Can not reproduce following the hyperparameter in the paper for finefuning ViT on Cifar100
NamlessM opened this issue · comments
Hi! I can reproduce the ViT-B_16's R-Drop results on cifar100 when I change img_size to 224, learning_rate to 8e-3 and num_steps to 20,000. Hope it can help you!
Thank you very much for your help! Just still wonder what is the alpha you are using in addition to the hyperparameters listed above?
I didn't change any hyperparameters other than img_size, learning_rate and num_steps. Therefore, the alpha is still 0.3, which is the default value.
Thank you! I will try this setting!