fast-reid/README.md

# FastReID

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](https://github.com/michuanhaohao/reid-strong-baseline).

## What's New

- Remove [ignite](https://github.com/pytorch/ignite)(a high-level library) dependency and powered by [PyTorch](https://pytorch.org/).
- Includes more features such as circle loss, abundant visualization methods and evaluation metrics, SoTA results on conventional, cross-domain, partial and vehicle re-id, testing on multi-datasets simultaneously, etc.
- Can be used as a library to support [different projects](https://github.com/JDAI-CV/fast-reid/tree/master/projects) on top of it. We'll open source more research projects in this way.
- It trains much faster.

We write a chinese blog about this toolbox in [zhihu](https://zhuanlan.zhihu.com/p/144944220)

## Installation

See [INSTALL.md](https://github.com/JDAI-CV/fast-reid/blob/master/INSTALL.md).

## Quick Start

The designed architecture follows this guide [PyTorch-Project-Template](https://github.com/L1aoXingyu/PyTorch-Project-Template), you can check each folder's purpose by yourself.

See [GETTING_STARTED.md](https://github.com/JDAI-CV/fast-reid/blob/master/GETTING_STARTED.md).

Learn more at out [documentation](). And see [projects/](https://github.com/JDAI-CV/fast-reid/tree/master/projects) for some projects that are build on top of fastreid.

## Model Zoo and Baselines

We provide a large set of baseline results and trained models available for download in the [Fastreid Model Zoo](https://github.com/JDAI-CV/fast-reid/blob/master/MODEL_ZOO.md).

## License

Fastreid is released under the [Apache 2.0 license](https://github.com/JDAI-CV/fast-reid/blob/master/LICENSE).
Update StrongBaseline results for market1501 and dukemtmc 2020-02-11 22:38:40 +08:00			`# FastReID`
Update sampler code 2020-02-10 07:38:56 +08:00
update readme and instruction 2020-05-28 20:01:20 +08:00			`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](https://github.com/michuanhaohao/reid-strong-baseline).`
Update sampler code 2020-02-10 07:38:56 +08:00
update readme and instruction 2020-05-28 20:01:20 +08:00			`## What's New`
Change architecture: 1. delete redundant preprocess 2. add data prefetcher to accelerate data loading 3. fix minor bug of triplet sampler when only one image for one id 2020-02-18 21:01:23 +08:00
update readme and instruction 2020-05-28 20:01:20 +08:00			`- Remove [ignite](https://github.com/pytorch/ignite)(a high-level library) dependency and powered by [PyTorch](https://pytorch.org/).`
update proejcts readme 2020-05-29 11:19:22 +08:00			`- Includes more features such as circle loss, abundant visualization methods and evaluation metrics, SoTA results on conventional, cross-domain, partial and vehicle re-id, testing on multi-datasets simultaneously, etc.`
update readme and instruction 2020-05-28 20:01:20 +08:00			`- Can be used as a library to support [different projects](https://github.com/JDAI-CV/fast-reid/tree/master/projects) on top of it. We'll open source more research projects in this way.`
			`- It trains much faster.`

update zhihu article url in readme 2020-05-31 23:32:49 +08:00			`We write a chinese blog about this toolbox in [zhihu](https://zhuanlan.zhihu.com/p/144944220)`
update readme and instruction 2020-05-28 20:01:20 +08:00
			`## Installation`
Update sampler code 2020-02-10 07:38:56 +08:00
update readme and instruction 2020-05-28 20:01:20 +08:00			`See [INSTALL.md](https://github.com/JDAI-CV/fast-reid/blob/master/INSTALL.md).`
Change architecture: 1. delete redundant preprocess 2. add data prefetcher to accelerate data loading 3. fix minor bug of triplet sampler when only one image for one id 2020-02-18 21:01:23 +08:00
update readme and instruction 2020-05-28 20:01:20 +08:00			`## Quick Start`

			`The designed architecture follows this guide [PyTorch-Project-Template](https://github.com/L1aoXingyu/PyTorch-Project-Template), you can check each folder's purpose by yourself.`
Change architecture: 1. delete redundant preprocess 2. add data prefetcher to accelerate data loading 3. fix minor bug of triplet sampler when only one image for one id 2020-02-18 21:01:23 +08:00
update readme and instruction 2020-05-28 20:01:20 +08:00			`See [GETTING_STARTED.md](https://github.com/JDAI-CV/fast-reid/blob/master/GETTING_STARTED.md).`
Change architecture: 1. delete redundant preprocess 2. add data prefetcher to accelerate data loading 3. fix minor bug of triplet sampler when only one image for one id 2020-02-18 21:01:23 +08:00
update readme and instruction 2020-05-28 20:01:20 +08:00			`Learn more at out [documentation](). And see [projects/](https://github.com/JDAI-CV/fast-reid/tree/master/projects) for some projects that are build on top of fastreid.`
Update sampler code 2020-02-10 07:38:56 +08:00
Update StrongBaseline results for market1501 and dukemtmc 2020-02-11 22:38:40 +08:00			`## Model Zoo and Baselines`
Update performance 2020-03-31 14:37:24 +08:00
docs: update README 2020-05-12 23:00:15 +08:00			`We provide a large set of baseline results and trained models available for download in the [Fastreid Model Zoo](https://github.com/JDAI-CV/fast-reid/blob/master/MODEL_ZOO.md).`
add license in readme 2020-05-29 10:33:21 +08:00
			`## License`

update proejcts readme 2020-05-29 11:19:22 +08:00			`Fastreid is released under the [Apache 2.0 license](https://github.com/JDAI-CV/fast-reid/blob/master/LICENSE).`