Update generated Python Op docs.

Change: 143626185

tensorflow/g3doc/api_docs/python/contrib.framework.md

@@ -983,3 +983,135 @@ save memory during initialization.
 *  <b>`ValueError`</b>: If ref tensor is initialized.
 
 
+
+## Checkpoint utilities
+
+- - -
+
+### `tf.contrib.framework.load_checkpoint(filepattern)` {#load_checkpoint}
+
+Returns CheckpointReader for latest checkpoint.
+
+##### Args:
+
+
+*  <b>`filepattern`</b>: Directory with checkpoints file or path to checkpoint.
+
+##### Returns:
+
+  `CheckpointReader` object.
+
+##### Raises:
+
+
+*  <b>`ValueError`</b>: if checkpoint_dir doesn't have 'checkpoint' file or checkpoints.
+
+
+- - -
+
+### `tf.contrib.framework.list_variables(checkpoint_dir)` {#list_variables}
+
+Returns list of all variables in the latest checkpoint.
+
+##### Args:
+
+
+*  <b>`checkpoint_dir`</b>: Directory with checkpoints file or path to checkpoint.
+
+##### Returns:
+
+  List of tuples `(name, shape)`.
+
+
+- - -
+
+### `tf.contrib.framework.load_variable(checkpoint_dir, name)` {#load_variable}
+
+Returns a Tensor with the contents of the given variable in the checkpoint.
+
+##### Args:
+
+
+*  <b>`checkpoint_dir`</b>: Directory with checkpoints file or path to checkpoint.
+*  <b>`name`</b>: Name of the tensor to return.
+
+##### Returns:
+
+  `Tensor` object.
+
+
+- - -
+
+### `tf.contrib.framework.init_from_checkpoint(checkpoint_dir, assignment_map)` {#init_from_checkpoint}
+
+Using assingment map initializes current variables with loaded tensors.
+
+Note: This overrides default initialization ops of specified variables and
+redefines dtype.
+
+##### Assignment map supports following syntax:
+
+  `'checkpoint_scope_name/': 'scope_name/'` - will load all variables in
+    current `scope_name` from `checkpoint_scope_name` with matching variable
+    names.
+  `'checkpoint_scope_name/some_other_variable': 'scope_name/variable_name'` -
+    will initalize `scope_name/variable_name` variable
+    from `checkpoint_scope_name/some_other_variable`.
+  `'scope_variable_name': variable` - will initialize given `tf.Variable`
+    object with variable from the checkpoint.
+  `'scope_variable_name': list(variable)` - will initialize list of
+    partitioned variables with variable from the checkpoint.
+  `'/': 'scope_name/'` - will load all variables in current `scope_name` from
+    checkpoint's root (e.g. no scope).
+
+Supports loading into partitioned variables, which are represented as
+'<variable>/part_<part #>'.
+
+
+*  <b>`Example`</b>: 
+```python
+  # Create variables.
+  with tf.variable_scope('test'):
+    m = tf.get_variable('my_var')
+  with tf.variable_scope('test2'):
+    var2 = tf.get_variable('my_var')
+  var3 = tf.get_variable(name="my1", shape=[100, 100],
+                         partitioner=lambda shape, dtype: [5, 1])
+  ...
+  # Specify which variables to intialize from checkpoint.
+  init_from_checkpoint(checkpoint_dir, {
+    'some_var': 'test/my_var',
+    'some_scope/': 'test2/'})
+  ...
+  # Or use `Variable` objects to identify what to initialize.
+  init_from_checkpoint(checkpoint_dir, {
+    'some_scope/var2': var2,
+  })
+  # Initialize partitioned variables
+  init_from_checkpoint(checkpoint_dir, {
+    'some_var_from_ckpt': 'part_var',
+  })
+  # Or specifying the list of `Variable` objects.
+  init_from_checkpoint(checkpoint_dir, {
+    'some_var_from_ckpt': var3._get_variable_list(),
+  })
+  ...
+  # Initialize variables as usual.
+  session.run(tf.get_all_variables())
+```
+
+##### Args:
+
+
+*  <b>`checkpoint_dir`</b>: Directory with checkpoints file or path to checkpoint.
+*  <b>`assignment_map`</b>: Dict, where keys are names of the variables in the
+    checkpoint and values are current variables or names of current variables
+    (in default graph).
+
+##### Raises:
+
+  tf.errors.OpError: If missing checkpoints or tensors in checkpoints.
+
+*  <b>`ValueError`</b>: If missing variables in current graph.
+
+

tensorflow/g3doc/api_docs/python/functions_and_classes/shard1/tf.contrib.framework.init_from_checkpoint.md

+### `tf.contrib.framework.init_from_checkpoint(checkpoint_dir, assignment_map)` {#init_from_checkpoint}
+
+Using assingment map initializes current variables with loaded tensors.
+
+Note: This overrides default initialization ops of specified variables and
+redefines dtype.
+
+##### Assignment map supports following syntax:
+
+  `'checkpoint_scope_name/': 'scope_name/'` - will load all variables in
+    current `scope_name` from `checkpoint_scope_name` with matching variable
+    names.
+  `'checkpoint_scope_name/some_other_variable': 'scope_name/variable_name'` -
+    will initalize `scope_name/variable_name` variable
+    from `checkpoint_scope_name/some_other_variable`.
+  `'scope_variable_name': variable` - will initialize given `tf.Variable`
+    object with variable from the checkpoint.
+  `'scope_variable_name': list(variable)` - will initialize list of
+    partitioned variables with variable from the checkpoint.
+  `'/': 'scope_name/'` - will load all variables in current `scope_name` from
+    checkpoint's root (e.g. no scope).
+
+Supports loading into partitioned variables, which are represented as
+'<variable>/part_<part #>'.
+
+
+*  <b>`Example`</b>: 
+```python
+  # Create variables.
+  with tf.variable_scope('test'):
+    m = tf.get_variable('my_var')
+  with tf.variable_scope('test2'):
+    var2 = tf.get_variable('my_var')
+  var3 = tf.get_variable(name="my1", shape=[100, 100],
+                         partitioner=lambda shape, dtype: [5, 1])
+  ...
+  # Specify which variables to intialize from checkpoint.
+  init_from_checkpoint(checkpoint_dir, {
+    'some_var': 'test/my_var',
+    'some_scope/': 'test2/'})
+  ...
+  # Or use `Variable` objects to identify what to initialize.
+  init_from_checkpoint(checkpoint_dir, {
+    'some_scope/var2': var2,
+  })
+  # Initialize partitioned variables
+  init_from_checkpoint(checkpoint_dir, {
+    'some_var_from_ckpt': 'part_var',
+  })
+  # Or specifying the list of `Variable` objects.
+  init_from_checkpoint(checkpoint_dir, {
+    'some_var_from_ckpt': var3._get_variable_list(),
+  })
+  ...
+  # Initialize variables as usual.
+  session.run(tf.get_all_variables())
+```
+
+##### Args:
+
+
+*  <b>`checkpoint_dir`</b>: Directory with checkpoints file or path to checkpoint.
+*  <b>`assignment_map`</b>: Dict, where keys are names of the variables in the
+    checkpoint and values are current variables or names of current variables
+    (in default graph).
+
+##### Raises:
+
+  tf.errors.OpError: If missing checkpoints or tensors in checkpoints.
+
+*  <b>`ValueError`</b>: If missing variables in current graph.
+

tensorflow/g3doc/api_docs/python/functions_and_classes/shard2/tf.contrib.framework.load_checkpoint.md

+### `tf.contrib.framework.load_checkpoint(filepattern)` {#load_checkpoint}
+
+Returns CheckpointReader for latest checkpoint.
+
+##### Args:
+
+
+*  <b>`filepattern`</b>: Directory with checkpoints file or path to checkpoint.
+
+##### Returns:
+
+  `CheckpointReader` object.
+
+##### Raises:
+
+
+*  <b>`ValueError`</b>: if checkpoint_dir doesn't have 'checkpoint' file or checkpoints.
+

tensorflow/g3doc/api_docs/python/functions_and_classes/shard4/tf.contrib.framework.load_variable.md

+### `tf.contrib.framework.load_variable(checkpoint_dir, name)` {#load_variable}
+
+Returns a Tensor with the contents of the given variable in the checkpoint.
+
+##### Args:
+
+
+*  <b>`checkpoint_dir`</b>: Directory with checkpoints file or path to checkpoint.
+*  <b>`name`</b>: Name of the tensor to return.
+
+##### Returns:
+
+  `Tensor` object.
+

tensorflow/g3doc/api_docs/python/functions_and_classes/shard5/tf.contrib.framework.list_variables.md

+### `tf.contrib.framework.list_variables(checkpoint_dir)` {#list_variables}
+
+Returns list of all variables in the latest checkpoint.
+
+##### Args:
+
+
+*  <b>`checkpoint_dir`</b>: Directory with checkpoints file or path to checkpoint.
+
+##### Returns:
+
+  List of tuples `(name, shape)`.
+

tensorflow/g3doc/api_docs/python/index.md

@@ -834,10 +834,14 @@
   * [`get_variables_by_suffix`](../../api_docs/python/contrib.framework.md#get_variables_by_suffix)
   * [`get_variables_to_restore`](../../api_docs/python/contrib.framework.md#get_variables_to_restore)
   * [`has_arg_scope`](../../api_docs/python/contrib.framework.md#has_arg_scope)
+  * [`init_from_checkpoint`](../../api_docs/python/contrib.framework.md#init_from_checkpoint)
   * [`is_non_decreasing`](../../api_docs/python/contrib.framework.md#is_non_decreasing)
   * [`is_numeric_tensor`](../../api_docs/python/contrib.framework.md#is_numeric_tensor)
   * [`is_strictly_increasing`](../../api_docs/python/contrib.framework.md#is_strictly_increasing)
   * [`is_tensor`](../../api_docs/python/contrib.framework.md#is_tensor)
+  * [`list_variables`](../../api_docs/python/contrib.framework.md#list_variables)
+  * [`load_checkpoint`](../../api_docs/python/contrib.framework.md#load_checkpoint)
+  * [`load_variable`](../../api_docs/python/contrib.framework.md#load_variable)
   * [`local_variable`](../../api_docs/python/contrib.framework.md#local_variable)
   * [`model_variable`](../../api_docs/python/contrib.framework.md#model_variable)
   * [`reduce_sum_n`](../../api_docs/python/contrib.framework.md#reduce_sum_n)