Python tensorflow.python.ops.variables.local_variables() Examples

def get_epoch_variable():
  """Returns the epoch variable, or [0] if not defined."""
  # Grab epoch variable defined in
  # //third_party/tensorflow/python/training/input.py::limit_epochs
  for v in tf_variables.local_variables():
    if 'limit_epochs/epoch' in v.op.name:
      return array_ops.reshape(v, [1])
  # TODO(thomaswc): Access epoch from the data feeder.
  return [0]


# A simple container to hold the training variables for a single tree. 

def get_epoch_variable():
  """Returns the epoch variable, or [0] if not defined."""
  # Grab epoch variable defined in
  # //third_party/tensorflow/python/training/input.py::limit_epochs
  for v in tf_variables.local_variables():
    if 'limit_epochs/epoch' in v.op.name:
      return array_ops.reshape(v, [1])
  # TODO(thomaswc): Access epoch from the data feeder.
  return [0]


# A simple container to hold the training variables for a single tree. 

def testVars(self):
    classification.f1_score(
        predictions=array_ops.ones((10, 1)),
        labels=array_ops.ones((10, 1)),
        num_thresholds=3)
    expected = {'f1/true_positives:0', 'f1/false_positives:0',
                'f1/false_negatives:0'}
    self.assertEqual(
        expected, set(v.name for v in variables.local_variables()))
    self.assertEqual(
        set(expected), set(v.name for v in variables.local_variables()))
    self.assertEqual(
        set(expected),
        set(v.name for v in ops.get_collection(ops.GraphKeys.METRIC_VARIABLES))) 

def test_local_variable(self):
    with self.cached_session() as sess:
      self.assertEqual([], variables_lib.local_variables())
      value0 = 42
      variables_lib2.local_variable(value0)
      value1 = 43
      variables_lib2.local_variable(value1)
      variables = variables_lib.local_variables()
      self.assertEqual(2, len(variables))
      self.assertRaises(errors_impl.OpError, sess.run, variables)
      variables_lib.variables_initializer(variables).run()
      self.assertAllEqual(set([value0, value1]), set(sess.run(variables))) 

def testLocalVariableNotInAllVariables(self):
    with self.cached_session():
      with variable_scope.variable_scope('A'):
        a = variables_lib2.local_variable(0)
        self.assertNotIn(a, variables_lib.global_variables())
        self.assertIn(a, variables_lib.local_variables()) 

def testLocalVariableNotInVariablesToRestore(self):
    with self.cached_session():
      with variable_scope.variable_scope('A'):
        a = variables_lib2.local_variable(0)
        self.assertNotIn(a, variables_lib2.get_variables_to_restore())
        self.assertIn(a, variables_lib.local_variables()) 

def testGlobalVariableNotInLocalVariables(self):
    with self.cached_session():
      with variable_scope.variable_scope('A'):
        a = variables_lib2.global_variable(0)
        self.assertNotIn(a, variables_lib.local_variables())
        self.assertIn(a, variables_lib.global_variables()) 

def testCreateVariable(self):
    with self.cached_session():
      with variable_scope.variable_scope('A'):
        a = variables_lib2.variable('a', [5])
        self.assertEqual(a.op.name, 'A/a')
        self.assertListEqual(a.get_shape().as_list(), [5])
        self.assertIn(a, ops.get_collection(ops.GraphKeys.GLOBAL_VARIABLES))
        self.assertNotIn(a, ops.get_collection(ops.GraphKeys.MODEL_VARIABLES))
        self.assertNotIn(a, variables_lib.local_variables()) 

def testNotInLocalVariables(self):
    with self.cached_session():
      with variable_scope.variable_scope('A'):
        a = variables_lib2.model_variable('a', [5])
        self.assertIn(a, variables_lib.global_variables())
        self.assertIn(a, ops.get_collection(ops.GraphKeys.MODEL_VARIABLES))
        self.assertNotIn(a, variables_lib.local_variables()) 

def get_epoch_variable():
  """Returns the epoch variable, or [0] if not defined."""
  # Grab epoch variable defined in
  # //third_party/tensorflow/python/training/input.py::limit_epochs
  for v in tf_variables.local_variables():
    if 'limit_epochs/epoch' in v.op.name:
      return array_ops.reshape(v, [1])
  # TODO(thomaswc): Access epoch from the data feeder.
  return [0]


# A simple container to hold the training variables for a single tree. 

def run(self,
          num_batches=None,
          graph=None,
          session=None,
          start_queues=True,
          initialize_variables=True,
          **kwargs):
    """Builds and runs the columns of the `DataFrame` and yields batches.

    This is a generator that yields a dictionary mapping column names to
    evaluated columns.

    Args:
      num_batches: the maximum number of batches to produce. If none specified,
        the returned value will iterate through infinite batches.
      graph: the `Graph` in which the `DataFrame` should be built.
      session: the `Session` in which to run the columns of the `DataFrame`.
      start_queues: if true, queues will be started before running and halted
        after producting `n` batches.
      initialize_variables: if true, variables will be initialized.
      **kwargs: Additional keyword arguments e.g. `num_epochs`.

