You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
they are all much lower (64.3~65.3) than the results in the paper (66.85), and using the updated transform in #8 (comment) for the released checkpoint achieves even worse performance.
For CoCoOp, the result of vit-b16-ep10 (nctx=4, shots=16, ctp=end) on ImageNet is 71.02, but our reproduce (training from scratch then inference) is 70.14, which is also underperformed.
Hi, thanks for the great work, but I found that it is hard to reproduce the results in the paper.
For example, using the released checkpoints in https://github.com/KaiyangZhou/CoOp#models-and-results, the results of vit-b32-ep50 (nctx=16, shots=16, ctp=end, csc=False) on ImageNet are:
they are all much lower (64.3~65.3) than the results in the paper (66.85), and using the updated transform in #8 (comment) for the released checkpoint achieves even worse performance.
For CoCoOp, the result of vit-b16-ep10 (nctx=4, shots=16, ctp=end) on ImageNet is 71.02, but our reproduce (training from scratch then inference) is 70.14, which is also underperformed.
Our environment informance:
V100-32G / Titan RTX
dassl=0.4.2
torch=1.7.1+cu110
torchvision=0.8.2+cu110
I wonder if I miss something? Thanks a lot.
The text was updated successfully, but these errors were encountered: