Python network_units.get_attrs_with_defaults方法代碼示例

# 需要導入模塊: from dragnn.python import network_units [as 別名]
# 或者: from dragnn.python.network_units import get_attrs_with_defaults [as 別名]
def MakeAttrs(self, defaults, key=None, value=None):
    """Returns attrs based on the |defaults| and one |key|,|value| override."""
    spec = spec_pb2.RegisteredModuleSpec()
    if key and value:
      spec.parameters[key] = value
    return network_units.get_attrs_with_defaults(spec.parameters, defaults) 

# 需要導入模塊: from dragnn.python import network_units [as 別名]
# 或者: from dragnn.python.network_units import get_attrs_with_defaults [as 別名]
def __init__(self, component):
    """Initializes layers.

    Args:
      component: Parent ComponentBuilderBase object.
    """
    layers = [
        network_units.Layer(self, 'lengths', -1),
        network_units.Layer(self, 'scores', -1),
        network_units.Layer(self, 'logits', -1),
        network_units.Layer(self, 'arcs', -1),
    ]
    super(MstSolverNetwork, self).__init__(component, init_layers=layers)

    self._attrs = network_units.get_attrs_with_defaults(
        component.spec.network_unit.parameters,
        defaults={
            'forest': False,
            'loss': 'softmax',
            'crf_max_dynamic_range': 20,
        })

    check.Eq(
        len(self._fixed_feature_dims.items()), 0, 'Expected no fixed features')
    check.Eq(
        len(self._linked_feature_dims.items()), 2,
        'Expected two linked features')

    check.In('lengths', self._linked_feature_dims,
             'Missing required linked feature')
    check.In('scores', self._linked_feature_dims,
             'Missing required linked feature') 

# 需要導入模塊: from dragnn.python import network_units [as 別名]
# 或者: from dragnn.python.network_units import get_attrs_with_defaults [as 別名]
def __init__(self, master, component_spec, attr_defaults=None):
    """Initializes the ComponentBuilder from specifications.

    Args:
      master: dragnn.MasterBuilder object.
      component_spec: dragnn.ComponentSpec proto to be built.
      attr_defaults: Optional dict of component attribute defaults.  If not
          provided or if empty, attributes are not extracted.
    """
    self.master = master
    self.num_actions = component_spec.num_actions
    self.name = component_spec.name
    self.spec = component_spec
    self.moving_average = None

    # Determine if this component should apply self-normalization.
    self.eligible_for_self_norm = (
        not self.master.hyperparams.self_norm_components_filter or self.name in
        self.master.hyperparams.self_norm_components_filter.split(','))

    # Extract component attributes before make_network(), so the network unit
    # can access them.
    self._attrs = {}
    if attr_defaults:
      self._attrs = network_units.get_attrs_with_defaults(
          self.spec.component_builder.parameters, attr_defaults)

    with tf.variable_scope(self.name):
      self.training_beam_size = tf.constant(
          self.spec.training_beam_size, name='TrainingBeamSize')
      self.inference_beam_size = tf.constant(
          self.spec.inference_beam_size, name='InferenceBeamSize')
      self.locally_normalize = tf.constant(False, name='LocallyNormalize')
      self._step = tf.get_variable(
          'step', [], initializer=tf.zeros_initializer(), dtype=tf.int32)
      self._total = tf.get_variable(
          'total', [], initializer=tf.zeros_initializer(), dtype=tf.int32)

    # Construct network variables.
    self.network = self.make_network(self.spec.network_unit)

    # Construct moving average.
    if self.master.hyperparams.use_moving_average:
      self.moving_average = tf.train.ExponentialMovingAverage(
          decay=self.master.hyperparams.average_weight, num_updates=self._step)
      self.avg_ops = [self.moving_average.apply(self.network.params)] 

# 需要導入模塊: from dragnn.python import network_units [as 別名]
# 或者: from dragnn.python.network_units import get_attrs_with_defaults [as 別名]
def __init__(self, master, component_spec, attr_defaults=None):
    """Initializes the ComponentBuilder from specifications.

    Args:
      master: dragnn.MasterBuilder object.
      component_spec: dragnn.ComponentSpec proto to be built.
      attr_defaults: Optional dict of component attribute defaults.  If not
          provided or if empty, attributes are not extracted.
    """
    self.master = master
    self.num_actions = component_spec.num_actions
    self.name = component_spec.name
    self.spec = component_spec
    self.moving_average = None

    # Determine if this component should apply self-normalization.
    self.eligible_for_self_norm = (
        not self.master.hyperparams.self_norm_components_filter or self.name in
        self.master.hyperparams.self_norm_components_filter.split(','))

    # Extract component attributes before make_network(), so the network unit
    # can access them.
    self._attrs = {}
    global_attr_defaults = {
        'locally_normalize': False,
        'output_as_probabilities': False
    }
    if attr_defaults:
      global_attr_defaults.update(attr_defaults)
    self._attrs = network_units.get_attrs_with_defaults(
        self.spec.component_builder.parameters, global_attr_defaults)
    do_local_norm = self._attrs['locally_normalize']
    self._output_as_probabilities = self._attrs['output_as_probabilities']
    with tf.variable_scope(self.name):
      self.training_beam_size = tf.constant(
          self.spec.training_beam_size, name='TrainingBeamSize')
      self.inference_beam_size = tf.constant(
          self.spec.inference_beam_size, name='InferenceBeamSize')
      self.locally_normalize = tf.constant(
          do_local_norm, name='LocallyNormalize')
      self._step = tf.get_variable(
          'step', [], initializer=tf.zeros_initializer(), dtype=tf.int32)
      self._total = tf.get_variable(
          'total', [], initializer=tf.zeros_initializer(), dtype=tf.int32)

    # Construct network variables.
    self.network = self.make_network(self.spec.network_unit)

    # Construct moving average.
    if self.master.hyperparams.use_moving_average:
      self.moving_average = tf.train.ExponentialMovingAverage(
          decay=self.master.hyperparams.average_weight, num_updates=self._step)
      self.avg_ops = [self.moving_average.apply(self.network.params)]

    # Used to export the cell; see add_cell_input() and add_cell_output().
    self._cell_subgraph_spec = export_pb2.CellSubgraphSpec()