Open Gy-Lu opened 2 years ago
Hi, I find that we have provided too many huge models as examples, for instance, we reshape cifar-10 to 224*224 and use ViT Huge(at least not tiny) to train. This reshape is quite redundant and so as ViT Huge for cifar-10.
Describe the feature
Hi, I find that we have provided too many huge models as examples, for instance, we reshape cifar-10 to 224*224 and use ViT Huge(at least not tiny) to train. This reshape is quite redundant and so as ViT Huge for cifar-10.