I'm curious about the training dataset to evaluate "nocaps".

[yoojin9649]

Hello. Thanks for sharing your code!

I'm curious about the training dataset to evaluate "nocaps".

I was wondering if the model(clipcap model) was trained with the train split of "MS COCO Karpathy's splits" and evaluated using the validation split of "nocaps".

[xiazhi1]

Hello. Thanks for sharing your code!

I'm curious about the training dataset to evaluate "nocaps".

I was wondering if the model(clipcap model) was trained with the train split of "MS COCO Karpathy's splits" and evaluated using the validation split of "nocaps".

@yoojin9649 have you solved that? I have same problem with you? could you shall your experience about it?