Fix a bunch of bad links and missing docs in contrib.

Change: 154820641

tensorflow/contrib/distributions/__init__.py

@@ -15,74 +15,6 @@
 """Classes representing statistical distributions and ops for working with them.
 
 See the @{$python/contrib.distributions} guide.
-
-## Distribution Object
-@@ReparameterizationType
-@@Distribution
-
-## Individual Distributions
-@@Binomial
-@@Bernoulli
-@@BernoulliWithSigmoidProbs
-@@Beta
-@@BetaWithSoftplusConcentration
-@@Categorical
-@@Chi2
-@@Chi2WithAbsDf
-@@Deterministic
-@@VectorDeterministic
-@@Exponential
-@@ExponentialWithSoftplusRate
-@@Gamma
-@@GammaWithSoftplusConcentrationRate
-@@Geometric
-@@InverseGamma
-@@InverseGammaWithSoftplusConcentrationRate
-@@Laplace
-@@LaplaceWithSoftplusScale
-@@Logistic
-@@NegativeBinomial
-@@Normal
-@@NormalWithSoftplusScale
-@@Poisson
-@@StudentT
-@@StudentTWithAbsDfSoftplusScale
-@@Uniform
-
-@@MultivariateNormalDiag
-@@MultivariateNormalTriL
-@@MultivariateNormalDiagPlusLowRank
-@@MultivariateNormalDiagWithSoftplusScale
-
-@@Dirichlet
-@@DirichletMultinomial
-@@Multinomial
-@@WishartCholesky
-@@WishartFull
-
-@@TransformedDistribution
-@@QuantizedDistribution
-
-@@Mixture
-
-@@ExpRelaxedOneHotCategorical
-@@OneHotCategorical
-@@RelaxedBernoulli
-@@RelaxedOneHotCategorical
-
-## Kullback-Leibler Divergence
-@@kl_divergence
-@@RegisterKL
-
-## Helper Functions
-@@matrix_diag_transform
-@@normal_conjugates_known_scale_posterior
-@@normal_conjugates_known_scale_predictive
-@@softplus_inverse
-
-## Functions for statistics of samples
-@@percentile
-
 """
 from __future__ import absolute_import
 from __future__ import division
@@ -140,6 +72,71 @@ _allowed_symbols = [
     'ConditionalTransformedDistribution',
     'FULLY_REPARAMETERIZED',
     'NOT_REPARAMETERIZED',
+    'Affine',
+    'AffineLinearOperator',
+    'Bijector',
+    'Chain',
+    'CholeskyOuterProduct',
+    'Exp',
+    'Identity',
+    'Inline',
+    'Invert',
+    'PowerTransform',
+    'SigmoidCentered',
+    'SoftmaxCentered',
+    'Softplus',
+    'ReparameterizationType',
+    'Distribution',
+    'Binomial',
+    'Bernoulli',
+    'BernoulliWithSigmoidProbs',
+    'Beta',
+    'BetaWithSoftplusConcentration',
+    'Categorical',
+    'Chi2',
+    'Chi2WithAbsDf',
+    'Deterministic',
+    'VectorDeterministic',
+    'Exponential',
+    'ExponentialWithSoftplusRate',
+    'Gamma',
+    'GammaWithSoftplusConcentrationRate',
+    'Geometric',
+    'InverseGamma',
+    'InverseGammaWithSoftplusConcentrationRate',
+    'Laplace',
+    'LaplaceWithSoftplusScale',
+    'Logistic',
+    'NegativeBinomial',
+    'Normal',
+    'NormalWithSoftplusScale',
+    'Poisson',
+    'StudentT',
+    'StudentTWithAbsDfSoftplusScale',
+    'Uniform',
+    'MultivariateNormalDiag',
+    'MultivariateNormalTriL',
+    'MultivariateNormalDiagPlusLowRank',
+    'MultivariateNormalDiagWithSoftplusScale',
+    'Dirichlet',
+    'DirichletMultinomial',
+    'Multinomial',
+    'WishartCholesky',
+    'WishartFull',
+    'TransformedDistribution',
+    'QuantizedDistribution',
+    'Mixture',
+    'ExpRelaxedOneHotCategorical',
+    'OneHotCategorical',
+    'RelaxedBernoulli',
+    'RelaxedOneHotCategorical',
+    'kl_divergence',
+    'RegisterKL',
+    'matrix_diag_transform',
+    'normal_conjugates_known_scale_posterior',
+    'normal_conjugates_known_scale_predictive',
+    'softplus_inverse',
+    'percentile'
 ]
 
 remove_undocumented(__name__, _allowed_symbols)

tensorflow/contrib/losses/__init__.py

@@ -22,10 +22,26 @@ from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 
-# pylint: disable=unused-import,wildcard-import
+# pylint: disable=wildcard-import
-from tensorflow.contrib.losses.python import losses
 from tensorflow.contrib.losses.python.losses import *
-# pylint: enable=unused-import,wildcard-import
+# pylint: enable=wildcard-import
 
 from tensorflow.python.util.all_util import remove_undocumented
-remove_undocumented(__name__, doc_string_modules=[losses])
+
+_allowed_symbols = [
+    'absolute_difference',
+    'add_loss',
+    'hinge_loss',
+    'compute_weighted_loss',
+    'cosine_distance',
+    'get_losses',
+    'get_regularization_losses',
+    'get_total_loss',
+    'log_loss',
+    'mean_pairwise_squared_error',
+    'mean_squared_error',
+    'sigmoid_cross_entropy',
+    'softmax_cross_entropy',
+    'sparse_softmax_cross_entropy',
+]
+remove_undocumented(__name__, _allowed_symbols)

tensorflow/contrib/losses/python/losses/__init__.py

@@ -12,127 +12,15 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 # ==============================================================================
-"""## Loss operations for use in neural networks.
+"""Ops for building neural network losses.
 
-Note: By default all the losses are collected into the `GraphKeys.LOSSES`
+See @{$python/contrib.losses}.
-collection.
-
-All of the loss functions take a pair of predictions and ground truth labels,
-from which the loss is computed. It is assumed that the shape of both these
-tensors is of the form [batch_size, d1, ... dN] where `batch_size` is the number
-of samples in the batch and `d1` ... `dN` are the remaining dimensions.
-
-It is common, when training with multiple loss functions, to adjust the relative
-strengths of individual losses. This is performed by rescaling the losses via
-a `weight` parameter passed to the loss functions. For example, if we were
-training with both log_loss and sum_of_squares_loss, and we wished that the
-log_loss penalty be twice as severe as the sum_of_squares_loss, we would
-implement this as:
-
-  # Explicitely set the weight.
-  tf.contrib.losses.log(predictions, labels, weight=2.0)
-
-  # Uses default weight of 1.0
-  tf.contrib.losses.sum_of_squares(predictions, labels)
-
-  # All the losses are collected into the `GraphKeys.LOSSES` collection.
-  losses = tf.get_collection(tf.GraphKeys.LOSSES)
-
-While specifying a scalar loss rescales the loss over the entire batch,
-we sometimes want to rescale the loss per batch sample. For example, if we have
-certain examples that matter more to us to get correctly, we might want to have
-a higher loss that other samples whose mistakes matter less. In this case, we
-can provide a weight vector of length `batch_size` which results in the loss
-for each sample in the batch being scaled by the corresponding weight element.
-For example, consider the case of a classification problem where we want to
-maximize our accuracy but we especially interested in obtaining high accuracy
-for a specific class:
-
-  inputs, labels = LoadData(batch_size=3)
-  logits = MyModelPredictions(inputs)
-
-  # Ensures that the loss for examples whose ground truth class is `3` is 5x
-  # higher than the loss for all other examples.
-  weight = tf.multiply(4, tf.cast(tf.equal(labels, 3), tf.float32)) + 1
-
-  onehot_labels = tf.one_hot(labels, num_classes=5)
-  tf.contrib.losses.softmax_cross_entropy(logits, onehot_labels, weight=weight)
-
-Finally, in certain cases, we may want to specify a different loss for every
-single measurable value. For example, if we are performing per-pixel depth
-prediction, or per-pixel denoising, a single batch sample has P values where P
-is the number of pixels in the image. For many losses, the number of measurable
-values matches the number of elements in the predictions and labels tensors.
-For others, such as softmax_cross_entropy and cosine_distance, the
-loss functions reduces the dimensions of the inputs to produces a tensor of
-losses for each measurable value. For example, softmax_cross_entropy takes as
-input predictions and labels of dimension [batch_size, num_classes] but the
-number of measurable values is [batch_size]. Consequently, when passing a weight
-tensor to specify a different loss for every measurable value, the dimension of
-the tensor will depend on the loss being used.
-
-For a concrete example, consider the case of per-pixel depth prediction where
-certain ground truth depth values are missing (due to sensor noise in the
-capture process). In this case, we want to assign zero weight to losses for
-these predictions.
-
-  # 'depths' that are missing have a value of 0:
-  images, depths = LoadData(...)
-  predictions = MyModelPredictions(images)
-
-  weight = tf.cast(tf.greater(depths, 0), tf.float32)
-  loss  = tf.contrib.losses.sum_of_squares(predictions, depths, weight)
-
-Note that when using weights for the losses, the final average is computed
-by rescaling the losses by the weights and then dividing by the total number of
-non-zero samples. For an arbitrary set of weights, this may not necessarily
-produce a weighted average. Instead, it simply and transparently rescales the
-per-element losses before averaging over the number of observations. For example
-if the losses computed by the loss function is an array [4, 1, 2, 3] and the
-weights are an array [1, 0.5, 3, 9], then the average loss is:
-
-  (4*1 + 1*0.5 + 2*3 + 3*9) / 4
-
-However, with a single loss function and an arbitrary set of weights, one can
-still easily create a loss function such that the resulting loss is a
-weighted average over the individual prediction errors:
-
-  images, labels = LoadData(...)
-  predictions = MyModelPredictions(images)
-
-  weight = MyComplicatedWeightingFunction(labels)
-  weight = tf.div(weight, tf.size(weight))
-  loss = tf.contrib.losses.sum_of_squares(predictions, depths, weight)
-
-@@absolute_difference
-@@add_loss
-@@hinge_loss
-@@compute_weighted_loss
-@@cosine_distance
-@@get_losses
-@@get_regularization_losses
-@@get_total_loss
-@@log_loss
-@@mean_pairwise_squared_error
-@@mean_squared_error
-@@sigmoid_cross_entropy
-@@softmax_cross_entropy
-@@sparse_softmax_cross_entropy
-
-The following are deprecated in favor of `mean_pairwise_squared_error` and
-`mean_squared_error`.
-@@sum_of_pairwise_squares
-@@sum_of_squares
 """
 
-
 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 
-# pylint: disable=unused-import,wildcard-import
+# pylint: disable=wildcard-import
 from tensorflow.contrib.losses.python.losses.loss_ops import *
-from tensorflow.python.util.all_util import make_all
+# pylint: enable=wildcard-import
-# pylint: enable=unused-import,wildcard-import
-
-__all__ = make_all(__name__)

tensorflow/contrib/seq2seq/__init__.py

@@ -16,36 +16,6 @@
 """Ops for building neural network seq2seq decoders and losses.
 
 See the @{$python/contrib.seq2seq} guide.
-
-@@Decoder
-@@dynamic_decode
-
-@@BasicDecoderOutput
-@@BasicDecoder
-
-@@BeamSearchDecoderOutput
-@@BeamSearchDecoderState
-@@BeamSearchDecoder
-@@FinalBeamSearchDecoderOutput
-
-@@Helper
-@@CustomHelper
-@@GreedyEmbeddingHelper
-@@ScheduledEmbeddingTrainingHelper
-@@ScheduledOutputTrainingHelper
-@@TrainingHelper
-
-@@BahdanauAttention
-@@LuongAttention
-
-@@hardmax
-
-@@AttentionWrapperState
-@@AttentionWrapper
-
-@@gather_tree
-
-@@tile_batch
 """
 
 from __future__ import absolute_import
@@ -63,6 +33,30 @@ from tensorflow.contrib.seq2seq.python.ops.loss import *
 from tensorflow.python.util.all_util import remove_undocumented
 # pylint: enable=unused-import,widcard-import,line-too-long
 
-_allowed_symbols = ["sequence_loss"]
+_allowed_symbols = [
+    "sequence_loss",
+    "Decoder",
+    "dynamic_decode",
+    "BasicDecoder",
+    "BasicDecoderOutput",
+    "BeamSearchDecoder",
+    "BeamSearchDecoderOutput",
+    "BeamSearchDecoderState",
+    "Helper",
+    "CustomHelper",
+    "FinalBeamSearchDecoderOutput",
+    "gather_tree",
+    "GreedyEmbeddingHelper",
+    "ScheduledEmbeddingTrainingHelper",
+    "ScheduledOutputTrainingHelper",
+    "TrainingHelper",
+    "BahdanauAttention",
+    "LuongAttention",
+    "hardmax",
+    "AttentionWrapperState",
+    "AttentionWrapper",
+    "AttentionMechanism",
+    "tile_batch"]
+
 
 remove_undocumented(__name__, _allowed_symbols)

tensorflow/contrib/seq2seq/python/ops/attention_wrapper.py

@@ -39,6 +39,7 @@ from tensorflow.python.util import nest
 
 
 __all__ = [
+    "AttentionMechanism",
     "AttentionWrapper",
     "AttentionWrapperState",
     "LuongAttention",

tensorflow/docs_src/api_guides/python/contrib.graph_editor.md

@@ -137,16 +137,16 @@ which to operate must always be given explicitly. This is the reason why
 
