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
I noticed that a few argument values in search/src/args.py differ from what is mentioned in the paper like max_weight_decay, mul_factor.
Also if I understood it right, in the paper most plots seem to indicate that overfitting is reduced with drop_path_prob >= 0.5, yet the default value of it in code is given 0.2
The value of "factor" parameter (the threshold for eigenvalues) is also different in the paper than code.
Could you please clarify about the good/default value of all these 3 parameters as per your experiments?
Thank You!
The text was updated successfully, but these errors were encountered:
sharadkak
changed the title
Different parameter values than what mentioned in the paper.
Different default parameter values than what is mentioned in the paper.
Nov 10, 2020
Hi
Thanks for the paper and code.
I noticed that a few argument values in search/src/args.py differ from what is mentioned in the paper like max_weight_decay, mul_factor.
Also if I understood it right, in the paper most plots seem to indicate that overfitting is reduced with drop_path_prob >= 0.5, yet the default value of it in code is given 0.2
The value of "factor" parameter (the threshold for eigenvalues) is also different in the paper than code.
Could you please clarify about the good/default value of all these 3 parameters as per your experiments?
Thank You!
The text was updated successfully, but these errors were encountered: