Skip to content
CAI
Software that uses CAICheck a score

roboflow/supervision

66.9

Adequate · 14 November 2026

52.5k

lines of production code

Python

primary language

7

measurements over time

CAI band scale
CAI trend line
CAI lens gauges

What this system is

Features

Add built-in asset download and verification

The \src/supervision/assets\ module now provides a \download\_assets\ function and \ImageAssets\/\VideoAssets\ enums, allowing users to programmatically download example media files (such as \vehicles.mp4\ or \people-walking.jpg\) directly from Roboflow's media server. The implementation includes MD5-based integrity checks to detect and automatically re-download corrupted files, ensuring reliable access to sample data for testing and demos.

src/supervision/assets · high confidence

Add heatmap and tracking example with RF-DETR and YOLOv8 support

The \examples/heatmap\_and\_track\ directory now includes a new demo that performs crowd analysis using object detection and ByteTrack multi-object tracking. Users can run the example with the recommended RF-DETR model (\rfdetr\_example.py\) or with YOLOv8 via Ultralytics (\script.py\), both of which generate heatmaps and track person IDs in video footage. The example provides CLI arguments for configuring detection thresholds, heatmap appearance, and tracking parameters, and includes a README with installation and usage instructions.

_examples/heatmap\_and\track · high confidence

Add polygon center calculation utility

A new \get\_polygon\_center\ function has been added to the \supervision.geometry.utils\ module, allowing users to calculate the centroid of a polygon defined by a NumPy array of vertices. The implementation uses a signed-area weighted average of triangle centroids to determine the center, handling edge cases such as empty polygons or zero-area figures.

src/supervision/geometry · high confidence

Add support for CreateML and LabelMe dataset formats

The dataset loader now supports CreateML and LabelMe annotation formats in addition to the existing COCO, Pascal VOC, and YOLO formats. CreateML annotations are loaded from a single JSON file containing bounding boxes defined by center coordinates, while LabelMe annotations are loaded from per-image JSON files supporting both rectangle and polygon shapes, with optional mask generation. Both formats include path validation to prevent directory traversal and handle class mapping consistently with other supported formats.

src/supervision/dataset/formats · high confidence

Initial repository scaffolding and development tooling

The repository has been initialized with the core structure for the \supervision\ library, including the \src/supervision/\ package source, \tests/\ directory, and a \demo.ipynb\ quickstart notebook. Development workflow is established via a comprehensive \.pre-commit-config.yaml\ enforcing code quality with \ruff\, \mypy\, \docformatter\, and \mdformat\, alongside \uv.lock\ for dependency management requiring Python 3.10+. Documentation is configured using \mkdocs.yml\ with Material theme, \mkdocstrings\, and \mike\ for versioning, while CI coverage is set up via \.codecov.yml\ and multi-version testing via \tox.ini\. Project metadata and guidelines are provided through \LICENSE.md\, \CITATION.cff\, \AGENTS.md\, and \CLAUDE.md\.

(repo-wide) · high confidence

Introduce depth map visualization and file reading capabilities

Added the \DepthAnnotator\ and \DepthColormap\ components to visualize depth maps with configurable color tables (Turbo, Viridis, Cividis, Inferno, Magma, Grayscale), and introduced readers to load depth data from 16-bit grayscale PNGs and PFM files. Also in this area: Improved documentation cross-references and CSV array serialization.

src/supervision/depth · high confidence

Introduce keypoint annotation and skeleton support

Added a new keypoint annotation module that provides annotators for drawing skeleton vertices and edges on images. The \VertexAnnotator\ draws circles at keypoint locations, while the \EdgeAnnotator\ connects them with lines, supporting both single-skeleton and multi-skeleton (class-specific) configurations. The module includes built-in skeleton definitions for COCO, Hand, GHUM, and FaceMesh, and handles non-finite coordinates and visibility masks to prevent rendering errors.

_src/supervision/key\points · high confidence

Introduction of the draw module with image annotation utilities

The \src/supervision/draw\ package has been introduced, providing a new set of tools for drawing geometric shapes on images. This includes functions for drawing lines, rectangles, filled rectangles (with opacity support), and rounded rectangles via \draw/utils.py\, along with a base module defining a consistent \ImageType\ type variable for numpy arrays and PIL images. The implementation leverages OpenCV for rendering and includes doctests for documentation.

src/supervision/draw · high confidence

Introduction of the supervision.metrics package

The \src/supervision/metrics\ module is now available, providing a comprehensive set of tools for evaluating detection and pose estimation models. Users can now import and use classes such as \MeanAveragePrecision\, \KeyPointMeanAveragePrecision\, \F1Score\, \Precision\, and \Recall\ to calculate standard performance metrics. The package also includes result classes (e.g., \MeanAveragePrecisionResult\) and utility functions for aggregating and plotting metric results, as well as categorizing object sizes.

src/supervision/metrics · high confidence

New CompactMask example demonstrating memory-efficient RLE mask storage

Added an example in \examples/compact\_mask\ that benchmarks \CompactMask\, a new mask representation replacing dense \(N, H, W)\ boolean arrays with crop-scoped Run-Length Encoding (RLE). The included \README.md\ details the memory and performance benefits for high-density scenes, while \benchmark\_nmm.py\ provides reproducible measurements for Non-Maximum Suppression (NMM) operations using this compact format.

_examples/compact\mask · high confidence

New CompactMask storage and geometry-aware detection dispatch

The detection module now includes a new CompactMask class that stores instance segmentation masks as run-length encoded (RLE) bounding-box crops, significantly reducing memory usage for large images with many sparse masks. Additionally, a new geometry-aware dispatch system centralizes detection area and IoU calculations, automatically selecting the most precise geometry available (masks, oriented boxes, or axis-aligned boxes) for accurate measurements.

src/supervision/detection · high confidence

New count-people-in-zone example with multi-model support and CLI arguments

The \examples/count\_people\_in\_zone\ directory now provides a complete, runnable demo for counting objects within configurable polygonal zones in video. It includes three distinct entry points—\rfdetr\_example.py\, \ultralytics\_example.py\, and \inference\_example.py\—allowing users to choose between RF-DETR, YOLO (Ultralytics), or Roboflow Inference models. The scripts have been updated to use \sv.calculate\_optimal\_line\_thickness\ and \sv.calculate\_optimal\_text\_scale\ for better annotation scaling, and they expose CLI arguments (via \jsonargparse\) for \confidence\_threshold\ and \iou\_threshold\, enabling users to tune detection filtering and non-maximum suppression directly from the command line.

_examples/count\_people\_in\zone · high confidence

New depth, classification, and compact mask capabilities with updated dataset handling

This release introduces several new capabilities and structural changes. Users can now work with depth data via the new \DepthMap\, \DepthAnnotator\, and \DepthCamera\ classes, which support metric, disparity, and relative inverse depth scales, along with clip-wide color range management. A new \Classifications\ dataclass has been added to standardize classification inference results from CLIP, Ultralytics, and timm models. For segmentation, a \CompactMask\ implementation provides memory-efficient RLE-based mask storage, demonstrated by new benchmark scripts in the \examples/compact\_mask\ directory. Additionally, the \DetectionDataset\ now supports lazy image loading via a list of paths (replacing the deprecated dictionary-based in-memory approach) and includes new format support for LabelMe and CreateML.

supervision · high confidence

New detection export and processing utilities

This release introduces a suite of new tools in the \supervision.detection.tools\ module to improve detection data handling. \CSVSink\ and \JSONSink\ provide structured serialization of detection results to CSV and JSON files, with support for per-row custom data and proper handling of NumPy types. \InferenceSlicer\ enables tiled inference on large images, supporting batched callbacks, multi-threading, and memory-efficient \CompactMask\ storage. \PolygonZone\ and \PolygonZoneAnnotator\ allow for zone-based detection counting with configurable anchor logic. \DetectionsSmoother\ stabilizes tracking results over time, while \transformers.py\ adds robust processing for Hugging Face Transformers v4 and v5 detection and segmentation outputs. Also in this area: 5 commits (2 fixes) modifying src/supervision/detection; 3 commits (3 fixes) fixing src/supervision/detection; Improved documentation cross-references and CSV array serialization; Fix Transformers semantic output handling and image crop bounds; Fixes for YOLO/Pascal VOC mask handling, YOLO label parsing, and smoother track updates.

src/supervision/detection/tools · medium confidence · unverified

New metrics aggregation and object-size utility functions

The \src/supervision/metrics/utils\ module now provides utilities for combining and analyzing metric results. Users can aggregate multiple \MetricResult\ objects into a single pandas DataFrame or generate a grouped bar chart comparing models, with an option to include small/medium/large object-size categories. Additionally, the module introduces \ObjectSizeCategory\ and helper functions to classify detections by area (using thresholds of 32² and 96² pixels) for bounding boxes, masks, and oriented bounding boxes, supporting size-bucketed metric analysis.

src/supervision/metrics/utils · high confidence

New speed estimation example with multi-model support

The \examples/speed\_estimation\ directory now provides a complete, runnable demo for estimating vehicle speed from video using object detection and tracking. It includes dedicated scripts for four backends: RF-DETR (recommended), Ultralytics (YOLOv8/YOLO11), Roboflow Inference, and a legacy YOLO-NAS reference. The example uses ByteTrack for multi-object tracking, \PolygonZone\ and \ViewTransformer\ for perspective-corrected ground-plane coordinate mapping, and Supervision annotators (\BoxAnnotator\, \LabelAnnotator\, \TraceAnnotator\) to display tracked IDs and calculated speeds (km/h) in real-time or saved output videos. A \video\_downloader.py\ script and \.gitignore\ are included to simplify setup, and the README documents configuration of SOURCE/TARGET polygons, CLI arguments, and licensing for each model variant.

_examples/speed\estimation · high confidence

New time-in-zone example with RF-DETR and Ultralytics support

The time\_in\_zone example has been updated to include new scripts for running object detection and dwell-time analysis using RF-DETR and Ultralytics YOLO models, in addition to the existing Roboflow Inference support. The example now provides separate entry points for processing video files and RTSP streams, with variants that use either a naive frame-polling approach or the InferencePipeline for background processing. Users can now configure model sizes (nano, small, medium, base, large), select computation devices (cpu, mps, cuda), and adjust input resolutions for RF-DETR, while all scripts support filtering by class, confidence, and IoU thresholds, and display real-time tracking IDs with elapsed time in the defined zones.

_examples/time\_in\zone · high confidence

New tracking examples for RF-DETR, Ultralytics, and Roboflow Inference

The \examples/tracking\ directory now includes three new scripts (\rfdetr\_example.py\, \ultralytics\_example.py\, and \inference\_example.py\) that demonstrate video processing with object detection and tracking using RF-DETR, YOLOv8 (via Ultralytics), and Roboflow Inference respectively. Each example uses the \ByteTrackTracker\ to assign persistent IDs to detected objects and \supervision\ annotators to visualize bounding boxes and labels on the output video. The examples support configurable confidence and IoU thresholds, accept source video and target output paths via CLI arguments (parsed using \jsonargparse\), and include a \README.md\ with installation and usage instructions.

examples/tracking · high confidence

New traffic flow analysis example with zone-based counting

A new \examples/traffic\_analysis\ directory has been added, providing a complete demo for traffic flow analysis using object detection and ByteTrack multi-object tracking. The example includes three variants—RF-DETR, Ultralytics (YOLOv8), and Roboflow Inference—each capable of counting vehicles as they transition between defined entry and exit polygon zones. It leverages the \supervision\ library for zone triggering, annotation (boxes, labels, traces), and video I/O, and includes a setup script to download sample data and a README detailing installation and CLI arguments.

_examples/traffic\analysis · high confidence

New utility modules for time-in-zone demo

Added new utility files (\general.py\, \timers.py\) to the \examples/time\_in\_zone/utils\ package to support the time-in-zone and dwell-time demonstration. \general.py\ provides helper functions for loading polygon zone configurations from JSON files, checking array membership, and generating frames from RTSP video streams. \timers.py\ introduces two timer classes, \FPSBasedTimer\ and \ClockBasedTimer\, which calculate the duration objects remain detected in a zone based on either frame counts or system clock time.

_examples/time\_in\zone/utils · high confidence

New utility scripts for the Time in Zone demo

The Time in Zone example now includes three new helper scripts to streamline setup and annotation workflows. Users can download source videos directly from YouTube using \download\_from\_youtube.py\, interactively draw and save polygon zone configurations on images or video frames via \draw\_zones.py\, and stream local video files over RTSP using \stream\_from\_file.py\ (which manages an RTSP server via Docker). These tools simplify the process of preparing data and defining detection zones for the demo.

_examples/time\_in\zone/scripts · high confidence

OpenCV dependency removed with pure NumPy/Pillow/PyAV fallbacks

The \src/supervision/\_cv2\ module now provides a comprehensive fallback backend that replaces the \opencv-python\ dependency. If OpenCV is not installed, the library automatically uses a pure NumPy, Pillow, and PyAV implementation for image I/O, color conversion, drawing, geometry, and video operations. This allows the library to function without OpenCV, though some operations may be slower or behave slightly differently. Also in this area: 2 commits (2 fixes) fixing src/supervision/\_cv2.

_src/supervision/\cv2 · medium confidence · unverified

Supervision package initialization and configuration constants

This change establishes the \src/supervision\ package structure by creating the main \\_\init\\_.py\ entry point, which exposes a comprehensive set of public API components including annotators, detection utilities, dataset classes, and key-point tools. It also introduces \config.py\ to define standard metadata field names (such as \CLASS\_NAME\_DATA\_FIELD\, \AREA\_DATA\_FIELD\, and \ORIENTED\_BOX\_COORDINATES\) used across the library for detection data handling, alongside a \py.typed\ marker file to enable static type checking for the package.

src/supervision · high confidence

Removals

Removal of core source files

The \src/\_\init\\_.py\ and \src/hello.py\ files have been deleted from the project. This removes the package version definition (previously 0.0.5) and the \hello()\ function that returned the string "World", effectively stripping the main source code from this location.

src · high confidence

Architecture

Reorganized detection utilities into a dedicated utils package

The detection utility functions have been reorganized from the top-level detection module into a new \src/supervision/detection/utils\ package. This change introduces a modular structure with dedicated files for specific concerns: \boxes.py\ for bounding box operations (clipping, padding, normalization), \converters.py\ for coordinate format conversions (xyxy, xywh, xcycwh) and polygon-to-mask generation, \masks.py\ for mask manipulation and centroid calculation, \iou\_and\_nms.py\ for overlap metrics and non-maximum suppression/merging, \polygons.py\ for polygon approximation and area filtering, \matching.py\ for public detection matching primitives, and \vlms.py\ for string matching utilities. Type definitions and internal helpers have also been moved into \\_typing.py\ and \internal.py\ respectively, improving code organization and maintainability without altering the public API surface.

src/supervision/detection/utils · high confidence

Behavioural changes

2 commits (0 fixes) modifying examples/depth\_showcase

A change to existing behaviour in examples/depth\_showcase — 2 commits, 2 files: “docs(examples): add depth showcase example (\#2804)”; “docs: update Depth example (\#2818)” (refs \#2804, \#2818).

_examples/depth\showcase · medium confidence · unverified

Annotators refactored with base class, dynamic sizing, and memory-efficient masks

The annotation system has been restructured to improve performance and usability. A new \BaseAnnotator\ class introduces a \requires\_mask\ attribute, allowing integrations to check for mask availability before materializing expensive payloads. Pixel and kernel sizes are now dynamic, adapting to the scene resolution. Memory usage is reduced through the introduction of \CompactMask\ for efficient crop-RLE mask storage and optimized mask blending. Additionally, several bugs were fixed: \CropAnnotator\ and \BackgroundOverlayAnnotator\ now correctly clip boxes to the scene, \HeatMapAnnotator\ avoids divide-by-zero errors on empty detections, and \TraceAnnotator\ handles stationary tracker IDs and empty frames more robustly.

src/supervision/annotators · high confidence

Dataset export safety and image handling improvements

The dataset module now prevents export failures caused by filename collisions by rejecting exports when multiple images share the same basename, and it ensures that EXIF-oriented images are resized correctly to match how they are loaded. Additionally, dataset load and save operations now support a progress indicator via the show\_progress parameter, and images are preserved in their original folders during export rather than being moved.

src/supervision/dataset · high confidence

New centralized validation module for detection inputs

A new \src/supervision/validators\ module has been introduced to centralize input validation for detection objects. This module provides internal helper functions (prefixed with \\validate\\) that enforce strict shape and type constraints for bounding boxes (\xyxy\), masks, class IDs, confidence scores, keypoint confidence, and tracker IDs. Public-facing wrapper functions (e.g., \validate\_xyxy\) are marked as deprecated and will be removed in version 0.32.0, signaling a shift toward using the new internal validation logic directly within the library's core components.

src/supervision/validators · high confidence

Refactored utility modules and introduced image URL loading and Tkinter-based preview window

The \src/supervision/utils\ package has been reorganized into dedicated modules (\conversion.py\, \file.py\, \image.py\, \image\_window.py\, \internal.py\, \iterables.py\, \logger.py\, \notebook.py\, \video.py\) to improve code structure and maintainability. A new \load\_image\_from\_url\ function allows users to fetch and cache images directly from HTTP(S) sources, while the new \ImageWindow\ class provides a desktop preview window using Tkinter and Pillow, enabling visual debugging without requiring a full OpenCV GUI backend. Image conversion utilities have been updated to robustly handle all Pillow modes (including high-bit-depth and palette images) by converting them to standard 8-bit BGR or grayscale layouts, and \VideoInfo.fps\ now returns a float to preserve sub-frame-rate precision.

src/supervision/utils · high confidence

Test coverage

60 commits adding/updating tests in tests/cv2; 8 commits adding/updating tests in tests/metrics/utils; Added comprehensive test coverage for dataset operations; Added comprehensive test coverage for detection module; Added comprehensive test coverage for detection tools; Added comprehensive test suite for annotators; Added comprehensive test suite for utility modules; Added test coverage for depth map core logic, annotators, and colormaps; Added test coverage for geometry core and utility functions; Added test infrastructure and coverage for validation deprecations; Added tests for asset download and listing functionality; Added tests for classification core functionality; Added tests for drawing utilities and color handling; Comprehensive test coverage for dataset format loaders and exporters; Comprehensive test coverage for detection utility functions; Expanded test coverage for metrics module; Initial test coverage for key points and annotators; Removal of hello module test suite.

Dependencies

Supervision 0.31.0.dev0 release with Python 3.10+ requirement and new example requirements

The Supervision package has been updated to version 0.31.0.dev0, raising the minimum supported Python version to 3.10 (supporting up to 3.14). The core dependencies now include av\>=14.2, defusedxml\>=0.7.1, and pydeprecate\>=0.9,\<0.13, while maintaining existing requirements for matplotlib, numpy, pillow, pyyaml, requests, scipy, and tqdm. New optional dependency groups have been added for geotiff (rasterio) and metrics (pandas). Additionally, dedicated requirements.txt files have been introduced for all example scripts (compact\_mask, count\_people\_in\_zone, heatmap\_and\_track, speed\_estimation, time\_in\_zone, tracking, traffic\_analysis), specifying their specific dependencies such as inference, rfdetr, ultralytics, and trackers.

(dependencies) · high confidence

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

How this codebase got here

This is the PUBLIC form of this artifact. Findings are listed in full, but the details of SECURITY findings — which rule fired, in which file, on which line, and how to fix it — are deliberately withheld, and any secret-scanner results are excluded entirely. Where detail is absent here it was REMOVED FOR PUBLICATION; it is not missing from the analysis. The complete artifact is available from the repository owner.

Score

  • CAI 64 → 67 (+2.4)
  • Rubric changed (rubric-2026.10.5 → rubric-2026.11.4) — scores are not directly comparable.

Lenses

  • Code Health 71 → 69 (-1.7)
  • Architecture 86 → 100 (+14.4)
  • Maturity 54 → 58 (+3.6)
  • Readiness 69 → 69 (+0.0)
  • Security 82 → 92 (+9.8)
  • Performance 89 → 89 (+0.0)

Resolved (50)

  • Documentation: no project overview (README.md)
  • Duplicated block (10 lines × 2) (src/supervision/dataset/formats/coco.py)
  • Duplicated block (10 lines × 2) (src/supervision/detection/utils/masks.py)
  • Duplicated block (10–11 lines × 2) (src/supervision/detection/tools/inference_slicer.py)
  • Duplicated block (12 lines × 2) (src/supervision/metrics/mean_average_precision.py)
  • Duplicated block (13–14 lines × 2) (src/supervision/dataset/formats/coco.py)
  • Duplicated block (16 lines × 2) (src/supervision/metrics/mean_average_precision.py)
  • Duplicated block (18 lines × 2) (examples/time_in_zone/inference_stream_example.py)
  • Duplicated block (18 lines × 2) (src/supervision/metrics/_confusion_matrix_metric.py)
  • Duplicated block (5 lines × 2) (src/supervision/annotators/utils.py)
  • Edited copy of a member (10 corresponding lines) (src/supervision/metrics/_confusion_matrix_metric.py)
  • Edited copy of a member (24 corresponding lines) (src/supervision/dataset/formats/coco.py)
  • Edited copy of a member (26 corresponding lines) (src/supervision/detection/utils/iou_and_nms.py)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • High: security finding (details withheld)
  • …and 30 more

New (92)

  • Detections.remap_classes (cognitive 16) (src/supervision/detection/core.py)
  • Duplicated block (10 lines × 2) (src/supervision/detection/utils/masks.py)
  • Duplicated block (10 lines × 2) (src/supervision/metrics/_confusion_matrix_metric.py)
  • Duplicated block (11 lines × 2) (examples/time_in_zone/inference_file_example.py)
  • Duplicated block (12–14 lines × 2) (src/supervision/detection/tools/inference_slicer.py)
  • Duplicated block (13–14 lines × 2) (src/supervision/dataset/core.py)
  • Duplicated block (15–17 lines × 2) (src/supervision/metrics/utils/object_size.py)
  • Duplicated block (18 lines × 2) (examples/time_in_zone/inference_file_example.py)
  • Duplicated block (5 lines × 2) (src/supervision/_cv2/_drawing.py)
  • Duplicated block (5 lines × 2) (src/supervision/metrics/utils/object_size.py)
  • Duplicated block (7 lines × 2) (src/supervision/key_points/core.py)
  • Duplicated block (8–10 lines × 2) (examples/time_in_zone/inference_file_example.py)
  • Duplicated block (9 lines × 2) (src/supervision/annotators/utils.py)
  • Duplicated block (9 lines × 3) (src/supervision/dataset/formats/pascal_voc.py)
  • Edited copies of one member (3 members, 16+ corresponding lines) (src/supervision/metrics/f1_score.py)
  • Edited copies of one member (3 members, 2+ corresponding lines) (examples/traffic_analysis/inference_example.py)
  • Edited copies of one member (3 members, 20+ corresponding lines) (examples/traffic_analysis/inference_example.py)
  • Edited copies of one member (3 members, 34+ corresponding lines) (examples/tracking/inference_example.py)
  • Edited copies of one member (3 members, 48+ corresponding lines) (examples/count_people_in_zone/inference_example.py)
  • Edited copies of one member (4 members, 3+ corresponding lines) (examples/speed_estimation/inference_example.py)
  • …and 72 more

Changes since last survey

  • 138 commits — 57 feature/other, 81 fixes

By area

  • docs/changelog.md — 71 commits
  • src/supervision — 24 commits
  • (root) — 16 commits
  • tests/metrics — 6 commits
  • tests/detection — 4 commits
  • .github/workflows — 3 commits
  • tests/utils — 3 commits
  • examples/depth_showcase — 2 commits
  • tests/annotators — 2 commits
  • tests/dataset — 2 commits
  • .github/CONTRIBUTING.md — 1 commit
  • .github/_tests — 1 commit
  • docs/how_to — 1 commit
  • docs/notebooks — 1 commit
  • examples/time_in_zone — 1 commit

Notable commits

  • fix: fix(annotators): accept short hex colors (#2801)
  • fix: fix(annotators): draw background overlays on grayscale scenes (#2832)
  • fix: fix(annotators): draw comparisons on grayscale scenes (#2803)
  • fix: fix(annotators): draw falsy non-string labels such as 0 as text (#2892)
  • fix: fix(annotators): draw heat maps on grayscale scenes (#2872)
  • fix: fix(annotators): draw rich labels on grayscale scenes (#2916)
  • fix: fix(annotators): keep labels wider than the frame at its left edge (#2940)
  • fix: fix(ci): restore pull-requests write on labeler (#2981)
  • fix: fix(color): round matplotlib palette colors like to_hex (#2903)
  • fix: fix(compact_mask): make np.sum work on CompactMask (#2880)
  • fix: fix(converters): prevent integer overflow in xyxy_to_xywh (#2951)
  • fix: fix(csv): preserve block exceptions during sink cleanup (#2869)
  • fix: fix(csv): reject extra fields that shadow built-in columns (#2934)
  • fix: fix(cv2): accept BGRA and (H, W, 1) gray in the cvtColor fallback like OpenCV (#2866)
  • fix: fix(cv2): blend addWeighted in float32 like OpenCV (#2836)
  • fix: fix(cv2): blur 16-bit images with OpenCV's exact sums and float32 scaling (#2875)
  • fix: fix(cv2): blur 8-bit images with OpenCV's integer rounding (#2811)
  • fix: fix(cv2): convert HSV to BGR with OpenCV's float32 arithmetic (#2904)
  • fix: fix(cv2): convert uint16 images to gray with OpenCV's fixed-point weights (#2855)
  • fix: fix(cv2): draw thin lines and circles like OpenCV without OpenCV (#2808)
  • …and 118 more

Architecture

  • Unchanged — 0 containers · 1 contexts · 0 edges

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

Survey your own repository

roboflow/supervision was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.

About this page

  • The score is its most recent published measurement, taken on 14 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
  • Measured at commit 5f9e21ef2d186da02a7fe65b20488337c04370b1 — the exact code this score is about.
  • Scored under rubric-2026.11.4 — the same rubric and the same method as every other entry in this index.
  • Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.65+preprod-36d4cd83012f.