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

wieght initiliazing #35

Open

elliotTAU opened this issue Feb 9, 2021 · 1 comment

elliotTAU commented Feb 9, 2021 •

edited

Loading

Hi

Is it possible to initialize weights with your build function "build_network" or "init_sess" ?
Or i need to write full function to do so?

I want to perform fine-tunning/transfer learning
So maybe just initializing the last layer

thanks

Owner

assafshocher commented Feb 10, 2021

Hi,
The weights are initialized at

Line 146 in d294852

    
           self.filters_t = [tf.get_variable(shape=meta.filter_shape[ind], name='filter_%d' % ind,

So you would need to add some flag and an option to load existing weights

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