Rethinking Sampling Strategies for Unsupervised Person Re-identification [arXiv]
git clone https://github.com/wavinflaghxm/GroupSampling.git
cd GroupSampling
python setup.py developcd examples && mkdir dataDownload the person datasets Market-1501, DukeMTMC-reID, MSMT17. Then unzip them under the directory like:
GroupSampling/examples/data
├── market1501
│ └── Market-1501-v15.09.15
├── dukemtmc
│ └── DukeMTMC-reID
└── msmt17
└── MSMT17_V2
We utilize 1 GTX-2080TI GPU for training.
- Use
--group-n 256for Market-1501,--group-n 128for DukeMTMC-reID, and--group-n 1024for MSMT17.
Market-1501:
CUDA_VISIBLE_DEVICES=0 python examples/train.py -d market1501 --logs-dir logs/market_resnet50 --group-n 256
DukeMTMC-reID:
CUDA_VISIBLE_DEVICES=0 python examples/train.py -d dukemtmc --logs-dir logs/duke_resnet50 --group-n 128
MSMT17:
CUDA_VISIBLE_DEVICES=0 python examples/train.py -d msmt17 --logs-dir logs/msmt_resnet50 --group-n 1024 --iters 800
We recommend using 4 GPUs to train MSMT17 for better performance.
CUDA_VISIBLE_DEVICES=0,1,2,3 python examples/train.py -d msmt17 --logs-dir logs/msmt_resnet50-gpu4 --group-n 1024 -b 256 --momentum 0.1 --lr 0.00005
To evaluate the model, run:
CUDA_VISIBLE_DEVICES=0 python examples/test.py -d $DATASET --resume $PATH
Some examples:
### Market-1501 ###
CUDA_VISIBLE_DEVICES=0 python examples/test.py -d market1501 --resume logs/market_resnet50/model_best.pth.tar
Codes are built upon SpCL. Thanks to Yixiao Ge for opening source.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent