rocklee2022

Results 3 comments of rocklee2022

> Hi, as you explain in the readme, you finetuned the pre-trained checkpoint using 8 A100 GPUs using a distributed package. Unfortunately i have just one GPU, thus i cannot...

I run "pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 -f https://download.pytorch.org/whl/torch_stable.html" to update the cuda. Then run make.sh sucessfully.