[ECCV2020] a toolbox of light-reid learning for faster inference, speed both feature extraction and retrieval stages up to >30x
a toolbox of light reid for fast feature extraction and search - [x] light-model: model distillation (3x faster feature extraction) - [x] light-feature: binary code learning (6x faster retrieval) - [x] light-search: coarse2fine search (2x faster retrieval)
it features - [x] easy switch between light and non-light reid - [x] simple modules for reid implementation - [x] implementations of state-of-the-art deep reid models
```shell script
git clone https://github.com/wangguanan/light-reid.git
cd light-reid conda create -n lightreid python=3.7 conda activate lightreid
pip install -r requirements
conda install pytorch==1.4.0 torchvision -c pytorch
conda install faiss-cpu -c pytorch ```
5 steps to implement a SOTA reid model
1 step to build a SOTA reid model with configs
Our light-reid partially refers open-sourced torch-reid and fast-reid, we thank their awesome contribution to reid community.
If you have any question about this reid toolbox, please feel free to contact me. E-mail: [email protected]