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.

Sign up for GitHub

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

Jump to bottom

Here none of the convolution weights are initialized to Xavier initialization as m.bias is always None because while initializing conv2d bias is always set to False #2

Open

singhsarvagya opened this issue Oct 27, 2019 · 1 comment

singhsarvagya commented Oct 27, 2019

Line 87 in 553da62

if class_name.find('Conv') != -1 and m.bias is not None:

Author

singhsarvagya commented Oct 27, 2019

Only in the squeezenet, the conv2d weights will be initialized to Xavier distribution

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment