# PaddlePaddle/PaddleDetection

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

Repository: https://github.com/PaddlePaddle/PaddleDetection
Canonical: https://ross.abutalabs.com/products/paddledetection
Language: Python
License: Apache-2.0
License Family: permissive
Topics: object-detection, instance-segmentation, faster-rcnn, mask-rcnn, yolov3, blazeface, face-detection, fcos, pp-yolo, fairmot, multi-object-tracking, deepsort, picodet, human-activity-recognition, human-pose-estimation, yolov5, yolox, yolov7, detr, rt-detr
Last push: 2026-05-28T07:28:31+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 84, release rhythm 43, longevity 100
- inputs: {"age_days": 2504, "days_push": 97, "days_rel": 167, "gap_med": 248.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 14389, forks 3024 (observed 2026-08-28T04:11:06.910138+00:00)

## What it is
PaddleDetection is an object detection toolkit built on the PaddlePaddle deep learning framework. It provides implementations of detection, instance segmentation, multi-object tracking, and real-time multi-person keypoint detection models.

## Use cases
- detect objects in images
- run instance segmentation on photos
- track multiple objects across video frames
- estimate human pose and keypoints in real time
- train a custom YOLO or Faster R-CNN detector
- deploy a real-time face detection model

## When to choose
- you want a comprehensive, maintained toolkit for detection, segmentation, tracking, and pose estimation
- your stack already uses PaddlePaddle
- you need production-ready pretrained models like PP-YOLO, PicoDet, or RT-DETR

## When to avoid
- you are committed to PyTorch or TensorFlow ecosystems
- you need a lightweight single-model library rather than a full toolkit
- you require models not covered by the detection/tracking/pose scope

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, machine-learning, deep-learning, image-processing
- platform: python
- tags: object-detection, instance-segmentation, multi-object-tracking, pose-estimation, yolo, paddlepaddle, keypoint-detection, linux, gpu

## Member repositories
- PaddlePaddle/PaddleDetection (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:06.910138+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:12:36.570871+00:00, confidence not recorded.
  - readme: https://github.com/PaddlePaddle/PaddleDetection (fetched 2026-08-28T04:11:06.910138+00:00, sha a1fe4b37313e)
- Data as of 2026-08-30T08:39:29.467469+00:00.