Open TonyLianLong opened 3 years ago
I tried run testing on CIFAR100 following by README.md (Zero-Shot Prediction)
and also can't achieve the performance in paper. did you solve this problem?
Please refer to https://github.com/openai/CLIP/blob/fcab8b6eb92af684e7ff0a904464be7b99b49b88/notebooks/Prompt_Engineering_for_ImageNet.ipynb for this concern.
Thanks for the amazing paper! I have a few questions about the details of the results in Figure 6 in the paper. I tried to use the linear probing code in the
README.md
on CIFAR to run one-shot evaluation on ImageNet. However, my evaluation implementation, withVIT-B/32
, only gets 27% accuracy on ImageNet validation set (not ImageNet V2) instead of about 45% as mentioned in the paper. Therefore, I suspect that I missed some details in the paper experiments and I have a few questions:ViT-B/32
. However, in my personal evaluation,ViT-B/32
does not provide a 45% one-shot accuracy.C
parameter in sklearn for this experiment? Although on my end the performance does not vary much in differentC
values, I will appreciate it if this value could be provided.Thanks again for the amazing paper and thanks in advance for helping me.