Open
Conversation
…ns train/validation/test and script cleanup
- Device type and Device info
…ing based on either validation accuracy or validation robust accuracy
Aaron99B
reviewed
Feb 18, 2026
Owner
Aaron99B
left a comment
Aaron99B
left a comment
There was a problem hiding this comment.
I would make the names for the networks and how they are handled consistent. Further, I recommend to never use a comment unless absolutely necessary. Many of the comments can be removed by making the code more readable
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull requests adds improved and cleaned up scripts as well as improved logging. During training both robust accuracy and clean accuracy are logged and displayed in wandb. Also in the end two more extensive metric tables are created containing training information such as training time, early stopping information and device info and final model performances on the train and validation sets. This improves usability of the tool vastly. Furthermore, the models were renamed and cleaned up in order to follow the same scheme.
It was tested using the mnist_relu_2 scripts and on a CNN-4 architecture using the pgd script including arguments.