MAE

MAE copied to clipboard

Custom masking

11

Hi, thanks for the code. You answered that we can modify the PatchShuffle class to create custom masks. However, the patch shuffle class takes the output of a Conv2d layer,...

harsmac

train_classifier

1

Hello, Why did we not drop the decoder and insert a new linear layer at the end of the norm layer in the train classifier for fine-tuning? Why did you...

amirrezadolatpour2000

Problem with embedding dimension

1

Hello, Thank you for sharing such a wonderful code. I found in my experiments that the parameter of emb_dim that refers to the embedding dimension should be always a multiple...

code-pan94