    Yields:
      A dictionary, mapping column names to the values resulting from running
      each column for a single batch.
    """
    if graph is None:
      graph = ops.get_default_graph()
    with graph.as_default():
      if session is None:
        session = sess.Session()
      self_built = self.build(**kwargs)
      keys = list(self_built.keys())
      cols = list(self_built.values())
      if initialize_variables:
        if variables.local_variables():
          session.run(variables.local_variables_initializer())
        if variables.global_variables():
          session.run(variables.global_variables_initializer())
      if start_queues:
        coord = coordinator.Coordinator()
        threads = qr.start_queue_runners(sess=session, coord=coord)
      i = 0
      while num_batches is None or i < num_batches:
        i += 1
        try:
          values = session.run(cols)
          yield collections.OrderedDict(zip(keys, values))
        except errors.OutOfRangeError:
          break
      if start_queues:
        coord.request_stop()
        coord.join(threads) 

def run(self,
          num_batches=None,
          graph=None,
          session=None,
          start_queues=True,
          initialize_variables=True,
          **kwargs):
    """Builds and runs the columns of the `DataFrame` and yields batches.

    This is a generator that yields a dictionary mapping column names to
    evaluated columns.

    Args:
      num_batches: the maximum number of batches to produce. If none specified,
        the returned value will iterate through infinite batches.
      graph: the `Graph` in which the `DataFrame` should be built.
      session: the `Session` in which to run the columns of the `DataFrame`.
      start_queues: if true, queues will be started before running and halted
        after producting `n` batches.
      initialize_variables: if true, variables will be initialized.
      **kwargs: Additional keyword arguments e.g. `num_epochs`.

    Yields:
      A dictionary, mapping column names to the values resulting from running
      each column for a single batch.
    """
    if graph is None:
      graph = ops.get_default_graph()
    with graph.as_default():
      if session is None:
        session = sess.Session()
      self_built = self.build(**kwargs)
      keys = list(self_built.keys())
      cols = list(self_built.values())
      if initialize_variables:
        if variables.local_variables():
          session.run(variables.local_variables_initializer())
        if variables.global_variables():
          session.run(variables.global_variables_initializer())
      if start_queues:
        coord = coordinator.Coordinator()
        threads = qr.start_queue_runners(sess=session, coord=coord)
      i = 0
      while num_batches is None or i < num_batches:
        i += 1
        try:
          values = session.run(cols)
          yield collections.OrderedDict(zip(keys, values))
        except errors.OutOfRangeError:
          break
      if start_queues:
        coord.request_stop()
        coord.join(threads) 

def run(self,
          num_batches=None,
          graph=None,
          session=None,
          start_queues=True,
          initialize_variables=True,
          **kwargs):
    """Builds and runs the columns of the `DataFrame` and yields batches.

    This is a generator that yields a dictionary mapping column names to
    evaluated columns.

    Args:
      num_batches: the maximum number of batches to produce. If none specified,
        the returned value will iterate through infinite batches.
      graph: the `Graph` in which the `DataFrame` should be built.
      session: the `Session` in which to run the columns of the `DataFrame`.
      start_queues: if true, queues will be started before running and halted
        after producting `n` batches.
      initialize_variables: if true, variables will be initialized.
      **kwargs: Additional keyword arguments e.g. `num_epochs`.

    Yields:
      A dictionary, mapping column names to the values resulting from running
      each column for a single batch.
    """
    if graph is None:
      graph = ops.get_default_graph()
    with graph.as_default():
      if session is None:
        session = sess.Session()
      self_built = self.build(**kwargs)
      keys = list(self_built.keys())
      cols = list(self_built.values())
      if initialize_variables:
        if variables.local_variables():
          session.run(variables.local_variables_initializer())
        if variables.global_variables():
          session.run(variables.global_variables_initializer())
      if start_queues:
        coord = coordinator.Coordinator()
        threads = qr.start_queue_runners(sess=session, coord=coord)
      i = 0
      while num_batches is None or i < num_batches:
        i += 1
        try:
          values = session.run(cols)
          yield collections.OrderedDict(zip(keys, values))
        except errors.OutOfRangeError:
          break
      if start_queues:
        coord.request_stop()
        coord.join(threads) 

def run(self,
          num_batches=None,
          graph=None,
          session=None,
          start_queues=True,
          initialize_variables=True,
          **kwargs):
    """Builds and runs the columns of the `DataFrame` and yields batches.

    This is a generator that yields a dictionary mapping column names to
    evaluated columns.

    Args:
      num_batches: the maximum number of batches to produce. If none specified,
        the returned value will iterate through infinite batches.
      graph: the `Graph` in which the `DataFrame` should be built.
      session: the `Session` in which to run the columns of the `DataFrame`.
      start_queues: if true, queues will be started before running and halted
        after producting `n` batches.
      initialize_variables: if true, variables will be initialized.
      **kwargs: Additional keyword arguments e.g. `num_epochs`.

    Yields:
      A dictionary, mapping column names to the values resulting from running
      each column for a single batch.
    """
    if graph is None:
      graph = ops.get_default_graph()
    with graph.as_default():
      if session is None:
        session = sess.Session()
      self_built = self.build(**kwargs)
      keys = list(self_built.keys())
      cols = list(self_built.values())
      if initialize_variables:
        if variables.local_variables():
          session.run(variables.local_variables_initializer())
        if variables.global_variables():
          session.run(variables.global_variables_initializer())
      if start_queues:
        coord = coordinator.Coordinator()
        threads = qr.start_queue_runners(sess=session, coord=coord)
      i = 0
      while num_batches is None or i < num_batches:
        i += 1
        try:
          values = session.run(cols)
          yield collections.OrderedDict(zip(keys, values))
        except errors.OutOfRangeError:
          break
      if start_queues:
        coord.request_stop()
        coord.join(threads)