What it does
Torchreid is a code library for person re-identification. This is the task of teaching a computer to tell whether people in photos or video clips taken by different cameras are the same person. It is written in PyTorch, a popular toolkit for building AI.
It helps researchers prepare common datasets, train models on one or more of them, and test how well the models work. It includes ready-made versions of several published models, including OSNet from the makers' own research, plus pretrained models you can download.
It also offers tools for viewing results and for exporting trained models to other formats such as ONNX, OpenVINO and TFLite, so they can run in other software.
Who it's for
Researchers and developers working on computer vision who want to train or compare person re-identification models.
Can I use it without coding?
Developers only. Using it means installing Python tools and writing or running Python code to train and test models. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Computer
- Works best on a powerful computer or one with a graphics card (GPU)
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- Plain-AyI is an independent guide and doesn't host or review the software it lists. Please check each project's official page before installing.
- License (MIT): Very permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- Torchreid: A Library for Deep Learning Person Re-Identification in PytorchResearch paper · Oct 2019
- Learning Generalisable Omni-Scale Representations for Person Re-IdentificationResearch paper · Oct 2019
- Omni-Scale Feature Learning for Person Re-IdentificationResearch paper · May 2019