If you use origin ResNet, you do not need to do anything. But if you want to use ResNet-ibn or ResNeSt, you need to download pretrain model in here.
And then you need to put it in ~/.cache/torch/checkpoints
or anywhere you like.
Then you should set the pretrain model path in configs/Base-bagtricks.yml
.
cd fastreid/evaluation/rank_cylib; make all
We provide a script in "tools/train_net.py", that is made to train all the configs provided in fastreid. You may want to use it as a reference to write your own training script.
To train a model with "train_net.py", first setup up the corresponding datasets following datasets/README.md, then run:
CUDA_VISIBLE_DEVICES=$gpus ./tools/train_net.py --config-file ./configs/Market1501/bagtricks_R50.yml
The configs are made for 1-GPU training.
To evaluate a model's performance, use
CUDA_VISIBLE_DEVICES=$gpus ./tools/train_net.py --config-file ./configs/Market1501/bagtricks_R50.yml \
--eval-only MODEL.WEIGHTS /path/to/checkpoint_file
For more options, see ./tools/train_net.py -h
.