python -m torch.distributed.launch --nproc_per_node=1 eval_linear.py --pretrained_weights /path/to/checkpoint.pth --checkpoint_key student--data_path /path/to/imagenet

git clone https://github.com/SwinTransformer/Swin-Transformer-Object-Detection
# single-gpu testing
python tools/test.py <CONFIG_FILE> <DET_CHECKPOINT_FILE> --eval bbox segm
# for example
python tools/test.py configs/swin/mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_1x_coco.py <DET_CHECKPOINT_FILE> --eval bbox segm

git clone https://github.com/fudan-zvg/SETR
# single-gpu testing
./tools/dist_test.sh ${CONFIG_FILE} ${CHECKPOINT_FILE} ${GPU_NUM}  [--eval ${EVAL_METRICS}]
# For example, test a SETR-PUP on Cityscapes dataset with 8 GPUs
./tools/dist_test.sh configs/SETR/SETR_PUP_768x768_40k_cityscapes_bs_8.py \
work_dirs/SETR_PUP_768x768_40k_cityscapes_bs_8/iter_40000.pth \
8 --eval mIoU

@article{li2021mst,
  title={MST: Masked Self-Supervised Transformer for Visual Representation},
  author={Li, Zhaowen and Chen, Zhiyang and Yang, Fan and Li, Wei and Zhu, Yousong and Zhao, Chaoyang and Deng, Rui and Wu, Liwei and Zhao, Rui and Tang, Ming and others},
  journal={arXiv preprint arXiv:2106.05656},
  year={2021}
}