Is the training procedure result normal? Masked regions do not improve and appear to be random noise.

[junzhin]

Hello,

thank you for the great work and the great repo.

I attempted to reproduce the pre-training of MAE-ViT-Large, and performed 68 epochs on a chest x -rays dataset with about 300 k medical images, and the loss stopped improving when it reached around 0.0045 loss without pixlossnorm. Additionally, the reconstruction results fail to predict the masked regions correctly.

Could you suggest a reason for that? Any idea why this is the case?

[CristoJV]

Hi @junzhin,

I'm facing the same errors.
Pretrained on 500k faces for 20 epochs, resuming from the authors' pretrained version MAE-ViT-Base.

Did you manage to solve them?

EDIT: I fixed it by disabling the pixlossnorm.

Thank you!

[ats4869]

I would like to ask how you use finetune to train the reconstruction model on your own data set. I see that through main_finetune.py only models for classification tasks can be generated.