Inhibition-aware (-regularized) 3D attention for robust visual recognition
- The version requirements of key frameworks are listed here:
python>=3.6
pytorch>=1.6.0
mxnet>=1.6.0- For more detailed requirements, please refer to 'requirements.txt'
- Download CIFAR-100 dataset.
- Convert to
mxnet.recordio.MXIndexedRecordIO:
cd datasets
python cvt_cifar_100.py- {Optional} For faster IO, you can copy your datasets folder (containing 'train.rec' and 'train.idx') to memory using this:
sudo mkdir /tmp/train_tmp
sudo mount -t tmpfs -o size=10G tmpfs /tmp/train_tmp
cp -r {Your_Datasets_Folder} /tmp/train_tmp
# you may get /tmp/train_tmp/cifar-100/train.rec...After setting this, you can set num_workers=0 in your training code.
- TODO
- Edit
config.pyas you need. - For
fp16, please refer to https://pytorch.org/docs/stable/amp.html. - For
rec, you need to set it as your datasets folder which includes 'xxx.rec' and 'xxx.idx'. - Some settings are useless. You may ignore them.
- This repository adopts DDP training scheme. Please refer to https://pytorch.org/docs/stable/distributed.html.
- You can start train on 4 GPUs like this:
CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 --nnodes=1 --node_rank=0 --master_addr="127.0.0.1" --master_port=1234 train.py --network iresnet18- For more
--networktypes, please refer tobackbones/__init__.py. - The evaluating process starts every 10 epoch during training. You don't need to run other codes for evaluation.
- TODO
- TODO