asyml / vision-transformer-pytorch

Pytorch version of Vision Transformer (ViT) with pretrained models. This is part of CASL (https://casl-project.github.io/) and ASYML project.
https://asyml.io/
Apache License 2.0
342 stars 58 forks source link

finetuned file available? #11

Closed Ferriksw closed 5 months ago

Ferriksw commented 5 months ago

Hey there! I wonder if there is a finetune.pth file available? etc generated by code <python src/finetune.py --exp-name vb16-CIFAR100-attn25-1-0-6 --n-gpu=1 --model-arch b16 --prune_rate 0.25 --iter_nums 1 --finetune_nums 0 --final_finetune 6 --prune_mode attn --checkpoint-path=[path\to\weight] --image-size 384 --batch-size 16 --data-dir data/ --dataset CIFAR100 --num-classes 100 --lr 0.0001 --wd 0.0001>