-
Notifications
You must be signed in to change notification settings - Fork 224
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
Improve MLPBN #171
Improve MLPBN #171
Conversation
chainerrl/links/mlp_bn.py
Outdated
to inputs. | ||
normalize_output (bool): If set to True, Batch Normalization is applied | ||
to outputs. | ||
nonlinearity (callable): Nonlinearity between layers. |
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.
In most cases, nonlinearity
is a chainer.Function
, and it cannot be a chainer.Link
. Could you make the followings clear?
nonlinearity
has no parameters;nonlinearity
, called with one argument ofchainer.Variable
, returnschainer.Variable
of the same shape as the input.
tests/links_tests/test_mlp_bn.py
Outdated
|
||
import unittest | ||
|
||
import numpy as np |
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.
In other files, numpy
and chainer
are in the same group of the import order.
LGTM |
nonlinearity
andlast_wscale
argument to MLPBNThe tests for MLPBN are actually not checking each configuration is applied or not, but it should be better than having no tests.