 ## Module: reroute
 
-*   @{tf.contrib.graph_editor.reroute.swap_ts}
+*   @{tf.contrib.graph_editor.swap_ts}
-*   @{tf.contrib.graph_editor.reroute.reroute_ts}
+*   @{tf.contrib.graph_editor.reroute_ts}
-*   @{tf.contrib.graph_editor.reroute.swap_inputs}
+*   @{tf.contrib.graph_editor.swap_inputs}
-*   @{tf.contrib.graph_editor.reroute.reroute_inputs}
+*   @{tf.contrib.graph_editor.reroute_inputs}
-*   @{tf.contrib.graph_editor.reroute.swap_outputs}
+*   @{tf.contrib.graph_editor.swap_outputs}
-*   @{tf.contrib.graph_editor.reroute.reroute_outputs}
+*   @{tf.contrib.graph_editor.reroute_outputs}
-*   @{tf.contrib.graph_editor.reroute.swap_ios}
+*   @{tf.contrib.graph_editor.swap_ios}
-*   @{tf.contrib.graph_editor.reroute.reroute_ios}
+*   @{tf.contrib.graph_editor.reroute_ios}
-*   @{tf.contrib.graph_editor.reroute.remove_control_inputs}
+*   @{tf.contrib.graph_editor.remove_control_inputs}
-*   @{tf.contrib.graph_editor.reroute.add_control_inputs}
+*   @{tf.contrib.graph_editor.add_control_inputs}
 
 ## Module: edit
 

tensorflow/docs_src/api_guides/python/contrib.linalg.md

@@ -21,7 +21,7 @@ Subclasses of `LinearOperator` provide a access to common methods on a
 *   @{tf.contrib.linalg.LinearOperatorDiag}
 *   @{tf.contrib.linalg.LinearOperatorIdentity}
 *   @{tf.contrib.linalg.LinearOperatorScaledIdentity}
-*   @{tf.contrib.linalg.LinearOperatorMatrix}
+*   @{tf.contrib.linalg.LinearOperatorFullMatrix}
 *   @{tf.contrib.linalg.LinearOperatorTriL}
 *   @{tf.contrib.linalg.LinearOperatorUDVHUpdate}
 

tensorflow/docs_src/api_guides/python/contrib.losses.md

@@ -13,8 +13,8 @@ of samples in the batch and `d1` ... `dN` are the remaining dimensions.
 It is common, when training with multiple loss functions, to adjust the relative
 strengths of individual losses. This is performed by rescaling the losses via
 a `weight` parameter passed to the loss functions. For example, if we were
-training with both log_loss and sum_of_squares_loss, and we wished that the
+training with both log_loss and mean_square_error, and we wished that the
-log_loss penalty be twice as severe as the sum_of_squares_loss, we would
+log_loss penalty be twice as severe as the mean_square_error, we would
 implement this as:
 
 ```python
@@ -22,7 +22,7 @@ implement this as:
   tf.contrib.losses.log(predictions, labels, weight=2.0)
 
   # Uses default weight of 1.0
-  tf.contrib.losses.sum_of_squares(predictions, labels)
+  tf.contrib.losses.mean_square_error(predictions, labels)
 
   # All the losses are collected into the `GraphKeys.LOSSES` collection.
   losses = tf.get_collection(tf.GraphKeys.LOSSES)
@@ -74,7 +74,7 @@ these predictions.
   predictions = MyModelPredictions(images)
 
   weight = tf.cast(tf.greater(depths, 0), tf.float32)
-  loss  = tf.contrib.losses.sum_of_squares(predictions, depths, weight)
+  loss  = tf.contrib.losses.mean_square_error(predictions, depths, weight)
 ```
 
 Note that when using weights for the losses, the final average is computed
@@ -100,7 +100,7 @@ weighted average over the individual prediction errors:
 
   weight = MyComplicatedWeightingFunction(labels)
   weight = tf.div(weight, tf.size(weight))
-  loss = tf.contrib.losses.sum_of_squares(predictions, depths, weight)
+  loss = tf.contrib.losses.mean_square_error(predictions, depths, weight)
 ```
 
 @{tf.contrib.losses.absolute_difference}
@@ -118,9 +118,4 @@ weighted average over the individual prediction errors:
 @{tf.contrib.losses.softmax_cross_entropy}
 @{tf.contrib.losses.sparse_softmax_cross_entropy}
 
-The following are deprecated in favor of `mean_pairwise_squared_error` and
-`mean_squared_error`.
-@{tf.contrib.losses.sum_of_pairwise_squares}
-@{tf.contrib.losses.sum_of_squares}
-
 

tensorflow/docs_src/get_started/tflearn.md

@@ -278,7 +278,7 @@ Then, the code creates a `DNNClassifier` model using the following arguments:
 
 The `tf.contrib.learn` API uses input functions, which create the TensorFlow
 operations that generate data for the model. In this case, the data is small
-enough that it can be stored in @{tf.constant TensorFlow constants}. The
+enough that it can be stored in @{tf.constant$TensorFlow constants}. The
 following code produces the simplest possible input pipeline:
 
 ```python

tensorflow/tools/docs/generate_lib.py

@@ -190,7 +190,6 @@ def _get_default_do_not_descend_map():
           'tensor_forest',
           'tensorboard',
           'testing',
-          'training',
           'tfprof',
       ],
       'contrib.bayesflow': [