wuyukun-tong

when i try to run python train.py some error occurred! ubuntu 20.04 cuda 11.8 cudnn 8.8.1 pytorch 1.10 I'm on another 18.04 computer with the same version of cuda, cudnn,...

I want to extract more features than just the 512 dimensional cls token from the CLIP pre-trained model, how can I modify that？