diff options
author | Kwotsin <kwotsin@users.noreply.github.com> | 2017-05-07 01:50:35 +0800 |
---|---|---|
committer | drpngx <drpngx@users.noreply.github.com> | 2017-05-06 10:50:35 -0700 |
commit | 91c9366589b1082e5d9d8fdc70fe46666efb69a1 (patch) | |
tree | 310922c7225cb3a85d035f7ebcd6c1255ef4f52a | |
parent | 50d816cbc55ac2fb5e2f9dfadb669553fd4e2525 (diff) |
Including batch_norm as the normalizer function by default, as mentioned in function description (#9652)
* fixed separable_conv2d description error and included batch_norm by default as mentioned in description
* Update layers.py
* Update layers.py
-rw-r--r-- | tensorflow/contrib/layers/python/layers/layers.py | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/tensorflow/contrib/layers/python/layers/layers.py b/tensorflow/contrib/layers/python/layers/layers.py index 32ca0c38d9..3681829f65 100644 --- a/tensorflow/contrib/layers/python/layers/layers.py +++ b/tensorflow/contrib/layers/python/layers/layers.py @@ -1087,7 +1087,7 @@ def convolution2d_transpose( """Adds a convolution2d_transpose with an optional batch normalization layer. The function creates a variable called `weights`, representing the - kernel, that is convolved with the input. If `batch_norm_params` is `None`, a + kernel, that is convolved with the input. If `normalizer_fn` is `None`, a second variable called 'biases' is added to the result of the operation. Args: @@ -1847,9 +1847,9 @@ def separable_convolution2d( This op first performs a depthwise convolution that acts separately on channels, creating a variable called `depthwise_weights`. If `num_outputs` is not None, it adds a pointwise convolution that mixes channels, creating a - variable called `pointwise_weights`. Then, if `batch_norm_params` is None, - it adds bias to the result, creating a variable called 'biases', otherwise - it adds a batch normalization layer. It finally applies an activation function + variable called `pointwise_weights`. Then, if `normalizer_fn` is None, + it adds bias to the result, creating a variable called 'biases', otherwise, + the `normalizer_fn` is applied. It finally applies an activation function to produce the end result. Args: |