diff options
author | A. Unique TensorFlower <gardener@tensorflow.org> | 2016-11-01 12:53:22 -0800 |
---|---|---|
committer | TensorFlower Gardener <gardener@tensorflow.org> | 2016-11-01 14:17:38 -0700 |
commit | 1dadfdd27650e21e0c679e615ddd377f380c574a (patch) | |
tree | d4cca1b0cfb53f1dd5966329ba339e380de498d4 | |
parent | 99f55f806f426a50c01dd06bd71a478009a84af2 (diff) |
Update generated Python Op docs.
Change: 137866950
-rw-r--r-- | tensorflow/g3doc/api_docs/python/contrib.distributions.md | 117 |
1 files changed, 60 insertions, 57 deletions
diff --git a/tensorflow/g3doc/api_docs/python/contrib.distributions.md b/tensorflow/g3doc/api_docs/python/contrib.distributions.md index bc4a79cf85..a86285a019 100644 --- a/tensorflow/g3doc/api_docs/python/contrib.distributions.md +++ b/tensorflow/g3doc/api_docs/python/contrib.distributions.md @@ -17325,62 +17325,6 @@ Variance. -- - - - -### `tf.contrib.distributions.matrix_diag_transform(matrix, transform=None, name=None)` {#matrix_diag_transform} - -Transform diagonal of [batch-]matrix, leave rest of matrix unchanged. - -Create a trainable covariance defined by a Cholesky factor: - -```python -# Transform network layer into 2 x 2 array. -matrix_values = tf.contrib.layers.fully_connected(activations, 4) -matrix = tf.reshape(matrix_values, (batch_size, 2, 2)) - -# Make the diagonal positive. If the upper triangle was zero, this would be a -# valid Cholesky factor. -chol = matrix_diag_transform(matrix, transform=tf.nn.softplus) - -# OperatorPDCholesky ignores the upper triangle. -operator = OperatorPDCholesky(chol) -``` - -Example of heteroskedastic 2-D linear regression. - -```python -# Get a trainable Cholesky factor. -matrix_values = tf.contrib.layers.fully_connected(activations, 4) -matrix = tf.reshape(matrix_values, (batch_size, 2, 2)) -chol = matrix_diag_transform(matrix, transform=tf.nn.softplus) - -# Get a trainable mean. -mu = tf.contrib.layers.fully_connected(activations, 2) - -# This is a fully trainable multivariate normal! -dist = tf.contrib.distributions.MVNCholesky(mu, chol) - -# Standard log loss. Minimizing this will "train" mu and chol, and then dist -# will be a distribution predicting labels as multivariate Gaussians. -loss = -1 * tf.reduce_mean(dist.log_pdf(labels)) -``` - -##### Args: - - -* <b>`matrix`</b>: Rank `R` `Tensor`, `R >= 2`, where the last two dimensions are - equal. -* <b>`transform`</b>: Element-wise function mapping `Tensors` to `Tensors`. To - be applied to the diagonal of `matrix`. If `None`, `matrix` is returned - unchanged. Defaults to `None`. -* <b>`name`</b>: A name to give created ops. - Defaults to "matrix_diag_transform". - -##### Returns: - - A `Tensor` with same shape and `dtype` as `matrix`. - - ### Other multivariate distributions @@ -20793,6 +20737,65 @@ Variance. +### Multivariate Utilities + +- - - + +### `tf.contrib.distributions.matrix_diag_transform(matrix, transform=None, name=None)` {#matrix_diag_transform} + +Transform diagonal of [batch-]matrix, leave rest of matrix unchanged. + +Create a trainable covariance defined by a Cholesky factor: + +```python +# Transform network layer into 2 x 2 array. +matrix_values = tf.contrib.layers.fully_connected(activations, 4) +matrix = tf.reshape(matrix_values, (batch_size, 2, 2)) + +# Make the diagonal positive. If the upper triangle was zero, this would be a +# valid Cholesky factor. +chol = matrix_diag_transform(matrix, transform=tf.nn.softplus) + +# OperatorPDCholesky ignores the upper triangle. +operator = OperatorPDCholesky(chol) +``` + +Example of heteroskedastic 2-D linear regression. + +```python +# Get a trainable Cholesky factor. +matrix_values = tf.contrib.layers.fully_connected(activations, 4) +matrix = tf.reshape(matrix_values, (batch_size, 2, 2)) +chol = matrix_diag_transform(matrix, transform=tf.nn.softplus) + +# Get a trainable mean. +mu = tf.contrib.layers.fully_connected(activations, 2) + +# This is a fully trainable multivariate normal! +dist = tf.contrib.distributions.MVNCholesky(mu, chol) + +# Standard log loss. Minimizing this will "train" mu and chol, and then dist +# will be a distribution predicting labels as multivariate Gaussians. +loss = -1 * tf.reduce_mean(dist.log_pdf(labels)) +``` + +##### Args: + + +* <b>`matrix`</b>: Rank `R` `Tensor`, `R >= 2`, where the last two dimensions are + equal. +* <b>`transform`</b>: Element-wise function mapping `Tensors` to `Tensors`. To + be applied to the diagonal of `matrix`. If `None`, `matrix` is returned + unchanged. Defaults to `None`. +* <b>`name`</b>: A name to give created ops. + Defaults to "matrix_diag_transform". + +##### Returns: + + A `Tensor` with same shape and `dtype` as `matrix`. + + + ## Transformed distributions - - - @@ -23052,7 +23055,7 @@ will broadcast in the case of multidimensional sets of parameters. -## Kullback Leibler Divergence +## Kullback-Leibler Divergence - - - |