByteTrack no longer requires detections to have a class_id (#1637)
• draw_line, draw_rectangle, draw_filled_rectangle, draw_polygon, draw_filled_polygon and PolygonZoneAnnotator now comes with a default color (#1591)
• Dataset classes are treated as case-sensitive when merging multiple datasets. (#1643)
• Expanded metrics documentation with example plots and printed results (#1660)
• Added usage example for polygon zone (#1608)
• Small improvements to error handling in polygons: (#1602)

🔧 Fixed

• Updated ByteTrack, removing shared variables. Previously, multiple instances of ByteTrack would share some date, requiring liberal use of tracker.reset(). (#1603), (#1528)
• Fixed a bug where class_agnostic setting in MeanAveragePrecision would not work. (#1577) hacktoberfest
• Removed welcome workflow from our CI system. (#1596)

✅ No removals or deprecations this time!

⚙️ Internal Changes

• Large refactor of ByteTrack (#1603)
  • STrack moved to separate class
  • Remove superfluous BaseTrack class
  • Removed unused variables
• Large refactor of RichLabelAnnotator, matching its contents with LabelAnnotator. (#1625)

🏆 Contributors

@onuralpszr (Onuralp SEZER), @kshitijaucharmal (KshitijAucharmal), @grzegorz-roboflow (Grzegorz Klimaszewski), @Kadermiyanyedi (Kader Miyanyedi), @PrakharJain1509 (Prakhar Jain), @DivyaVijay1234 (Divya Vijay), @souhhmm (Soham Kalburgi), @joaomarcoscrs (João Marcos Cardoso Ramos da Silva), @AHuzail (Ahmad Huzail Khan), @DemyCode (DemyCode), @ablazejuk (Andrey Blazejuk), @LinasKo (Linas Kondrackis)

A special thanks goes out to everyone who joined us for Hacktoberfest! We hope it was a rewarding experience and look forward to seeing you continue contributing and growing with our community. Keep building, keep innovating—your efforts make a difference! 🚀

- Python
Published by LinasKo over 1 year ago

supervision - supervision-0.24.0

Supervision 0.24.0 is here! We've added many new changes, including the F1 score, enhancements to LineZone, EasyOCR support, NCNN support, and the best Cookbook to date! You can also try out our annotators directly in the browser. Check out the release notes to find out more!

📢 Announcements

• Supervision is celebrating Hacktoberfest! Whether you're a newcomer to open source or a veteran contributor, we welcome you to join us in improving supervision. You can grab any issue without an assigned contributor: Hacktoberfest Issues Board. We'll be adding many more issues next week! 🎉

• We recently launched the Model Leaderboard. Come check how the latest models perform! It is also open-source, so you can contribute to it as well! 🚀

Changelog

🚀 Added

• Added F1 score as a new metric for detection and segmentation. The F1 score balances precision and recall, providing a single metric for model evaluation. #1521

```python import supervision as sv from supervision.metrics import F1Score

predictions = sv.Detections(...) targets = sv.Detections(...)

f1metric = F1Score() f1result = f1_metric.update(predictions, targets).compute()

print(f1result) print(f1result.f150) print(f1result.smallobjects.f150) ```

• Added new cookbook: Small Object Detection with SAHI. This cookbook provides a detailed guide on using InferenceSlicer for small object detection, and is one of the best cookbooks we've ever seen. Thank you @ediardo! #1483

• You can now try supervision annotators on your own images. Check out the annotator docs. The preview is powered by an Embedded Workflow. Thank you @joaomarcoscrs! #1533

• Enhanced LineZoneAnnotator, allowing the labels to align with the line, even when it's not horizontal. Also, you can now disable text background, and choose to draw labels off-center which minimizes overlaps for multiple LineZone labels. Thank you @jcruz-ferreyra! #854

```python import supervision as sv import cv2

image = cv2.imread("")

linezone = sv.LineZone( start=sv.Point(0, 100), end=sv.Point(50, 200) ) linezoneannotator = sv.LineZoneAnnotator( textorienttoline=True, displaytextbox=False, text_centered=False )

annotatedframe = linezoneannotator.annotate( frame=image.copy(), linecounter=line_zone )

sv.plot_image(frame) ```

https://github.com/user-attachments/assets/d7694b81-26ca-4236-bc66-af3d9e79d367

• Added per-class counting capabilities to LineZone and introduced LineZoneAnnotatorMulticlass for visualizing the counts per class. This feature allows tracking of individual classes crossing a line, enhancing the flexibility of use cases like traffic monitoring or crowd analysis. #1555

```python import supervision as sv import cv2

image = cv2.imread("")

linezone = sv.LineZone( start=sv.Point(0, 100), end=sv.Point(50, 200) ) linezone_annotator = sv.LineZoneAnnotatorMulticlass()

frame = linezoneannotator.annotate( frame=frame, linezones=[linezone] )

sv.plot_image(frame) ```

https://github.com/user-attachments/assets/b109f5bd-6ae7-473b-b4e8-910a869736b4

• Added from_easyocr, allowing integration of OCR results into the supervision framework. EasyOCR is an open-source optical character recognition (OCR) library that can read text from images. Thank you @onuralpszr! #1515

```python import supervision as sv import easyocr import cv2

image = cv2.imread("")

reader = easyocr.Reader(["en"]) result = reader.readtext("", paragraph=True) detections = sv.Detections.from_easyocr(result)

boxannotator = sv.BoxAnnotator(colorlookup=sv.ColorLookup.INDEX) labelannotator = sv.LabelAnnotator(colorlookup=sv.ColorLookup.INDEX)

annotatedimage = image.copy() annotatedimage = boxannotator.annotate(scene=annotatedimage, detections=detections) annotatedimage = labelannotator.annotate(scene=annotated_image, detections=detections)

sv.plotimage(annotatedimage) ```

• Added oriented_box_iou_batch function to detection.utils. This function computes Intersection over Union (IoU) for oriented or rotated bounding boxes (OBB), making it easier to evaluate detections with non-axis-aligned boxes. Thank you @patel-zeel! #1502

```python import numpy as np

boxestrue = np.array([[[1, 0], [0, 1], [3, 4], [4, 3]]]) boxesdetection = np.array([[[1, 1], [2, 0], [4, 2], [3, 3]]]) ious = sv.orientedboxioubatch(boxestrue, boxes_detection) print("IoU between true and detected boxes:", ious) ```

Note: the IoU is approximated as mask IoU.

• Extended PolygonZoneAnnotator to allow setting opacity when drawing zones, providing enhanced visualization by filling the zone with adjustable transparency. Thank you @grzegorz-roboflow! #1527

• Added from_ncnn, a connector for the NCNN. It is a powerful object detection framework from Tencent, written from ground-up in C++, with no third party dependencies. Thank you @onuralpszr! #1524

```python import cv2 from ncnn.modelzoo import getmodel import supervision as sv

image = cv2.imread("") model = getmodel( "yolov8s", targetsize=640, probthreshold=0.5, nmsthreshold=0.45, numthreads=4, usegpu=True, ) result = model(image) detections = sv.Detections.from_ncnn(result) ```

🌱 Changed

• Supervision now depends on opencv-python rather than opencv-python-headless. #1530

• Fixed broken or outdated links in documentation and notebooks, improving navigation and ensuring accuracy of references. Thanks to @capjamesg for identifying these issues. #1523

• Enabled and fixed Ruff rules for code formatting, including changes like avoiding unnecessary iterable allocations and using Optional for default mutable arguments. #1526

🔧 Fixed

• Updated the COCO 101 point Average Precision algorithm to correctly interpolate precision, providing a more precise calculation of average precision without averaging out intermediate values. #1500

• Resolved miscellaneous issues highlighted when building documentation. This mostly includes whitespace adjustments and type inconsistencies. Updated documentation for clarity and fixed formatting issues. Added explicit version for mkdocstrings-python. #1549

• Clarified documentation around the overlap_ratio_wh argument deprecation in InferenceSlicer. #1547

✅ No deprecations this time!

❌ Removed

• The frame_resolution_wh parameter in PolygonZone has been removed due to deprecation.
• Supervision installation methods "headless" and "desktop" removed, as they are no longer needed. pip install supervision[headless] will install the base library and warn of non-existent extra.

🏆 Contributors

@onuralpszr (Onuralp SEZER), @joaomarcoscrs (João Marcos Cardoso Ramos da Silva), @jcruz-ferreyra (Juan Cruz), @patel-zeel (Zeel B Patel), @grzegorz-roboflow (Grzegorz Klimaszewski), @Kadermiyanyedi (Kader Miyanyedi), @ediardo (Eddie Ramirez), @CharlesCNorton, @ethanwhite (Ethan White), @josephofiowa (Joseph Nelson), @tibeoh (Thibault Itart-Longueville), @SkalskiP (Piotr Skalski), @LinasKo (Linas Kondrackis)

Thank you to Pexels for providing fantastic images and videos!

- Python
Published by LinasKo over 1 year ago

supervision - supervision-0.23.0

🚀 Added

• BackgroundOverlayAnnotator annotates the background of your image! #1385

https://github.com/user-attachments/assets/c1f3ce11-08c1-4648-9176-4e7920b91a8a

(video by Pexels)

• We're introducing metrics, which currently supports xyxy boxes and masks. Over the next few releases, supervision will focus on adding more metrics, allowing you to evaluate your model performance. We plan to support not just boxes, masks, but oriented bounding boxes as well! #1442

[!TIP] Help in implementing metrics is very welcome! Keep an eye on our issue board if you'd like to contribute!

```python import supervision as sv from supervision.metrics import MeanAveragePrecision

predictions = sv.Detections(...) targets = sv.Detections(...)

mapmetric = MeanAveragePrecision() mapresult = map_metric.update(predictions, targets).compute()

print(mapresult) print(mapresult.map5095) print(mapresult.largeobjects.map5095) map_result.plot() ```

Here's a very basic way to compare model results:

📊 Example code

```python import supervision as sv from supervision.metrics import MeanAveragePrecision from inference import get_model import matplotlib.pyplot as plt # !wget https://media.roboflow.com/notebooks/examples/dog.jpeg image = "dog.jpeg" model_1 = get_model("yolov8n-640") model_2 = get_model("yolov8s-640") model_3 = get_model("yolov8m-640") model_4 = get_model("yolov8l-640") results_1 = model_1.infer(image)[0] results_2 = model_2.infer(image)[0] results_3 = model_3.infer(image)[0] results_4 = model_4.infer(image)[0] detections_1 = sv.Detections.from_inference(results_1) detections_2 = sv.Detections.from_inference(results_2) detections_3 = sv.Detections.from_inference(results_3) detections_4 = sv.Detections.from_inference(results_4) map_n_metric = MeanAveragePrecision().update([detections_1], [detections_4]).compute() map_s_metric = MeanAveragePrecision().update([detections_2], [detections_4]).compute() map_m_metric = MeanAveragePrecision().update([detections_3], [detections_4]).compute() labels = ["YOLOv8n", "YOLOv8s", "YOLOv8m"] map_values = [map_n_metric.map50_95, map_s_metric.map50_95, map_m_metric.map50_95] plt.title("YOLOv8 Model Comparison") plt.bar(labels, map_values) ax = plt.gca() ax.set_ylim([0, 1]) plt.show() ```

• Added the IconAnnotator, which allows you to place icons on your images. #930

https://github.com/user-attachments/assets/ff80acf5-67f2-4c20-a3fe-b63cac07ae31

(Video by Pexels, icons by Icons8)

```python import supervision as sv from inference import get_model

image = icondog = <DOGPNGPATH> iconcat =

model = getmodel(modelid="yolov8n-640") results = model.infer(image)[0] detections = sv.Detections.from_inference(results)

iconpaths = [] for classname in detections.data["classname"]: if classname == "dog": iconpaths.append(icondog) elif classname == "cat": iconpaths.append(iconcat) else: iconpaths.append("")

iconannotator = sv.IconAnnotator() annotatedframe = iconannotator.annotate( scene=image.copy(), detections=detections, iconpath=icon_paths ) ```

• Segment Anything 2 was released this month. And while you can load its results via from_sam, we've added support to from_ultralytics for loading the results if you ran it with Ultralytics. #1354

```python import cv2 import supervision as sv from ultralytics import SAM

image = cv2.imread("...")

model = SAM("mobilesam.pt") results = model(image, bboxes=[[588, 163, 643, 220]]) detections = sv.Detections.fromultralytics(results[0])

polygonannotator = sv.PolygonAnnotator() maskannotator = sv.MaskAnnotator()

annoatedimage = maskannotator.annotate(image.copy(), detections) annoatedimage = polygonannotator.annotate(annoated_image, detections)

sv.plotimage(annoatedimage, (12,12)) ```

SAM2 with our annotators:

https://github.com/user-attachments/assets/6a98d651-2596-43e9-b485-ea6f0de4fffa

• TriangleAnnotator and DotAnnotator contour color customization #1458
• VertexLabelAnnotator for keypoints now has text_color parameter #1409

🌱 Changed

• Updated sv.Detections.from_transformers to support the transformers v5 functions. This includes the DetrImageProcessor methods post_process_object_detection, post_process_panoptic_segmentation, post_process_semantic_segmentation, and post_process_instance_segmentation. #1386
• InferenceSlicer now features an overlap_ratio_wh parameter, making it easier to compute slice sizes when handling overlapping slices. #1434

```python imagewithsmallobjects = cv2.imread("...") model = getmodel("yolov8n-640")

def callback(imageslice: np.ndarray) -> sv.Detections: print("imageslice.shape:", imageslice.shape) result = model.infer(imageslice)[0] return sv.Detections.from_inference(result)

slicer = sv.InferenceSlicer( callback=callback, slicewh=(128, 128), overlapratio_wh=(0.2, 0.2), )

detections = slicer(imagewithsmall_objects) ```

🛠️ Fixed

• Annotator type fixes #1448
• New way of seeking to a specific video frame, where other methods don't work #1348
• plot_image now clearly states the size is in inches. #1424

⚠️ Deprecated

• overlap_filter_strategy in InferenceSlicer.__init__ is deprecated and will be removed in supervision-0.27.0. Use overlap_strategy instead.
• overlap_ratio_wh in InferenceSlicer.__init__ is deprecated and will be removed in supervision-0.27.0. Use overlap_wh instead.

❌ Removed

• The track_buffer, track_thresh, and match_thresh parameters in ByteTrack are deprecated and were removed as of supervision-0.23.0. Use lost_track_buffer, track_activation_threshold, and minimum_matching_threshold instead.
• The triggering_position parameter in sv.PolygonZone was removed as of supervision-0.23.0. Use triggering_anchors instead.

🏆 Contributors

@shaddu, @onuralpszr (Onuralp SEZER), @Kadermiyanyedi (Kader Miyanyedi), @xaristeidou (Christoforos Aristeidou), @Gk-rohan (Rohan Gupta), @Bhavay-2001 (Bhavay Malhotra), @arthurcerveira (Arthur Cerveira), @J4BEZ (Ju Hoon Park), @venkatram-dev, @eric220, @capjamesg (James), @yeldarby (Brad Dwyer), @SkalskiP (Piotr Skalski), @LinasKo (LinasKo)

- Python
Published by LinasKo over 1 year ago

supervision - supervision-0.22.0

🚀 Added

• Supervision Cheatsheet 🔥

• sv.KeyPoints.from_mediapipe adding support for Mediapipe keypoint models (both legacy and modern), along with default visualizers for face and body pose keypoints. (#1232, #1316)

```python import numpy as np import mediapipe as mp import supervision as sv from PIL import Image

model = mp.solutions.face_mesh.FaceMesh()

edge_annotator = sv.EdgeAnnotator(color=sv.Color.BLACK, thickness=2)

image = Image.open().convert('RGB') results = model.process(np.array(image)) keypoints = sv.KeyPoints.frommediapipe(results, resolution_wh=image.size)

annotatedimage = edgeannotator.annotate(scene=image, keypoints=keypoints) ```

https://github.com/user-attachments/assets/883a6bcc-5e39-41b0-9b6d-0348b5b2fe0e

• sv.KeyPoints.from_detectron2 and sv.Detections.from_detectron2 extending support for Detectron2 models. (#1310, #1300)

• sv.RichLabelAnnotator allowing to draw unicode characters (e.g. from non-latin languages), as long as you provide a compatible font. (#1277)

https://github.com/user-attachments/assets/de60eeb4-1259-421b-af66-f622a15988ea

🌱 Changed

• sv.DetectionsDataset and sv.ClassificationDataset allowing to load the images into memory only when necessary (lazy loading). (#1326)

```python import roboflow from roboflow import Roboflow import supervision as sv

roboflow.login() rf = Roboflow()

project = rf.workspace().project() dataset = project.version().download("coco")

dstrain = sv.DetectionDataset.fromcoco( imagesdirectorypath=f"{dataset.location}/train", annotationspath=f"{dataset.location}/train/annotations.coco.json", )

path, image, annotation = ds_train[0] # loads image on demand

for path, image, annotation in ds_train: # loads image on demand ```

• sv.Detections.from_lmm allowing to parse Florence-2 text result into sv.Detections object. (#1296)

• sv.DotAnnotator and sv.TriangleAnnotator allowing to add marker outlines. (#1294)

🛠️ Fixed

• sv.ColorAnnotator and sv.CropAnnotator buggy behaviours. (#1277, #1312)

🧑‍🍳 Cookbooks

This release, @onuralpszr added two new Cookbooks to our collection. Check them out to learn how to save Detections to a file and convert it back to Detections!

• Serialize detections to JSON (#975)
• Serialize detections to CSV (#975).

🏆 Contributors

@onuralpszr (Onuralp SEZER), @David-rn (David Redó), @jeslinpjames (Jeslin P James), @Bhavay-2001 (Bhavay Malhotra), @hardikdava (Hardik Dava), @kirilman, @dsaha21 (Dripto Saha), @cdragos (Dragos Catarahia), @mqasim41 (Muhammad Qasim), @SkalskiP (Piotr Skalski), @LinasKo (Linas Kondrackis)

Special thanks to @rolson24 (Raif Olson) for helping the community with ByteTrack!

- Python
Published by LinasKo over 1 year ago

supervision - supervision-0.21.0

📅 Timeline

The supervision-0.21.0 release is around the corner. Here is the timeline:

• 5 Jun 2024 08:00 PM CEST (UTC +2) / 5 Jun 2024 11:00 AM PDT (UTC -7) - merge develop into main - closing list supervision-0.21.0 features
• 6 Jun 2024 11:00 AM CEST (UTC +2) / 6 Jun 2024 02:00 AM PDT (UTC -7) - release supervision-0.21.0

🪵 Changelog

🚀 Added

• sv.Detections.with_nmm to perform non-maximum merging on the current set of object detections. (#500)

• sv.Detections.from_lmm allowing to parse Large Multimodal Model (LMM) text result into sv.Detections object. For now from_lmm supports only PaliGemma result parsing. (#1221)

```python import supervision as sv

paligemmaresult = " cat" detections = sv.Detections.fromlmm( sv.LMM.PALIGEMMA, paligemmaresult, resolutionwh=(1000, 1000), classes=['cat', 'dog'] ) detections.xyxy

array([[250., 250., 750., 750.]])

detections.class_id

array([0])

```

• sv.VertexLabelAnnotator allowing to annotate every vertex of a keypoint skeleton with custom text and color. (#1236)

```python import supervision as sv

image = ... key_points = sv.KeyPoints(...)

LABELS = [ "nose", "left eye", "right eye", "left ear", "right ear", "left shoulder", "right shoulder", "left elbow", "right elbow", "left wrist", "right wrist", "left hip", "right hip", "left knee", "right knee", "left ankle", "right ankle" ]

COLORS = [ "#FF6347", "#FF6347", "#FF6347", "#FF6347", "#FF6347", "#FF1493", "#00FF00", "#FF1493", "#00FF00", "#FF1493", "#00FF00", "#FFD700", "#00BFFF", "#FFD700", "#00BFFF", "#FFD700", "#00BFFF" ] COLORS = [sv.Color.fromhex(colorhex=c) for c in COLORS]

vertexlabelannotator = sv.VertexLabelAnnotator( color=COLORS, textcolor=sv.Color.BLACK, borderradius=5 ) annotatedframe = vertexlabelannotator.annotate( scene=image.copy(), keypoints=key_points, labels=labels ) ```

• sv.KeyPoints.from_inference and sv.KeyPoints.from_yolo_nas allowing to create sv.KeyPoints from Inference and YOLO-NAS result. (#1147 and #1138)

• sv.mask_to_rle and sv.rle_to_mask allowing for easy conversion between mask and rle formats. (#1163)

🌱 Changed

• sv.InferenceSlicer allowing to select overlap filtering strategy (NONE, NON_MAX_SUPPRESSION and NON_MAX_MERGE). (#1236)

• sv.InferenceSlicer adding instance segmentation model support. (#1178)

```python import cv2 import numpy as np import supervision as sv from inference import get_model

model = getmodel(modelid="yolov8x-seg-640") image = cv2.imread()

def callback(imageslice: np.ndarray) -> sv.Detections: results = model.infer(imageslice)[0] return sv.Detections.from_inference(results)

slicer = sv.InferenceSlicer(callback = callback) detections = slicer(image)

maskannotator = sv.MaskAnnotator() labelannotator = sv.LabelAnnotator()

annotatedimage = maskannotator.annotate( scene=image, detections=detections) annotatedimage = labelannotator.annotate( scene=annotated_image, detections=detections) ```

• sv.LineZone making it 10-20 times faster, depending on the use case. (#1228)

• sv.DetectionDataset.from_coco and sv.DetectionDataset.as_coco adding support for run-length encoding (RLE) mask format. (#1163)

🏆 Contributors

@onuralpszr (Onuralp SEZER), @LinasKo (Linas Kondrackis), @rolson24 (Raif Olson), @mario-dg (Mario da Graca), @xaristeidou (Christoforos Aristeidou), @ManzarIMalik (Manzar Iqbal Malik), @tc360950 (Tomasz Cąkała), @emSko, @SkalskiP (Piotr Skalski)

- Python
Published by SkalskiP over 1 year ago

supervision - supervision-0.20.0

🚀 Added

• sv.KeyPoints to provide initial support for pose estimation and broader keypoint detection models. (#1128)

• sv.EdgeAnnotator and sv.VertexAnnotator to enable rendering of results from keypoint detection models. (#1128)

```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)

edgeannotators = sv.EdgeAnnotator(color=sv.Color.GREEN, thickness=5) annotatedimage = edge_annotators.annotate(image.copy(), keypoints) ```

```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)

vertexannotators = sv.VertexAnnotator(color=sv.Color.GREEN, radius=10) annotatedimage = vertex_annotators.annotate(image.copy(), keypoints) ```

🌱 Changed

• sv.LabelAnnotator by adding an additional corner_radius argument that allows for rounding the corners of the bounding box. (#1037)

• sv.PolygonZone such that the frame_resolution_wh argument is no longer required to initialize sv.PolygonZone. (#1109)

[!WARNING]
The frame_resolution_wh parameter in sv.PolygonZone is deprecated and will be removed in supervision-0.24.0.

• sv.get_polygon_center to calculate a more accurate polygon centroid. (#1084)

• sv.Detections.from_transformers by adding support for Transformers segmentation models and extract class names values. (#1069)

```python import torch import supervision as sv from PIL import Image from transformers import DetrImageProcessor, DetrForSegmentation

processor = DetrImageProcessor.frompretrained("facebook/detr-resnet-50-panoptic") model = DetrForSegmentation.frompretrained("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 targetsize = torch.tensor([[height, width]]) results = processor.postprocesssegmentation( outputs=outputs, targetsizes=targetsize)[0] detections = sv.Detections.fromtransformers(results, id2label=model.config.id2label)

maskannotator = sv.MaskAnnotator() labelannotator = sv.LabelAnnotator(text_position=sv.Position.CENTER)

annotatedimage = maskannotator.annotate( scene=image, detections=detections) annotatedimage = labelannotator.annotate( scene=annotated_image, detections=detections) ```

🛠️ Fixed

• sv.ByteTrack.update_with_detections which was removing segmentation masks while tracking. Now, ByteTrack can be used alongside segmentation models. (#787)

🏆 Contributors

@onuralpszr (Onuralp SEZER), @rolson24 (Raif Olson), @xaristeidou (Christoforos Aristeidou), @jeslinpjames (Jeslin P James), @Griffin-Sullivan (Griffin Sullivan), @PawelPeczek-Roboflow (Paweł Pęczek), @pirnerjonas (Jonas Pirner), @sharingan000, @macc-n, @LinasKo (Linas Kondrackis), @SkalskiP (Piotr Skalski)

- Python
Published by SkalskiP almost 2 years ago

supervision - supervision-0.19.0

🧑‍🍳 Cookbooks

Supervision Cookbooks - A curated open-source collection crafted by the community, offering practical examples, comprehensive guides, and walkthroughs for leveraging Supervision alongside diverse Computer Vision models. (#860)

🚀 Added

• sv.CSVSink allowing for the straightforward saving of image, video, or stream inference results in a .csv file. (#818)

```python import supervision as sv from ultralytics import YOLO

model = YOLO() csvsink = sv.CSVSink(<RESULTCSVFILEPATH>) framesgenerator = sv.getvideoframesgenerator()

with csvsink: for frame in framesgenerator: result = model(frame)[0] detections = sv.Detections.fromultralytics(result) csvsink.append(detections, customdata={<CUSTOMLABEL>:}) ```

https://github.com/roboflow/supervision/assets/26109316/621588f9-69a0-44fe-8aab-ab4b0ef2ea1b

• sv.JSONSink allowing for the straightforward saving of image, video, or stream inference results in a .json file. (#819)

```python import supervision as sv from ultralytics import YOLO

model = YOLO() jsonsink = sv.JSONSink(<RESULTJSONFILEPATH>) framesgenerator = sv.getvideoframesgenerator()

with jsonsink: for frame in framesgenerator: result = model(frame)[0] detections = sv.Detections.fromultralytics(result) jsonsink.append(detections, customdata={<CUSTOMLABEL>:}) ```

• sv.mask_iou_batch allowing to compute Intersection over Union (IoU) of two sets of masks. (#847)
• sv.mask_non_max_suppression allowing to perform Non-Maximum Suppression (NMS) on segmentation predictions. (#847)
• sv.CropAnnotator allowing users to annotate the scene with scaled-up crops of detections. (#888)

```python import cv2 import supervision as sv from inference import get_model

image = cv2.imread() model = getmodel(modelid="yolov8n-640")

result = model.infer(image)[0] detections = sv.Detections.from_inference(result)

cropannotator = sv.CropAnnotator() annotatedframe = crop_annotator.annotate( scene=image.copy(), detections=detections ) ```

https://github.com/roboflow/supervision/assets/26109316/0a5b67ce-55e7-4e26-9495-a68f9ad97ec7

🌱 Changed

• sv.ByteTrack.reset allowing users to clear trackers state, enabling the processing of multiple video files in sequence. (#827)
• sv.LineZoneAnnotator allowing to hide in/out count using display_in_count and display_out_count properties. (#802)
• sv.ByteTrack input arguments and docstrings updated to improve readability and ease of use. (#787)

[!WARNING]
The track_buffer, track_thresh, and match_thresh parameters in sv.ByterTrack are deprecated and will be removed in supervision-0.23.0. Use lost_track_buffer, track_activation_threshold, and minimum_matching_threshold instead.

• sv.PolygonZone to now accept a list of specific box anchors that must be in zone for a detection to be counted. (#910)

[!WARNING]
The triggering_position parameter in sv.PolygonZone is deprecated and will be removed in supervision-0.23.0. Use triggering_anchors instead.

• Annotators adding support for Pillow images. All supervision Annotators can now accept an image as either a numpy array or a Pillow Image. They automatically detect its type, draw annotations, and return the output in the same format as the input. (#875)

🛠️ Fixed

• sv.DetectionsSmoother removing tracking_id from sv.Detections. (#944)
• sv.DetectionDataset which, after changes introduced in supervision-0.18.0, failed to load datasets in YOLO, PASCAL VOC, and COCO formats.

🏆 Contributors

@onuralpszr (Onuralp SEZER), @LinasKo (Linas Kondrackis), @LeviVasconcelos (Levi Vasconcelos), @AdonaiVera (Adonai Vera), @xaristeidou (Christoforos Aristeidou), @Kadermiyanyedi (Kader Miyanyedi), @NickHerrig (Nick Herrig), @PacificDou (Shuyang Dou), @iamhatesz (Tomasz Wrona), @capjamesg (James Gallagher), @sansyo, @SkalskiP (Piotr Skalski)

- Python
Published by SkalskiP almost 2 years ago

supervision - supervision-0.18.0

🚀 Added

• sv.PercentageBarAnnotator allowing to annotate images and videos with percentage values representing confidence or other custom property. (#720)

```python import supervision as sv

image = ... detections = sv.Detections(...)

percentagebarannotator = sv.PercentageBarAnnotator() annotatedframe = percentagebar_annotator.annotate( scene=image.copy(), detections=detections ) ```

• sv.RoundBoxAnnotator allowing to annotate images and videos with rounded corners bounding boxes. (#702)
• sv.DetectionsSmoother allowing for smoothing detections over multiple frames in video tracking. (#696)

https://github.com/roboflow/supervision/assets/26109316/4dd703ad-ffba-492b-97ff-1be84e237e83

• sv.OrientedBoxAnnotator allowing to annotate images and videos with OBB (Oriented Bounding Boxes). (#770)

```python import cv2 import supervision as sv from ultralytics import YOLO

image = cv2.imread() model = YOLO("yolov8n-obb.pt")

result = model(image)[0] detections = sv.Detections.from_ultralytics(result)

orientedboxannotator = sv.OrientedBoxAnnotator() annotatedframe = orientedbox_annotator.annotate( scene=image.copy(), detections=detections ) ```

• sv.ColorPalette.from_matplotlib allowing users to create a sv.ColorPalette instance from a Matplotlib color palette. (#769)

```python import supervision as sv

sv.ColorPalette.from_matplotlib('viridis', 5)

ColorPalette(colors=[Color(r=68, g=1, b=84), Color(r=59, g=82, b=139), ...])

```

🌱 Changed

• sv.Detections.from_ultralytics adding support for OBB (Oriented Bounding Boxes). (#770)
• sv.LineZone to now accept a list of specific box anchors that must cross the line for a detection to be counted. This update marks a significant improvement from the previous requirement, where all four box corners were necessary. Users can now specify a single anchor, such as sv.Position.BOTTOM_CENTER, or any other combination of anchors defined as List[sv.Position]. (#735)
• sv.Detections to support custom payload. (#700)
• sv.Color's and sv.ColorPalette's method of accessing predefined colors, transitioning from a function-based approach (sv.Color.red()) to a more intuitive and conventional property-based method (sv.Color.RED). (#756) (#769)

[!WARNING]
sv.ColorPalette.default() is deprecated and will be removed in supervision-0.21.0. Use sv.ColorPalette.DEFAULT instead.

• sv.ColorPalette.DEFAULT value, giving users a more extensive set of annotation colors. (#769)

• sv.Detections.from_roboflow to sv.Detections.from_inference streamlining its functionality to be compatible with both the both inference pip package and the Roboflow hosted API. (#677)

[!WARNING]
Detections.from_roboflow() is deprecated and will be removed in supervision-0.21.0. Use Detections.from_inference instead.

```python import cv2 import supervision as sv from inference.models.utils import getroboflowmodel

image = cv2.imread() model = getroboflowmodel(model_id="yolov8s-640")

result = model.infer(image)[0] detections = sv.Detections.from_inference(result) ```

🛠️ Fixed

• sv.LineZone functionality to accurately update the counter when an object crosses a line from any direction, including from the side. This enhancement enables more precise tracking and analytics, such as calculating individual in/out counts for each lane on the road. (#735)

https://github.com/roboflow/supervision/assets/26109316/412c4d9c-b228-4bcc-a4c7-e6a0c8f2da6e

🏆 Contributors

@onuralpszr (Onuralp SEZER), @HinePo (Rafael Levy), @xaristeidou (Christoforos Aristeidou), @revtheundead (Utku Özbek), @paulguerrie (Paul Guerrie), @yeldarby (Brad Dwyer), @capjamesg (James Gallagher), @SkalskiP (Piotr Skalski)

- Python
Published by SkalskiP about 2 years ago

supervision - supervision-0.17.1

🚀 Added

• Support for Python 3.12.

🏆 Contributors

@onuralpszr (Onuralp SEZER), @SkalskiP (Piotr Skalski)

- Python
Published by SkalskiP about 2 years ago

supervision - supervision-0.17.0

🚀 Added

• sv.PixelateAnnotator allowing to pixelate objects on images and videos. (#633)

https://github.com/roboflow/supervision/assets/26109316/c2d4b3b1-fd19-44bb-94ec-f21b28dfd05f

• sv.TriangleAnnotator allowing to annotate images and videos with triangle markers. (#652)

• sv.PolygonAnnotator allowing to annotate images and videos with segmentation mask outline. (#602)

  ```python

  import supervision as sv

  image = ... detections = sv.Detections(...)

  polygonannotator = sv.PolygonAnnotator() annotatedframe = polygon_annotator.annotate( ... scene=image.copy(), ... detections=detections ... ) ```

https://github.com/roboflow/supervision/assets/26109316/c9236bf7-6ba4-4799-bf2a-b5532ad3591b

• sv.assets allowing download of video files that you can use in your demos. (#476)

  ```python

  from supervision.assets import downloadassets, VideoAssets downloadassets(VideoAssets.VEHICLES) "vehicles.mp4" ```

• Position.CENTER_OF_MASS allowing to place labels in center of mass of segmentation masks. (#605)

• sv.scale_boxes allowing to scale sv.Detections.xyxy values. (#651)

• sv.calculate_dynamic_text_scale and sv.calculate_dynamic_line_thickness allowing text scale and line thickness to match image resolution. (#637)

• sv.Color.as_hex allowing to extract color value in HEX format. (#620)

• sv.Classifications.from_timm allowing to load classification result from timm models. (#572)

• sv.Classifications.from_clip allowing to load classification result from clip model. (#478)

• sv.Detections.from_azure_analyze_image allowing to load detection results from Azure Image Analysis. (#571)

🌱 Changed

• sv.BoxMaskAnnotator renaming it to sv.ColorAnnotator. (#646)

• sv.MaskAnnotator to make it 5x faster. (#606)

🛠️ Fixed

• sv.DetectionDataset.from_yolo to ignore empty lines in annotation files. (#584)

• sv.BlurAnnotator to trim negative coordinates before bluring detections. (#555)

• sv.TraceAnnotator to respect trace position. (#511)

🏆 Contributors

@onuralpszr (Onuralp SEZER), @hugoles (Hugo Dutra), @karanjakhar (Karan Jakhar), @kim-jeonghyun (Jeonghyun Kim), @fdloopes ( Felipe Lopes), @abhishek7kalra (Abhishek Kalra), @SummitStudiosDev, @xenteros @capjamesg (James Gallagher), @SkalskiP (Piotr Skalski)

- Python
Published by SkalskiP about 2 years ago

supervision - supervision-0.16.0

🚀 Added

https://github.com/roboflow/supervision/assets/26109316/691e219c-0565-4403-9218-ab5644f39bce

• sv.BoxMaskAnnotator allowing to annotate images and videos with mox masks. (#422)
• sv.HaloAnnotator allowing to annotate images and videos with halo effect. (#433)

```python

import supervision as sv

image = ... detections = sv.Detections(...)

haloannotator = sv.HaloAnnotator() annotatedframe = halo_annotator.annotate( ... scene=image.copy(), ... detections=detections ... ) ```

• sv.HeatMapAnnotator allowing to annotate videos with heat maps. (#466)
• sv.DotAnnotator allowing to annotate images and videos with dots. (#492)
• sv.draw_image allowing to draw an image onto a given scene with specified opacity and dimensions. (#449)
• sv.FPSMonitor for monitoring frames per second (FPS) to benchmark latency. (#280)
• 🤗 Hugging Face Annotators space. (#454)

🌱 Changed

• sv.LineZone.trigger now return Tuple[np.ndarray, np.ndarray]. The first array indicates which detections have crossed the line from outside to inside. The second array indicates which detections have crossed the line from inside to outside. (#482)
• Annotator argument name from color_map: str to color_lookup: ColorLookup enum to increase type safety. (#465)
• sv.MaskAnnotator allowing 2x faster annotation. (#426)

🛠️ Fixed

• Poetry env definition allowing proper local installation. (#477)
• sv.ByteTrack to return np.array([], dtype=int) when svDetections is empty. (#430)
• YOLONAS detection missing predication part added & fixed (#416)
• SAM detection at Demo Notebook MaskAnnotator(color_map="index") color_map set to index (#416)

🗑️ Deleted

Warning Deleted sv.Detections.from_yolov8 and sv.Classifications.from_yolov8 as those are now replaced by sv.Detections.from_ultralytics and sv.Classifications.from_ultralytics. (#438)

🏆 Contributors

@hardikdava (Hardik Dava), @onuralpszr (Onuralp SEZER), @kapter, @keshav278 (Keshav Subramanian), @akashpambhar (Akash Pambhar), @AntonioConsiglio (Antonio Consiglio), @ashishdatta, @mario-dg (Mario da Graca), @ jayaBalaR (JAYABALAMBIKA.R), @abhishek7kalra (Abhishek Kalra), @PankajKrana (Pankaj Kumar Rana), @capjamesg (James Gallagher), @SkalskiP (Piotr Skalski)

- Python
Published by SkalskiP over 2 years ago

supervision - supervision-0.15.0

🚀 Added

https://github.com/roboflow/supervision/assets/26109316/4d6c4a70-b40e-48fc-9e58-23b7e67bf94a

• sv.LabelAnnotator allowing to annotate images and videos with text. (#170)

• sv.BoundingBoxAnnotator allowing to annotate images and videos with bounding boxes. (#170)

• sv.BoxCornerAnnotator allowing to annotate images and videos with just bounding box corners. (#170)

• sv.MaskAnnotator allowing to annotate images and videos with segmentation masks. (#170)

• sv.EllipseAnnotator allowing to annotate images and videos with ellipses (sports game style). (#170)

• sv.CircleAnnotator allowing to annotate images and videos with circles. (#386)

• sv.TraceAnnotator allowing to draw path of moving objects on videos. (#354)

• sv.BlurAnnotator allowing to blur objects on images and videos. (#405)

```python

import supervision as sv

image = ... detections = sv.Detections(...)

boundingboxannotator = sv.BoundingBoxAnnotator() annotatedframe = boundingbox_annotator.annotate( ... scene=image.copy(), ... detections=detections ... ) ```

• Supervision usage example. You can now learn how to perform traffic flow analysis with Supervision. (#354)

https://github.com/roboflow/supervision/assets/26109316/c9436828-9fbf-4c25-ae8c-60e9c81b3900

🌱 Changed

• sv.Detections.from_roboflow now does not require class_list to be specified. The class_id value can be extracted directly from the inference response. (#399)

• sv.VideoSink now allows to customize the output codec. (#381)

• sv.InferenceSlicer can now operate in multithreading mode. (#361)

🛠️ Fixed

• sv.Detections.from_deepsparse to allow processing empty deepsparse result object. (#348)

🏆 Contributors

@hardikdava (Hardik Dava), @onuralpszr (Onuralp SEZER), @Killua7362 (Akshay Bhat), @fcakyon (Fatih C. Akyon), @akashAD98 (Akash A Desai), @Rajarshi-Misra, @capjamesg (James Gallagher), @SkalskiP (Piotr Skalski)

- Python
Published by SkalskiP over 2 years ago

supervision - 0.14.0

🚀 Added

• Support for SAHI inference technique with sv.InferenceSlicer. (#282)

```python

import cv2 import supervision as sv import numpy as np from ultralytics import YOLO

image = cv2.imread(SOURCEIMAGEPATH) model = YOLO(...)

def callback(imageslice: np.ndarray) -> sv.Detections: ... result = model(imageslice)[0] ... return sv.Detections.from_ultralytics(result)

slicer = sv.InferenceSlicer(callback = callback)

detections = slicer(image) ```

https://github.com/roboflow/supervision/assets/26109316/da665575-4d74-469c-a1f7-a43b7ee7e214

• Detections.from_deepsparse to enable seamless integration with DeepSparse framework. (#297)

• sv.Classifications.from_ultralytics to enable seamless integration with Ultralytics framework. This will enable you to use supervision with all models that Ultralytics supports. (#281)

  Warning sv.Detections.from_yolov8 and sv.Classifications.from_yolov8 are now deprecated and will be removed with supervision-0.16.0 release.

• First supervision usage example script showing how to detect and track objects on video using YOLOv8 + Supervision. (#341)

https://github.com/roboflow/supervision/assets/26109316/d8128440-6bd7-491a-8c7d-519254b76ec5

🌱 Changed

• sv.ClassificationDataset and sv.DetectionDataset now use image path (not image name) as dataset keys. (#296)

🛠️ Fixed

• Detections.from_roboflow to filter out polygons with less than 3 points. (#300)

🏆 Contributors

@hardikdava (Hardik Dava), @onuralpszr (Onuralp SEZER), @mayankagarwals (Mayank Agarwal), @rizavelioglu (Riza Velioglu), @arjun-234 (Arjun D.), @mwitiderrick (Derrick Mwiti), @ShubhamKanitkar32, @gasparitiago (Tiago De Gaspari), @capjamesg (James Gallagher), @SkalskiP (Piotr Skalski)

- Python
Published by capjamesg over 2 years ago

supervision - supervision-0.13.0

🚀 Added

• Support for mean average precision (mAP) for object detection models with sv.MeanAveragePrecision. (#236)

```python

import supervision as sv from ultralytics import YOLO

dataset = sv.DetectionDataset.from_yolo(...)

model = YOLO(...) def callback(image: np.ndarray) -> sv.Detections: ... result = model(image)[0] ... return sv.Detections.from_yolov8(result)

meanaverageprecision = sv.MeanAveragePrecision.benchmark( ... dataset = dataset, ... callback = callback ... )

meanaverageprecision.map50_95 0.433 ```

• Support for ByteTrack for object tracking with sv.ByteTrack. (#256)

```python

import supervision as sv from ultralytics import YOLO

model = YOLO(...) byte_tracker = sv.ByteTrack() annotator = sv.BoxAnnotator()

def callback(frame: np.ndarray, index: int) -> np.ndarray: ... results = model(frame)[0] ... detections = sv.Detections.fromyolov8(results) ... detections = bytetracker.updatefromdetections(detections=detections) ... labels = [ ... f"#{trackerid} {model.model.names[classid]} {confidence:0.2f}" ... for , _, confidence, classid, tracker_id ... in detections ... ] ... return annotator.annotate(scene=frame.copy(), detections=detections, labels=labels)

sv.processvideo( ... sourcepath='...', ... target_path='...', ... callback=callback ... ) ```

https://github.com/roboflow/supervision/assets/26109316/d5d393f5-e577-474a-bc8c-82483ef8a578

• sv.Detections.from_ultralytics to enable seamless integration with Ultralytics framework. This will enable you to use supervision with all models that Ultralytics supports. (#222)

  Warning sv.Detections.from_yolov8 is now deprecated and will be removed with supervision-0.15.0 release.

• sv.Detections.from_paddledet to enable seamless integration with PaddleDetection framework. (#191)

• Support for loading PASCAL VOC segmentation datasets with sv.DetectionDataset.. (#245)

🏆 Contributors

@hardikdava (Hardik Dava), @kirilllzaitsev (Kirill Zaitsev), @onuralpszr (Onuralp SEZER), @dbroboflow, @mayankagarwals (Mayank Agarwal), @danigarciaoca (Daniel M. García-Ocaña), @capjamesg (James Gallagher), @SkalskiP (Piotr Skalski)

- Python
Published by capjamesg over 2 years ago

supervision - supervision-0.12.0

Warning With the supervision-0.12.0 release, we are terminating official support for Python 3.7. (#179)

🚀 Added

• Initial support for object detection model benchmarking with sv.ConfusionMatrix. (#177)

```python

import supervision as sv from ultralytics import YOLO

dataset = sv.DetectionDataset.from_yolo(...)

model = YOLO(...) def callback(image: np.ndarray) -> sv.Detections: ... result = model(image)[0] ... return sv.Detections.from_yolov8(result)

confusion_matrix = sv.ConfusionMatrix.benchmark( ... dataset = dataset, ... callback = callback ... )

confusion_matrix.matrix array([ [0., 0., 0., 0.], [0., 1., 0., 1.], [0., 1., 1., 0.], [1., 1., 0., 0.] ]) ```

• Detections.from_mmdetection to enable seamless integration with MMDetection framework. (#173)

• Ability to install package in headless or desktop mode. (#130)

🌱 Changed

• Packing method from setup.py to pyproject.toml. (#180)

🛠️ Fixed

• sv.DetectionDataset.from_cooc can't be loaded when there are images without annotations. (#188)
• sv.DetectionDataset.from_yolo can't load background instances. (#226)

🏆 Contributors

@kirilllzaitsev @hardikdava @onuralpszr @Ucag @SkalskiP @capjamesg

- Python
Published by capjamesg over 2 years ago

supervision - supervision-0.11.1

🛠️ Fixed

• as_folder_structure fails to save sv.ClassificationDataset when it is result of inference. (https://github.com/roboflow/supervision/pull/165)

🏆 Contributors

@capjamesg @SkalskiP

- Python
Published by SkalskiP over 2 years ago

supervision - supervision-0.11.0

🚀 Added

• Ability to load and save sv.DetectionDataset in COCO format using as_coco and from_coco methods. (https://github.com/roboflow/supervision/pull/150)

```python

import supervision as sv

ds = sv.DetectionDataset.fromcoco( ... imagesdirectorypath='...', ... annotationspath='...' ... )

ds.ascoco( ... imagesdirectorypath='...', ... annotationspath='...' ... ) ```

• Ability to marge multiple sv.DetectionDataset together using merge method. (https://github.com/roboflow/supervision/pull/158)

```python

import supervision as sv

ds1 = sv.DetectionDataset(...) len(ds1) 100 ds_1.classes ['dog', 'person']

ds2 = sv.DetectionDataset(...) len(ds2) 200 ds_2.classes ['cat']

dsmerged = sv.DetectionDataset.merge([ds1, ds2]) len(dsmerged) 300 ds_merged.classes ['cat', 'dog', 'person'] ```

• Additional start and end arguments to sv.get_video_frames_generator allowing to generate frames only for a selected part of the video. (https://github.com/roboflow/supervision/pull/162)

🛠️ Fixed

• Incorrect loading of YOLO dataset class names from data.yaml. (https://github.com/roboflow/supervision/pull/157)

🏆 Contributors

@SkalskiP @hardikdava

- Python
Published by SkalskiP over 2 years ago

supervision - supervision-0.10.0

🚀 Added

• Ability to load and save sv.ClassificationDataset in a folder structure format. (https://github.com/roboflow/supervision/pull/125)

```python

import supervision as sv

cs = sv.ClassificationDataset.fromfolderstructure( ... rootdirectorypath='...' ... )

cs.asfolderstructure( ... rootdirectorypath='...' ... ) ```

• Support for sv.ClassificationDataset.split allowing to divide sv.ClassificationDataset into two parts. (https://github.com/roboflow/supervision/pull/125)

```python

import supervision as sv

cs = sv.ClassificationDataset(...) traincs, testcs = cs.split(splitratio=0.7, randomstate=42, shuffle=True)

len(traincs), len(testcs) (700, 300) ```

• Ability to extract masks from Roboflow API results using sv.Detections.from_roboflow. (https://github.com/roboflow/supervision/pull/110)

• Supervision Quickstart notebook where you can learn more about Detection, Dataset and Video APIs.

🌱 Changed

• sv.get_video_frames_generator documentation to better describe actual behavior. (https://github.com/roboflow/supervision/pull/135)

🏆 Contributors

@capjamesg @dankresio @SkalskiP

- Python
Published by SkalskiP over 2 years ago

supervision - supervision-0.9.0

🚀 Added

• Ability to select sv.Detections by index, list of indexes or slice. Here is an example illustrating the new selection methods. (https://github.com/roboflow/supervision/pull/118)

```python

import supervision as sv

detections = sv.Detections(...) len(detections[0]) 1 len(detections[[0, 1]]) 2 len(detections[0:2]) 2 ```

• Ability to extract masks from YOLOv8 results using sv.Detections.from_yolov8. Here is an example illustrating how to extract boolean masks from the result of the YOLOv8 model inference. (https://github.com/roboflow/supervision/pull/101)

```python

import cv2 from ultralytics import YOLO import supervision as sv

image = cv2.imread(...) image.shape (640, 640, 3)

model = YOLO('yolov8s-seg.pt') result = model(image)[0] detections = sv.Detections.from_yolov8(result) detections.mask.shape (2, 640, 640) ```

• Ability to crop the image using sv.crop. Here is an example showing how to get a separate crop for each detection in sv.Detections. (https://github.com/roboflow/supervision/pull/122)

```python

import cv2 import supervision as sv

image = cv2.imread(...) detections = sv.Detections(...) len(detections) 2 crops = [ ... sv.crop(image=image, xyxy=xyxy) ... for xyxy ... in detections.xyxy ... ] len(crops) 2 ```

• Ability to conveniently save multiple images into directory using sv.ImageSink. An example shows how to save every tenth video frame as a separate image. (https://github.com/roboflow/supervision/pull/120)

```python

import supervision as sv

with sv.ImageSink(targetdirpath='target/directory/path') as sink: ... for image in sv.getvideoframesgenerator(sourcepath='sourcevideo.mp4', stride=10): ... sink.saveimage(image=image) ```

🛠️ Fixed

• Inconvenient handling of sv.PolygonZone coordinates. Now sv.PolygonZone accepts coordinates in the form of [[x1, y1], [x2, y2], ...] that can be both integers and floats. (https://github.com/roboflow/supervision/issues/106)

🏆 Contributors

@SkalskiP @lomnes-atlast-food @hardikdava

- Python
Published by SkalskiP over 2 years ago

supervision - supervision-0.8.0

🚀 Added

• Support for dataset inheritance. The current Dataset got renamed to DetectionDataset. Now DetectionDataset inherits from BaseDataset. This change was made to enforce the future consistency of APIs of different types of computer vision datasets. (https://github.com/roboflow/supervision/pull/100)
• Ability to save datasets in YOLO format using DetectionDataset.as_yolo. (https://github.com/roboflow/supervision/pull/100)

```python

import supervision as sv

ds = sv.DetectionDataset(...) ds.asyolo( ... imagesdirectorypath='...', ... annotationsdirectorypath='...', ... datayaml_path='...' ... ) ```

• Support for DetectionDataset.split allowing to divide DetectionDataset into two parts. (https://github.com/roboflow/supervision/pull/102)

```python

import supervision as sv

ds = sv.DetectionDataset(...) trainds, testds = ds.split(splitratio=0.7, randomstate=42, shuffle=True)

len(trainds), len(testds) (700, 300) ```

🌱 Changed

• Default value of approximation_percentage parameter from 0.75 to 0.0 in DetectionDataset.as_yolo and DetectionDataset.as_pascal_voc. (https://github.com/roboflow/supervision/pull/100)

🏆 Contributors

• @SkalskiP

- Python
Published by SkalskiP almost 3 years ago

supervision - supervision-0.7.0

🚀 Added

• Detections.from_yolo_nas to enable seamless integration with YOLO-NAS model. (https://github.com/roboflow/supervision/pull/91)
• Ability to load datasets in YOLO format using Dataset.from_yolo. (https://github.com/roboflow/supervision/pull/86)
• Detections.merge to merge multiple Detections objects together. (https://github.com/roboflow/supervision/pull/84)

🌱 Changed

• LineZoneAnnotator.annotate to allow for the custom text for the in and out tags. (https://github.com/roboflow/supervision/pull/44)

🛠️ Fixed

• LineZoneAnnotator.annotate does not return annotated frame. (https://github.com/roboflow/supervision/pull/81)

🏆 Contributors

• @SkalskiP
• @iPoe
• @hardikdava

- Python
Published by SkalskiP almost 3 years ago

supervision - supervision-0.6.0

🚀 Added

• Initial Dataset support and ability to save Detections in Pascal VOC XML format. (https://github.com/roboflow/supervision/pull/71)
• New mask_to_polygons, filter_polygons_by_area, polygon_to_xyxy and approximate_polygon utilities. (https://github.com/roboflow/supervision/pull/71)
• Ability to load Pascal VOC XML object detections dataset as Dataset. (https://github.com/roboflow/supervision/pull/72)

🌱 Changed

• order of Detections attributes to make it consistent with order of objects in __iter__ tuple. (https://github.com/roboflow/supervision/pull/70)
• generate_2d_mask to polygon_to_mask. (https://github.com/roboflow/supervision/pull/71)

🏆 Contributors

• @SkalskiP
• @alexandercarruthers

- Python
Published by SkalskiP almost 3 years ago

supervision - supervision-0.5.2

🛠️ Fixed

• Fixed LineZone.trigger function expects 4 values instead of 5 (https://github.com/roboflow/supervision/pull/63)

🏆 Contributors

• @SkalskiP @ChaseDDevelopment

- Python
Published by SkalskiP almost 3 years ago

supervision - supervision-0.5.1

🛠️ Fixed

• Fixed Detections.__getitem__ method did not return mask for selected item.
• Fixed Detections.area crashed for mask detections.

🏆 Contributors

• @SkalskiP

- Python
Published by SkalskiP almost 3 years ago

supervision - supervision-0.5.0

🚀 Added

• Detections.mask to enable segmentation support. (https://github.com/roboflow/supervision/pull/58)
• MaskAnnotator to allow easy Detections.mask annotation. (https://github.com/roboflow/supervision/pull/58)
• Detections.from_sam to enable native Segment Anything Model (SAM) support. (https://github.com/roboflow/supervision/pull/58)

🌱 Changed

• Detections.area behaviour to work not only with boxes but also with masks. (https://github.com/roboflow/supervision/pull/58)

🏆 Contributors

• @SkalskiP

- Python
Published by SkalskiP almost 3 years ago

supervision - supervision-0.4.0

🚀 Added

• Detections.empty to allow easy creation of empty Detections objects. (https://github.com/roboflow/supervision/discussions/48)
• Detections.from_roboflow to allow easy creation of Detections objects from Roboflow API inference results. (https://github.com/roboflow/supervision/pull/56)
• plot_images_grid to allow easy plotting of multiple images on single plot. (https://github.com/roboflow/supervision/pull/56)
• Initial support for Pascal VOC XML format with detections_to_voc_xml method. (https://github.com/roboflow/supervision/pull/56)

🌱 Changed

• show_frame_in_notebook refactored and renamed to plot_image. (https://github.com/roboflow/supervision/pull/56)

🏆 Contributors

• @SkalskiP

- Python
Published by SkalskiP almost 3 years ago

supervision - supervision-0.3.2

🌱 Changed

• Drop requirement for class_id in sv.Detections (https://github.com/roboflow/supervision/pull/50) to make it more flexible

🏆 Contributors

• @SkalskiP

- Python
Published by SkalskiP almost 3 years ago

supervision - supervision-0.3.1

🌱 Changed

• Detections.wth_nms support class agnostic and non-class agnostic case (https://github.com/roboflow/supervision/pull/36)

🛠️ Fixed

• PolygonZone throws an exception when the object touches the bottom edge of the image (https://github.com/roboflow/supervision/issues/41)
• Detections.wth_nms method throws an exception when Detections is empty (https://github.com/roboflow/supervision/issues/42)

🏆 Contributors

• @SkalskiP

- Python
Published by SkalskiP almost 3 years ago

supervision - supervision-0.3.0

🚀 Added

New methods in sv.Detections API: - from_transformers - convert Object Detection 🤗 Transformer result into sv.Detections - from_detectron2 - convert Detectron2 result into sv.Detections - from_coco_annotations - convert COCO annotation into sv.Detections - area - dynamically calculated property storing bbox area - with_nms - initial implementation (only class agnostic) of sv.Detections NMS

🌱 Changed

• Make sv.Detections.confidence field Optional.

🏆 Contributors

• @SkalskiP

- Python
Published by SkalskiP almost 3 years ago

supervision - supervision-0.2.0

🔪 Killer features

• Support for PolygonZone and PolygonZoneAnnotator 🔥

👉 Code example

```python import numpy as np import supervision as sv from ultralytics import YOLO # initiate polygon zone polygon = np.array([ [1900, 1250], [2350, 1250], [3500, 2160], [1250, 2160] ]) video_info = sv.VideoInfo.from_video_path(MALL_VIDEO_PATH) zone = sv.PolygonZone(polygon=polygon, frame_resolution_wh=video_info.resolution_wh) # initiate annotators box_annotator = sv.BoxAnnotator(thickness=4, text_thickness=4, text_scale=2) zone_annotator = sv.PolygonZoneAnnotator(zone=zone, color=sv.Color.white(), thickness=6, text_thickness=6, text_scale=4) # extract video frame generator = sv.get_video_frames_generator(MALL_VIDEO_PATH) iterator = iter(generator) frame = next(iterator) # detect model = YOLO('yolov8s.pt') results = model(frame, imgsz=1280)[0] detections = sv.Detections.from_yolov8(results) detections = detections[detections.class_id == 0] zone.trigger(detections=detections) # annotate box_annotator = sv.BoxAnnotator(thickness=4, text_thickness=4, text_scale=2) labels = [f"{model.names[class_id]} {confidence:0.2f}" for _, confidence, class_id, _ in detections] frame = box_annotator.annotate(scene=frame, detections=detections, labels=labels) frame = zone_annotator.annotate(scene=frame) ```

• Advanced vs.Detections filtering with pandas-like API.

python detections = detections[(detections.class_id == 0) & (detections.confidence > 0.5)]

• Improved integration with YOLOv5 and YOLOv8 models.

```python import torch import supervision as sv

model = torch.hub.load('ultralytics/yolov5', 'yolov5x6') results = model(frame, size=1280) detections = sv.Detections.from_yolov5(results) ```

```python from ultralytics import YOLO import supervision as sv

model = YOLO('yolov8s.pt') results = model(frame, imgsz=1280)[0] detections = sv.Detections.from_yolov8(results) ```

🚀 Added

• supervision.get_polygon_center function - takes in a polygon as a 2-dimensional numpy.ndarray and returns the center of the polygon as a Point object
• supervision.draw_polygon function - draw a polygon on a scene
• supervision.draw_text function - draw a text on a scene
• supervision.ColorPalette.default() - class method - to generate default ColorPalette
• supervision.generate_2d_mask function - generate a 2D mask from a polygon
• supervision.PolygonZone class - to define polygon zones and validate if supervision.Detections are in the zone
• supervision.PolygonZoneAnnotator class - to draw supervision.PolygonZone on scene

🌱 Changed

• VideoInfo API - change the property name resolution -> resolution_wh to make it more descriptive; convert VideoInfo to dataclass
• process_frame API - change argument name frame -> scene to make it consistent with other classes and methods
• LineCounter API - rename class LineCounter -> LineZone to make it consistent with PolygonZone
• LineCounterAnnotator API - rename class LineCounterAnnotator -> LineZoneAnnotator

🏆 Contributors

• @SkalskiP
• @capjamesg

- Python
Published by capjamesg about 3 years ago

supervision - supervision-0.1.0

🚀 Added

• ⓒ Add project license
• 🎨 DEFAULT_COLOR_PALETTE, Color, and ColorPalette classes
• 📐 initial implementation of Point, Vector, and Rect classes
• 🎬 VideoInfo and VideoSink classes as well as get_video_frames_generator -📓 show_frame_in_notebook util
• 🖌️ draw_line, draw_rectangle, draw_filled_rectangle utils added
• 📦 Initial version Detections and BoxAnnotator added
• 🧮 initial implementation of LineCounter and LineCounterAnnotator classes

🏆 Contributors

@SkalskiP

- Python
Published by SkalskiP about 3 years ago