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

Unable to reproduce results with CIFAR-10 dataset on efficientnet-l2-475 #12

Open
MiguelCosta94 opened this issue Jul 26, 2021 · 0 comments

Comments

@MiguelCosta94
Copy link

Hi,

I am running the following command to reproduce your results achieved with CIFAR-10 dataset on efficientnet-l2-475. I reduced the number of epochs just to see the script running from the very beginning till the end faster.
python3 -m sam.sam_jax.train --dataset cifar10 --model_name efficientnet-l2-475 --output_dir /tmp/my_experiment --image_level_augmentations autoaugment --num_epochs 2 --sam_rho 0.05

Nevertheless, I am getting the following error. How can I fix this?
python3 -m sam.sam_jax.train --dataset cifar10 --model_name efficientnet-l2-475 --output_dir /tmp/my_experiment --image_level_augmentations autoaugment --num_epochs 2 --sam_rho 0.05

Best regards,
Miguel

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

1 participant