#131131st of 168 in ML frameworks and libraries
object-detection-metrics
Python functions for computing object detection metrics like PASCAL VOC AP
- Stars
- 5.1k
- License
- MIT
- Last commit
- Oct 2026
- Language
- Python
5,075 on 20 Apr 20265,101 on 9 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Reference implementation of object detection evaluation metrics: IOU, precision x recall curves, and average precision with all-point or 11-point interpolation. It takes ground truth and detected bounding boxes in a simple format, without conversion to XML or JSON. The README says results match the official competition implementations, and that a newer tool (review_object_detection_metrics) supersedes this one.
Who it is for: Researchers evaluating object detectors against PASCAL VOC-style metrics
Strengths
- Implements PASCAL VOC AP with both all-point and 11-point interpolation
- Simple box input; no XML or JSON conversion of detections required
- README explains the metrics with a worked numeric example
- Backed by a peer-reviewed paper (Electronics, 2021) for citation
Weaknesses
- Superseded by review_object_detection_metrics, per the README's own notice
- Fewer metrics than the newer tool, which adds all COCO metrics
- No UI and no STT-AP video metric; both are only in the newer tool
- No tagged releases
What it needs
- no GPU
Quick answers
Is object-detection-metrics open source?
Yes. Its code is on GitHub under the MIT license.
Does object-detection-metrics need a GPU?
No, it runs without one.
Also in ML frameworks and libraries
See all 168| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |