PaddlePaddle/PaddleDetection

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

67
/ 100
Established

Based on the README, here's a technical summary: Built on PaddlePaddle's modular architecture, PaddleDetection provides specialized model variants including PP-YOLOE for general detection, PP-PicoDet for ultra-lightweight real-time inference, and domain-specific tools like PP-Human and PP-Vehicle for end-to-end pedestrian and vehicle analysis pipelines. The framework integrates with PaddleX, a low-code development platform offering 55+ unified models across detection, segmentation, and OCR through a single Python API, with seamless hardware switching for NVIDIA GPUs, Kunlun, Ascend, and other accelerators.

14,116 stars. Actively maintained with 2 commits in the last 30 days.

No Package No Dependents
Maintenance 16 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

14,116

Forks

3,014

Language

Python

License

Apache-2.0

Last pushed

Mar 16, 2026

Commits (30d)

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/PaddlePaddle/PaddleDetection"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.