diff options
author | A. Unique TensorFlower <gardener@tensorflow.org> | 2018-07-02 17:17:54 -0700 |
---|---|---|
committer | TensorFlower Gardener <gardener@tensorflow.org> | 2018-07-02 17:21:06 -0700 |
commit | 9c919582b06cedaf31c6474e4436d0c68d98b9d3 (patch) | |
tree | a0e17fa03206c913118adbab0297db37ae3a475d /tensorflow/python/layers | |
parent | 73e38c29c74d9d9bf7128bf4737a410ff005611e (diff) |
batch_norm: Whether to use batch normalization after each hidden layer.
PiperOrigin-RevId: 203039199
Diffstat (limited to 'tensorflow/python/layers')
-rw-r--r-- | tensorflow/python/layers/normalization.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/tensorflow/python/layers/normalization.py b/tensorflow/python/layers/normalization.py index ece6667981..f7bc10a6a6 100644 --- a/tensorflow/python/layers/normalization.py +++ b/tensorflow/python/layers/normalization.py @@ -44,7 +44,7 @@ class BatchNormalization(keras_layers.BatchNormalization, base.Layer): normalized, typically the features axis/axes. For instance, after a `Conv2D` layer with `data_format="channels_first"`, set `axis=1`. If a list of axes is provided, each axis in `axis` will be normalized - simultaneously. Default is `-1` which takes uses last axis. Note: when + simultaneously. Default is `-1` which uses the last axis. Note: when using multi-axis batch norm, the `beta`, `gamma`, `moving_mean`, and `moving_variance` variables are the same rank as the input Tensor, with dimension size 1 in all reduced (non-axis) dimensions). |