Finetuning Command for RESISC-45 Downstream Dataset

[AkshitSharma1]

Hello! Thank you for sharing the code and the impressive results.

Will it be possible for you to please share the exact command involving main_finetune.py that has been used to finetune ViT-L on the RESISC-45 downstream dataset?

Thanks Akshit

[techmn]

CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m torch.distributed.launch --nproc_per_node=8 --master_port=29202 main_finetune.py \
--batch_size 8 --accum_iter 16 \
--epochs 50 --warmup_epochs 5 \
--input_size 224 --patch_size 16 \
--model_type vanilla \
--dataset_type resisc \
--nb_classes 45 \
--weight_decay 0.05 --drop_path 0.2 --reprob 0.25 --mixup 0.8 --cutmix 1.0 \
--lr 0.001 --num_workers 16 \
--base_path /datasets/RESISC45/Images/ \
--train_path /datasets/RESISC45/train-resisc.txt \
--test_path /datasets/RESISC45/val-resisc.txt \
--output_dir ./finetune_dir \
--log_dir ./finetune_dir \
--finetune ./output_dir/checkpoint-799.pth