Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

How to eval #3

Open
lyyaixuexi opened this issue May 22, 2023 · 4 comments
Open

How to eval #3

lyyaixuexi opened this issue May 22, 2023 · 4 comments

Comments

@lyyaixuexi
Copy link

Can you please tell me what the instructions for testing the pre-trained model you provided are?

@wangsr126
Copy link
Owner

I've updated the README.md with instructions for evaluating the fine-tuned models on ImageNet. Hope this helps!

@lyyaixuexi
Copy link
Author

Thanks! I run this scripts

python mae_lite/tools/eval.py -b 512 -d 7 -f projects/eval_tools/finetuning_exp.py
--ckpt /mnt/cephfs/home/lyy/Quantization/MAE-Lite/model/mae_tiny_400e_ft_300e.pth.tar
--exp-options pretrain_exp_name=mae_lite/mae_tiny_400e/ft_eval

But it encountered an error while loading the model, with some Missing keys and Unexpected keys,Did I use the correct model and exp file?

@wangsr126
Copy link
Owner

Please check if you use the latest version of the code. We updated some code for evaluation in the latest commit.

@lyyaixuexi
Copy link
Author

Thanks!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants