-
Notifications
You must be signed in to change notification settings - Fork 22
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
Add support for UpSampling layers to converter #130
Conversation
f6f84bb
to
13f9024
Compare
bias_relay, | ||
output, | ||
transform=nengo.Sparse( | ||
(output.size_in, bias_relay.size_out), indices=broadcast_indices |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I would explicitly set init=1
here, just to make it clear what the sparse values are.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I assumed that it was 1, personally. If we thought it would be ambiguous we should have made init
a required argument in nengo.Sparse
, but since that didn't come up when working on that, I feel like it's what we would naturally assume.
This was accidentally removed at some point in the 3.0 rewrite.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This all LGTM. I'll merge when CI finishes unless @drasmuss wants to make the init=1
change.
No description provided.