MAE-pytorch

MAE-pytorch copied to clipboard

Bad transfer learning result while fine tuning in iNaturalist 2019 which is not IN1K

7

Dear Author, Firstly thanks and appreciated for your great contribution. While fine tuning with IN1K base on the pre-train model which also trained with IN1K, the result is similar to...

cssddnnc9527

I'm running mae's finetune"return torch.layer_norm(input, normalized_shape, weight, bias, eps, torch.backends.cudnn.enabled) RuntimeError: Given normalized_shape=[768], expected input with shape [*, 768], but got input of size[12]",Please tell me what the problem is.

zhengzaidenglu

I wonder if you plan to release the mask prediction visualization code?

dreamercv

Low Linear-Prob accuracy

6

Dear author I have reproduced your code using 64 V100 GPUs. Every setting is the same as paper (batch size 4096), The end-to-end finetuning is almost the same as paper....

launchauto

I used the argument --resume /path/to/checkpoint But this doesn't work. Also the --auto_resume will restart from epoch 0 How to resume after a break?

SAOHPRWHG

Why learning rate from 0 to 1e-4? Shouldn't it be 1e-4 to 0?

together0

Could you please provide the pretrained weights of smaller vit variants?

GuHuangAI

Hey, Thanks very much for this excellent repo, it is definitely worth hundreds of thousands of stars! :) I wonder which datasets are used for the released pretrained model? Since...

AArchLichKing

IndexError: index 129600 is out of bounds for axis 0 with size 129600

CASlzwde

Weights & Biases logger for MAE-pytorch

2

Hi @pengzhiliang I am an ML Engineer at Weights & Biases and I wanted to know if you were actively reviewing PRs at the moment? We would love to make...

morganmcg1