Skip to content
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 regarding the functionality #101

Open
dfroze opened this issue Aug 17, 2018 · 0 comments
Open

Question regarding the functionality #101

dfroze opened this issue Aug 17, 2018 · 0 comments

Comments

@dfroze
Copy link

dfroze commented Aug 17, 2018

Hi, I am a beginner to this so there are still some things that I don't understand.
Regarding the conv2d, how are the filters set?
I've found in code the way they are created:
W_conv1 = weight_variable([5, 5, 1, 48])
W_conv2 = weight_variable([5, 5, 48, 64])
W_conv3 = weight_variable([5, 5, 64, 128])
But how are the weights/filters set in them? Are they set with some default or modified during the training? How can I find a list of the weight associated with the filters (if I didn't understand wrong)?
I've looked for tutorials but could not find a clear response.

Thank you in advanced
P.S. yes, this is not an issue but more of a question, sorry if I didn't respect the protocol

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant