KaiyangZhou/deep-person-reid
Torchreid: Deep learning person re-identification in PyTorch.
This tool helps security analysts and surveillance operators track specific individuals across different camera feeds or video clips. You provide it with images or video of people, and it identifies and matches the same person even if their appearance or camera angle changes. It's designed for professionals managing large-scale surveillance or forensics tasks.
4,774 stars.
Use this if you need to reliably identify and track individuals across multiple non-overlapping camera views or video sources.
Not ideal if you're looking for a simple face recognition system or a tool to identify people from a database of known individuals.
Stars
4,774
Forks
1,201
Language
Python
License
MIT
Category
Last pushed
Jan 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/KaiyangZhou/deep-person-reid"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
Cysu/open-reid
Open source person re-identification library in python
alexppppp/keypoint_rcnn_training_pytorch
How to Train a Custom Keypoint Detection Model with PyTorch (Article on Medium)
mangye16/ReID-Survey
Deep Learning for Person Re-identification: A Survey and Outlook
jian667/face-dataset
Face related datasets
tlpss/keypoint-detection
2D keypoint detection with Pytorch Lightning and wandb