search

youweiliang / evit

Python code for ICLR 2022 spotlight paper EViT: Expediting Vision Transformers via Token Reorganizations
Apache License 2.0
162 stars 19 forks source link

Visualize #16

Open bsaberla opened 1 year ago

bsaberla commented 1 year ago

Hello,

I am using this command, but it does not save any masked images. python3 main.py --model deit_small_patch16_shrink_base --fuse_token --base_keep_rate 0.7 --visualize_mask --n_visualization 64 --resume checkpoint --data-path /path/to/imagenet

I think this part is not working in the code: if args.visualize_mask: visualize_mask(data_loader_val, model, device, args.output_dir, args.n_visualization, args.fuse_token) return

youweiliang commented 1 year ago

Hi, Sorry for the late reply. Can you provide more information regarding why it's not working? Like any error messages?