You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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?
The text was updated successfully, but these errors were encountered:
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.
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?
The text was updated successfully, but these errors were encountered: