-
Notifications
You must be signed in to change notification settings - Fork 70
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
question in Backward code #11
Comments
You are right, @flymark2010 . That might be some testing code that I forgot to comment. Better comment those lines for higher efficiency. |
@yiwenguo Ok. Thanks ! |
@yiwenguo I also have a question about this part. According to your paper, |
@kai-xie I think if we use mask computed diffs(just as moving codes as you asked),weights and biases masked wil never be alive.So we pass errors to udpate those masked parameters to see if they can come alive although it's not correct in mathematics. |
Hi, thanks for your great work. I have some doubt about the Backward code:
To my understanding of caffe, the diff of weight blob is always set to 0 before each iteration. That's to say,
weights_diff[k]
andbias_diff[k]
are always 0 before thebackward_cpu_bias
andweight_cpu_gemm
. So operations of line 14 & line 24 are redundant. What do you really want to do? Does it should beweightTmp
instead ofweight_diff
on line 24?Thanks very much!
The text was updated successfully, but these errors were encountered: