This implementation is based on the official implementation of "CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows".
timm==0.3.4, pytorch>=1.4, opencv, ... , run:
bash install_req.sh
Apex for mixed precision training is used for finetuning. To install apex, run:
git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./
Data prepare: ImageNet with the following folder structure, you can extract imagenet by this script. Please follow the train-test splits of CSwin.
│imagenet/
├──train/
│ ├── n01440764
│ │ ├── n01440764_10026.JPEG
│ │ ├── n01440764_10027.JPEG
│ │ ├── ......
│ ├── ......
├──val/
│ ├── n01440764
│ │ ├── ILSVRC2012_val_00000293.JPEG
│ │ ├── ILSVRC2012_val_00002138.JPEG
│ │ ├── ......
│ ├── ......
Train the three lite variants: CSWin-Tiny, CSWin-Small and CSWin-Base:
bash train.sh 8 --data <data path> --model CSWin_64_12211_tiny_224 -b 256 --lr 2e-3 --weight-decay .05 --amp --img-size 224 --warmup-epochs 20 --model-ema-decay 0.99984 --drop-path 0.2
bash train.sh 8 --data <data path> --model CSWin_64_24322_small_224 -b 256 --lr 2e-3 --weight-decay .05 --amp --img-size 224 --warmup-epochs 20 --model-ema-decay 0.99984 --drop-path 0.4
bash train.sh 8 --data <data path> --model CSWin_96_24322_base_224 -b 128 --lr 1e-3 --weight-decay .1 --amp --img-size 224 --warmup-epochs 20 --model-ema-decay 0.99992 --drop-path 0.5
This is developped based on CSWin Transformer