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

what the result of this code #1

Open
ShuchunXu opened this issue Apr 29, 2024 · 2 comments
Open

what the result of this code #1

ShuchunXu opened this issue Apr 29, 2024 · 2 comments

Comments

@ShuchunXu
Copy link

Hi
I ran this code, and all parameters adopted the default settings in the code, which should be consistent with the experiments in the paper. However, the experimental results show that the model performs very poorly on the test data,
train E079: 100% 110/110 [00:28<00:00, 3.85it/s, acc_adv=68.6410, acc_cl=91.4404, loss=0.5546]
test E079: 100% 79/79 [00:27<00:00, 2.85it/s, acc_adv=8.8800, acc_cl=68.0400, loss_adv=0.9494, loss_cl=0.9494]
but the model performs well on the training data, basically in line with the results in the paper. What is the reason for this?

@GuanlinLee
Copy link
Owner

Would you mind giving me information about your running environment? You can try pytorch=1.17.0, because there could be some inconsistency between different versions.

@ShuchunXu
Copy link
Author

Sure, My environment as the fig below
屏幕截图 2024-04-29 192052
But are you sure the cause is the different environment? I will try pytorch=1.17.0

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