diff options
author | Shanqing Cai <cais@google.com> | 2017-12-06 18:43:24 -0800 |
---|---|---|
committer | TensorFlower Gardener <gardener@tensorflow.org> | 2017-12-06 18:47:41 -0800 |
commit | fe8406149feec453250905965a14285465cd2063 (patch) | |
tree | be3cd75d543f3c0f29f368da61d915abbae7fcbf /tensorflow/contrib/model_pruning | |
parent | 8ad62af489df718992561710123bc8c037e7d17b (diff) |
Merge changes from github.
PiperOrigin-RevId: 178185697
Diffstat (limited to 'tensorflow/contrib/model_pruning')
-rw-r--r-- | tensorflow/contrib/model_pruning/python/layers/core_layers.py | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/tensorflow/contrib/model_pruning/python/layers/core_layers.py b/tensorflow/contrib/model_pruning/python/layers/core_layers.py index ae60d8b1e1..95dfd8f421 100644 --- a/tensorflow/contrib/model_pruning/python/layers/core_layers.py +++ b/tensorflow/contrib/model_pruning/python/layers/core_layers.py @@ -72,8 +72,8 @@ class _MaskedConv(base.Layer): linear activation. use_bias: Boolean, whether the layer uses a bias. kernel_initializer: An initializer for the convolution kernel. - bias_initializer: An initializer for the bias vector. If None, no bias will - be applied. + bias_initializer: An initializer for the bias vector. If None, the default + initializer will be used. kernel_regularizer: Optional regularizer for the convolution kernel. bias_regularizer: Optional regularizer for the bias vector. activity_regularizer: Regularizer function for the output. @@ -279,8 +279,8 @@ class MaskedConv2D(_MaskedConv): linear activation. use_bias: Boolean, whether the layer uses a bias. kernel_initializer: An initializer for the convolution kernel. - bias_initializer: An initializer for the bias vector. If None, no bias will - be applied. + bias_initializer: An initializer for the bias vector. If None, the default + initializer will be used. kernel_regularizer: Optional regularizer for the convolution kernel. bias_regularizer: Optional regularizer for the bias vector. activity_regularizer: Regularizer function for the output. |