conda install -c pytorch pytorch torchvision
pip install timm==0.3.2

/path/to/imagenet/
  train/
    class1/
      img1.jpeg
    class2/
      img2.jpeg
  val/
    class1/
      img3.jpeg
    class/2
      img4.jpeg

export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
OUTPUT='./output/Conformer_small_patch16_batch_1024_lr1e-3_300epochs'

python -m torch.distributed.launch --master_port 50130 --nproc_per_node=8 --use_env main.py \
                                   --model Conformer_small_patch16 \
                                   --data-set IMNET \
                                   --batch-size 128 \
                                   --lr 0.001 \
                                   --num_workers 4 \
                                   --data-path /data/user/Dataset/ImageNet_ILSVRC2012/ \
                                   --output_dir ${OUTPUT} \
                                   --epochs 300

@article{peng2021conformer,
      title={Conformer: Local Features Coupling Global Representations for Visual Recognition}, 
      author={Zhiliang Peng and Wei Huang and Shanzhi Gu and Lingxi Xie and Yaowei Wang and Jianbin Jiao and Qixiang Ye},
      journal={arXiv preprint arXiv:2105.03889},
      year={2021},
}