-
Notifications
You must be signed in to change notification settings - Fork 227
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
Print the actual pruning rate #290
Comments
cc'ed @mkaglins |
We also need to revise information that is printed after each epoch. I found some strange numbers that make it unclear. Just check out: +---------------+---------------+------------+-------------+-------+-----------+ I don't understand why, for example, "Mask zero" is 12.5%, while "PR" and "Filter PR" are 0. @mkaglins to comment. |
@AlexKoff88 That means weights aren't zeroed for some reason (or became non-zero). |
Maybe this issue is related to #353. Anyway, we need to change the column names and even the set of columns keeping only something like "Expected PR", "Actual PR". |
@AlexKoff88 you suggest delete |
Will added actual pruning rate in flops |
Add calculation of average pruning rate for the whole model (no for pruning layers) and print it after the table with per-layers statistics.
The text was updated successfully, but these errors were encountered: