experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Fixes GitHub

Browse Source 
PiperOrigin-RevId: 337182753
Change-Id: I3e42be2bda1256577a74b351e6e13dd7dd2153d2
This commit is contained in:
A. Unique TensorFlower 2020-10-14 15:14:04 -07:00 committed by TensorFlower Gardener
parent 7e6c28f901
commit 9318f787e6
1 changed files with 2 additions and 2 deletions

4
tensorflow/python/keras/layers/normalization.py
View File

@ -80,8 +80,8 @@ class BatchNormalizationBase(Layer):
inference data*.
Arguments:
axis: Integer, the axis that should be normalized (typically the features
axis). For instance, after a `Conv2D` layer with
axis: Integer or a list of integers, the axis that should be normalized
(typically the features axis). For instance, after a `Conv2D` layer with
`data_format="channels_first"`, set `axis=1` in `BatchNormalization`.
momentum: Momentum for the moving average.
epsilon: Small float added to variance to avoid dividing by zero.