We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
n_in, n_out
initialisers.py
(n_out, n_in)
There may be a better design here that keeps track of these dimensions... i.e. functions like sample_W in layers.py are horrible!
sample_W
layers.py
The text was updated successfully, but these errors were encountered:
This also should fix the autonorm initialization, see d25947e
autonorm
Sorry, something went wrong.
Merge pull request #193 from data61/feature/#192
e973bde
Feature/#192
No branches or pull requests
n_in, n_out
ininitialisers.py
, our 2-d weights are typically(n_out, n_in)
There may be a better design here that keeps track of these dimensions... i.e. functions like
sample_W
inlayers.py
are horrible!The text was updated successfully, but these errors were encountered: