FastReID is a research platform that implements state-of-the-art re-identification algorithms. It is a groud-up rewrite of the previous verson, reid strong baseline.
- Remove ignite(a high-level library) dependency and powered by PyTorch.
- Includes more features such as circle loss, visualizing ranklist and label, SoTA results on intra-domain, cross-domain and partial reid, testing on multi-datasets at the same time, etc.
- Can be used as a library to support different projects on top of it. We'll open source more research projects in this way.
- It trains much faster.
See our zhihu blog to learn more about fastreid.
See INSTALL.md.
The designed architecture follows this guide PyTorch-Project-Template, you can check each folder's purpose by yourself.
See GETTING_STARTED.md.
Learn more at out documentation. And see projects/ for some projects that are build on top of fastreid.
We provide a large set of baseline results and trained models available for download in the Fastreid Model Zoo.
Fastreid is released under the Apache 2.0 license.