diff options
author | Brennan Saeta <saeta@google.com> | 2017-02-13 15:34:03 -0800 |
---|---|---|
committer | TensorFlower Gardener <gardener@tensorflow.org> | 2017-02-13 17:21:19 -0800 |
commit | 69d028435d3b10809f5bf34708e493233485e626 (patch) | |
tree | a779f8a0d4d0229d277248bd733595c41f875ee2 /tensorflow/contrib/layers/__init__.py | |
parent | 3aa4b69be09dc47893ffcc6226d014dde759ea64 (diff) |
Documentation changes to adhere to new doc generator
Change: 147402290
Diffstat (limited to 'tensorflow/contrib/layers/__init__.py')
-rw-r--r-- | tensorflow/contrib/layers/__init__.py | 40 |
1 files changed, 1 insertions, 39 deletions
diff --git a/tensorflow/contrib/layers/__init__.py b/tensorflow/contrib/layers/__init__.py index c563b29de9..5a7b6b7d27 100644 --- a/tensorflow/contrib/layers/__init__.py +++ b/tensorflow/contrib/layers/__init__.py @@ -14,11 +14,7 @@ # ============================================================================== """Ops for building neural network layers, regularizers, summaries, etc. -## Higher level ops for building neural network layers. - -This package provides several ops that take care of creating variables that are -used internally in a consistent way and provide the building blocks for many -common machine learning algorithms. +See the @{$python/contrib.layers} guide. @@avg_pool2d @@batch_norm @@ -45,57 +41,24 @@ common machine learning algorithms. @@unit_norm @@embed_sequence -Aliases for fully_connected which set a default activation function are -available: `relu`, `relu6` and `linear`. - -`stack` operation is also available. It builds a stack of layers by applying -a layer repeatedly. - -## Regularizers - -Regularization can help prevent overfitting. These have the signature -`fn(weights)`. The loss is typically added to -`tf.GraphKeys.REGULARIZATION_LOSSES`. - @@apply_regularization @@l1_regularizer @@l2_regularizer @@sum_regularizer -## Initializers - -Initializers are used to initialize variables with sensible values given their -size, data type, and purpose. - @@xavier_initializer @@xavier_initializer_conv2d @@variance_scaling_initializer -## Optimization - -Optimize weights given a loss. - @@optimize_loss -## Summaries - -Helper functions to summarize specific variables or ops. - @@summarize_activation @@summarize_tensor @@summarize_tensors @@summarize_collection -The layers module defines convenience functions `summarize_variables`, -`summarize_weights` and `summarize_biases`, which set the `collection` argument -of `summarize_collection` to `VARIABLES`, `WEIGHTS` and `BIASES`, respectively. - @@summarize_activations -## Feature columns - -Feature columns provide a mechanism to map data to a model. - @@bucketized_column @@check_feature_columns @@create_feature_spec_for_parsing @@ -118,7 +81,6 @@ Feature columns provide a mechanism to map data to a model. @@weighted_sum_from_feature_columns @@infer_real_valued_columns @@sequence_input_from_feature_columns - """ from __future__ import absolute_import |