This is code of paper "ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer"
26
stars
3
forks
source link
The file main.py is missing for training the model. It's not included in github package, I would request if you could please provide this main.py in order to run the command. !python3 -m torch.distributed.launch --nproc_per_node=8 --use_env main.py --model scalable_vit_small --batch-size 128 --data-path ${path_to_imagenet} --dist-eval --drop-path 0.2 #1
Sorry, I am too busy to clear up codes in time. It will be pushed later~