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
Fix #7 #8
Fix #7 #8
Conversation
I am not sure if this ipynb file is clean -- I see some references to my own github repo. |
@rainwoodman the notebook is great. Just a few minor suggestions:
|
You are right I forgot to remove the lines. Those were for debugging, when I checked that the before this change indeed we used to have gradients == sam_gradients. |
I removed the lines, and updated README. Please take a look, thanks! |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@rainwoodman thank you for the changes. Just one more minor comment.
@@ -27,8 +27,8 @@ SAM has only one hyperparameter namely `rho` that controls the neighborhood of t | |||
| Without SAM | 0.575114 | 82.9 | |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Did you also want to update this table with the final scores?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes It was updated in the previous commit. ;)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Oh I see. Anyway the current README should reflect the changes you made. Thank you so much.
Fix #7.
The SAM training accuracy is near 82.5%, increased from the quoted numbers on the home page.
The non-SAM training appears to terminated early at 5m30, ~ 70 epochs, and at a lower accuracy than the home page number.