Python tensorflow.python.ops.init_ops.zeros_initializer() Examples

def vgg_arg_scope(weight_decay=0.0005):
  """Defines the VGG arg scope.

  Args:
    weight_decay: The l2 regularization coefficient.

  Returns:
    An arg_scope.
  """
  with arg_scope(
      [layers.conv2d, layers_lib.fully_connected],
      activation_fn=nn_ops.relu,
      weights_regularizer=regularizers.l2_regularizer(weight_decay),
      biases_initializer=init_ops.zeros_initializer()):
    with arg_scope([layers.conv2d], padding='SAME') as arg_sc:
      return arg_sc 

def _create_baseline(self, n_output=1, n_hidden=100,
                       is_zero_init=False,
                       collection='BASELINE'):
    # center input
    h = self._x
    if self.mean_xs is not None:
      h -= self.mean_xs

    if is_zero_init:
      initializer = init_ops.zeros_initializer()
    else:
      initializer = slim.variance_scaling_initializer()

    with slim.arg_scope([slim.fully_connected],
                        variables_collections=[collection, Q_COLLECTION],
                        trainable=False,
                        weights_initializer=initializer):
      h = slim.fully_connected(h, n_hidden, activation_fn=tf.nn.tanh)
      baseline = slim.fully_connected(h, n_output, activation_fn=None)

      if n_output == 1:
        baseline = tf.reshape(baseline, [-1])  # very important to reshape
    return baseline 

def vgg_arg_scope(weight_decay=0.0005):
  """Defines the VGG arg scope.

  Args:
    weight_decay: The l2 regularization coefficient.

  Returns:
    An arg_scope.
  """
  with arg_scope(
      [layers.conv2d, layers_lib.fully_connected],
      activation_fn=nn_ops.relu,
      weights_regularizer=regularizers.l2_regularizer(weight_decay),
      biases_initializer=init_ops.zeros_initializer()):
    with arg_scope([layers.conv2d], padding='SAME') as arg_sc:
      return arg_sc 

def vgg_arg_scope(weight_decay=0.0005):
  """Defines the VGG arg scope.

  Args:
    weight_decay: The l2 regularization coefficient.

  Returns:
    An arg_scope.
  """
  with arg_scope(
      [layers.conv2d, layers_lib.fully_connected],
      activation_fn=nn_ops.relu,
      weights_regularizer=regularizers.l2_regularizer(weight_decay),
      biases_initializer=init_ops.zeros_initializer()):
    with arg_scope([layers.conv2d], padding='SAME') as arg_sc:
      return arg_sc 

def _create_baseline(self, n_output=1, n_hidden=100,
                       is_zero_init=False,
                       collection='BASELINE'):
    # center input
    h = self._x
    if self.mean_xs is not None:
      h -= self.mean_xs

    if is_zero_init:
      initializer = init_ops.zeros_initializer()
    else:
      initializer = slim.variance_scaling_initializer()

    with slim.arg_scope([slim.fully_connected],
                        variables_collections=[collection, Q_COLLECTION],
                        trainable=False,
                        weights_initializer=initializer):
      h = slim.fully_connected(h, n_hidden, activation_fn=tf.nn.tanh)
      baseline = slim.fully_connected(h, n_output, activation_fn=None)

      if n_output == 1:
        baseline = tf.reshape(baseline, [-1])  # very important to reshape
    return baseline 

def vgg_arg_scope(weight_decay=0.0005):
    """Defines the VGG arg scope.

    Args:
      weight_decay: The l2 regularization coefficient.

    Returns:
      An arg_scope.
    """
    with arg_scope(
        [layers.conv2d, layers_lib.fully_connected],
        activation_fn=nn_ops.relu,
        weights_regularizer=regularizers.l2_regularizer(weight_decay),
        biases_initializer=init_ops.zeros_initializer()
    ):
        with arg_scope([layers.conv2d], padding='SAME') as arg_sc:
            return arg_sc 

def __init__(self, units,
               activation=None,
               use_bias=True,
               kernel_initializer=None,
               bias_initializer=init_ops.zeros_initializer(),
               kernel_regularizer=None,
               bias_regularizer=None,
               activity_regularizer=None,
               trainable=True,
               name=None,
               **kwargs):
    super(Dense, self).__init__(trainable=trainable, name=name, **kwargs)
    self.units = units
    self.activation = activation
    self.use_bias = use_bias
    self.kernel_initializer = kernel_initializer
    self.bias_initializer = bias_initializer
    self.kernel_regularizer = kernel_regularizer
    self.bias_regularizer = bias_regularizer
    self.activity_regularizer = activity_regularizer 

def _adaptive_max_norm(norm, std_factor, decay, global_step, epsilon, name):
  """Find max_norm given norm and previous average."""
  with vs.variable_scope(name, "AdaptiveMaxNorm", [norm]):
    log_norm = math_ops.log(norm + epsilon)

    def moving_average(name, value, decay):
      moving_average_variable = vs.get_variable(
          name, shape=value.get_shape(), dtype=value.dtype,
          initializer=init_ops.zeros_initializer, trainable=False)
      return moving_averages.assign_moving_average(
          moving_average_variable, value, decay, zero_debias=False)

    # quicker adaptation at the beginning
    if global_step is not None:
      n = math_ops.to_float(global_step)
      decay = math_ops.minimum(decay, n / (n + 1.))

    # update averages
    mean = moving_average("mean", log_norm, decay)
    sq_mean = moving_average("sq_mean", math_ops.square(log_norm), decay)

    variance = sq_mean - math_ops.square(mean)
    std = math_ops.sqrt(math_ops.maximum(epsilon, variance))
    max_norms = math_ops.exp(mean + std_factor*std)
    return max_norms, mean 

def __init__(self, units,
               activation=None,
               use_bias=True,
               kernel_initializer=None,
               bias_initializer=init_ops.zeros_initializer(),
               kernel_regularizer=None,
               bias_regularizer=None,
               activity_regularizer=None,
               trainable=True,
               name=None,
               **kwargs):
    super(Dense, self).__init__(trainable=trainable, name=name, **kwargs)
    self.units = units
    self.activation = activation
    self.use_bias = use_bias
    self.kernel_initializer = kernel_initializer
    self.bias_initializer = bias_initializer
    self.kernel_regularizer = kernel_regularizer
    self.bias_regularizer = bias_regularizer
    self.activity_regularizer = activity_regularizer
    self.input_spec = base.InputSpec(min_ndim=2) 

def _get_or_create_eval_step():
  """Gets or creates the eval step `Tensor`.

  Returns:
    A `Tensor` representing a counter for the evaluation step.

  Raises:
    ValueError: If multiple `Tensors` have been added to the
      `tf.GraphKeys.EVAL_STEP` collection.
  """
  graph = ops.get_default_graph()
  eval_steps = graph.get_collection(ops.GraphKeys.EVAL_STEP)
  if len(eval_steps) == 1:
    return eval_steps[0]
  elif len(eval_steps) > 1:
    raise ValueError('Multiple tensors added to tf.GraphKeys.EVAL_STEP')
  else:
    counter = variable_scope.get_variable(
        'eval_step',
        shape=[],
        dtype=dtypes.int64,
        initializer=init_ops.zeros_initializer(),
        trainable=False,
        collections=[ops.GraphKeys.LOCAL_VARIABLES, ops.GraphKeys.EVAL_STEP])
    return counter 

def _create_dense_column_weighted_sum(
    column, builder, units, weight_collections, trainable):
  """Create a weighted sum of a dense column for linear_model."""
  tensor = column._get_dense_tensor(  # pylint: disable=protected-access
      builder,
      weight_collections=weight_collections,
      trainable=trainable)
  num_elements = column._variable_shape.num_elements()  # pylint: disable=protected-access
  batch_size = array_ops.shape(tensor)[0]
  tensor = array_ops.reshape(tensor, shape=(batch_size, num_elements))
  weight = variable_scope.get_variable(
      name='weights',
      shape=[num_elements, units],
      initializer=init_ops.zeros_initializer(),
      trainable=trainable,
      collections=weight_collections)
  return math_ops.matmul(tensor, weight, name='weighted_sum') 

def create_global_step(graph=None):
  """Create global step tensor in graph.

  Args:
    graph: The graph in which to create the global step. If missing, use default
        graph.

  Returns:
    Global step tensor.

  Raises:
    ValueError: if global step key is already defined.
  """
  graph = ops.get_default_graph() if graph is None else graph
  if get_global_step(graph) is not None:
    raise ValueError('"global_step" already exists.')
  # Create in proper graph and base name_scope.
  with graph.as_default() as g, g.name_scope(None):
    collections = [ops.GraphKeys.GLOBAL_VARIABLES, ops.GraphKeys.GLOBAL_STEP]
    return variable(ops.GraphKeys.GLOBAL_STEP, shape=[], dtype=dtypes.int64,
                    initializer=init_ops.zeros_initializer, trainable=False,
                    collections=collections) 

def vgg_arg_scope(weight_decay=0.0005):
  """Defines the VGG arg scope.

  Args:
    weight_decay: The l2 regularization coefficient.

  Returns:
    An arg_scope.
  """
  with arg_scope(
      [layers.conv2d, layers_lib.fully_connected],
      activation_fn=nn_ops.relu,
      weights_regularizer=regularizers.l2_regularizer(weight_decay),
      biases_initializer=init_ops.zeros_initializer()):
    with arg_scope([layers.conv2d], padding='SAME') as arg_sc:
      return arg_sc 

def fully_connected(inputs, num_outputs, sn, activation_fn=None,
                    normalizer_fn=None, normalizer_params=None,
                    weights_initializer=ly.xavier_initializer(),
                    weight_decay_rate=1e-6,
                    biases_initializer=init_ops.zeros_initializer(),
                    biases_regularizer=None,
                    reuse=None, scope=None):
    # TODO move regularizer definitions to model
    weights_regularizer = ly.l2_regularizer(weight_decay_rate)

    input_dim = inputs.get_shape().as_list()[1]

    with tf.variable_scope(scope, 'fully_connected', [inputs], reuse=reuse) as sc:
        inputs = tf.convert_to_tensor(inputs)

        weights = tf.get_variable(name="weights", shape=(input_dim, num_outputs),
                                  initializer=weights_initializer, regularizer=weights_regularizer,
                                  trainable=True, dtype=inputs.dtype.base_dtype)

        # Spectral Normalization
        if sn:
            weights = spectral_normed_weight(weights, num_iters=1, update_collection=Config.SPECTRAL_NORM_UPDATE_OPS)

        linear_out = tf.matmul(inputs, weights)

        if biases_initializer is not None:
            biases = tf.get_variable(name="biases", shape=(num_outputs,),
                                     initializer=biases_initializer, regularizer=biases_regularizer,
                                     trainable=True, dtype=inputs.dtype.base_dtype)

        linear_out = tf.nn.bias_add(linear_out, biases)

        # Apply normalizer function / layer.
        if normalizer_fn is not None:
            normalizer_params = normalizer_params or {}
            linear_out = normalizer_fn(linear_out, activation_fn=None, **normalizer_params)

        if activation_fn is not None:
            linear_out = activation_fn(linear_out)

    return linear_out 

def _wide_embedding_lookup_arguments(self, input_tensor):
    return _LinearEmbeddingLookupArguments(
        input_tensor=self.to_sparse_tensor(input_tensor),
        weight_tensor=None,
        vocab_size=self.length * self.source_column.dimension,
        initializer=init_ops.zeros_initializer(),
        combiner="sum") 

def _wide_embedding_lookup_arguments(self, input_tensor):
    return _LinearEmbeddingLookupArguments(
        input_tensor=self.id_tensor(input_tensor),
        weight_tensor=self.weight_tensor(input_tensor),
        vocab_size=self.length,
        initializer=init_ops.zeros_initializer,
        combiner=self.sparse_id_column.combiner) 

def _create_global_step(graph):
  graph = graph or ops.get_default_graph()
  if training.get_global_step(graph) is not None:
    raise ValueError('"global_step" already exists.')
  # Create in proper graph and base name_scope.
  with graph.as_default() as g, g.name_scope(None):
    return variable_scope.get_variable(
        ops.GraphKeys.GLOBAL_STEP,
        shape=[],
        dtype=dtypes.int64,
        initializer=init_ops.zeros_initializer(),
        trainable=False,
        use_resource=True,
        collections=[ops.GraphKeys.GLOBAL_VARIABLES, ops.GraphKeys.GLOBAL_STEP]) 

def _wide_embedding_lookup_arguments(self, input_tensor):
    return _LinearEmbeddingLookupArguments(
        input_tensor=input_tensor,
        weight_tensor=None,
        vocab_size=self.length,
        initializer=init_ops.zeros_initializer,
        combiner=self.combiner) 

def _wide_embedding_lookup_arguments(self, input_tensor):
    return _LinearEmbeddingLookupArguments(
        input_tensor=self.to_sparse_tensor(input_tensor),
        weight_tensor=None,
        vocab_size=self.length * self.source_column.dimension,
        initializer=init_ops.zeros_initializer,
        combiner="sum") 

def _create_global_step(graph):
  graph = graph or ops.get_default_graph()
  if training.get_global_step(graph) is not None:
    raise ValueError('"global_step" already exists.')
  # Create in proper graph and base name_scope.
  with graph.as_default() as g, g.name_scope(None):
    return variable_scope.get_variable(
        ops.GraphKeys.GLOBAL_STEP,
        shape=[],
        dtype=dtypes.int64,
        initializer=init_ops.zeros_initializer(),
        trainable=False,
        use_resource=True,
        collections=[ops.GraphKeys.GLOBAL_VARIABLES, ops.GraphKeys.GLOBAL_STEP]) 

def convolution1d(inputs,
                  num_outputs,
                  kernel_size,
                  stride=1,
                  padding='SAME',
                  data_format=None,
                  rate=1,
                  activation_fn=nn.relu,
                  normalizer_fn=None,
                  normalizer_params=None,
                  weights_initializer=initializers.xavier_initializer(),
                  weights_regularizer=None,
                  biases_initializer=init_ops.zeros_initializer(),
                  biases_regularizer=None,
                  reuse=None,
                  variables_collections=None,
                  outputs_collections=None,
                  trainable=True,
                  scope=None):
  return convolution(
      inputs,
      num_outputs,
      kernel_size,
      stride,
      padding,
      data_format,
      rate,
      activation_fn,
      normalizer_fn,
      normalizer_params,
      weights_initializer,
      weights_regularizer,
      biases_initializer,
      biases_regularizer,
      reuse,
      variables_collections,
      outputs_collections,
      trainable,
      scope,
      conv_dims=1) 

def _auc_hist_accumulate(hist_true, hist_false, nbins, collections):
  """Accumulate histograms in new variables."""
  with variable_scope.variable_scope(
      None, 'hist_accumulate', [hist_true, hist_false]):
    # Holds running total histogram of scores for records labeled True.
    hist_true_acc = variable_scope.get_variable(
        'hist_true_acc',
        shape=[nbins],
        dtype=hist_true.dtype,
        initializer=init_ops.zeros_initializer(),
        collections=collections,
        trainable=False)
    # Holds running total histogram of scores for records labeled False.
    hist_false_acc = variable_scope.get_variable(
        'hist_false_acc',
        shape=[nbins],
        dtype=hist_true.dtype,
        initializer=init_ops.zeros_initializer(),
        collections=collections,
        trainable=False)

    update_op = control_flow_ops.group(
        hist_true_acc.assign_add(hist_true),
        hist_false_acc.assign_add(hist_false),
        name='update_op')

    return hist_true_acc, hist_false_acc, update_op 

def _create_global_step(graph):
  graph = graph or ops.get_default_graph()
  if training.get_global_step(graph) is not None:
    raise ValueError('"global_step" already exists.')
  # Create in proper graph and base name_scope.
  with graph.as_default() as g, g.name_scope(None):
    return variable_scope.get_variable(
        ops.GraphKeys.GLOBAL_STEP,
        shape=[],
        dtype=dtypes.int64,
        initializer=init_ops.zeros_initializer(),
        trainable=False,
        use_resource=True,
        collections=[ops.GraphKeys.GLOBAL_VARIABLES, ops.GraphKeys.GLOBAL_STEP]) 

def flatten_fully_connected(inputs,
                            num_outputs,
                            activation_fn=tf.nn.relu,
                            normalizer_fn=None,
                            normalizer_params=None,
                            weights_initializer=slim.xavier_initializer(),
                            weights_regularizer=None,
                            biases_initializer=tf.zeros_initializer(),
                            biases_regularizer=None,
                            reuse=None,
                            variables_collections=None,
                            outputs_collections=None,
                            trainable=True,
                            scope=None):
    with tf.variable_scope(scope, 'flatten_fully_connected', [inputs]):
        if inputs.shape.ndims > 2:
            inputs = slim.flatten(inputs)
        return slim.fully_connected(inputs,
                                    num_outputs,
                                    activation_fn,
                                    normalizer_fn,
                                    normalizer_params,
                                    weights_initializer,
                                    weights_regularizer,
                                    biases_initializer,
                                    biases_regularizer,
                                    reuse,
                                    variables_collections,
                                    outputs_collections,
                                    trainable,
                                    scope) 

def _centered_bias(logits_dimension, head_name=None):
  """Returns `logits`, optionally with centered bias applied.

  Args:
    logits_dimension: Last dimension of `logits`. Must be >= 1.
    head_name: Optional name of the head.

  Returns:
    Centered bias `Variable`.

  Raises:
    ValueError: if `logits_dimension` is invalid.
  """
  if (logits_dimension is None) or (logits_dimension < 1):
    raise ValueError("Invalid logits_dimension %s." % logits_dimension)
  centered_bias = variable_scope.get_variable(
      name="centered_bias_weight",
      shape=(logits_dimension,),
      initializer=init_ops.zeros_initializer(),
      trainable=True)
  for dim in range(logits_dimension):
    if head_name:
      summary.scalar("centered_bias/bias_%d/%s" % (dim, head_name),
                     centered_bias[dim])
    else:
      summary.scalar("centered_bias/bias_%d" % dim, centered_bias[dim])
  return centered_bias 

def flatten_fully_connected_v1(inputs,
                               num_outputs,
                               activation_fn=tf.nn.relu,
                               normalizer_fn=None,
                               normalizer_params=None,
                               weights_initializer=slim.xavier_initializer(),
                               weights_regularizer=None,
                               biases_initializer=tf.zeros_initializer(),
                               biases_regularizer=None,
                               reuse=None,
                               variables_collections=None,
                               outputs_collections=None,
                               trainable=True,
                               scope=None):
    with tf.variable_scope(scope, 'flatten_fully_connected_v1'):
        if inputs.shape.ndims > 2:
            inputs = slim.flatten(inputs)
        return slim.fully_connected(inputs,
                                    num_outputs,
                                    activation_fn,
                                    normalizer_fn,
                                    normalizer_params,
                                    weights_initializer,
                                    weights_regularizer,
                                    biases_initializer,
                                    biases_regularizer,
                                    reuse,
                                    variables_collections,
                                    outputs_collections,
                                    trainable,
                                    scope) 

def flatten_fully_connected_v2(inputs,
                               num_outputs,
                               activation_fn=nn.relu,
                               normalizer_fn=None,
                               normalizer_params=None,
                               weights_normalizer_fn=None,
                               weights_normalizer_params=None,
                               weights_initializer=initializers.xavier_initializer(),
                               weights_regularizer=None,
                               biases_initializer=init_ops.zeros_initializer(),
                               biases_regularizer=None,
                               reuse=None,
                               variables_collections=None,
                               outputs_collections=None,
                               trainable=True,
                               scope=None):
    with variable_scope.variable_scope(scope, 'flatten_fully_connected_v2'):
        if inputs.shape.ndims > 2:
            inputs = layers.flatten(inputs)
        return fully_connected(inputs=inputs,
                               num_outputs=num_outputs,
                               activation_fn=activation_fn,
                               normalizer_fn=normalizer_fn,
                               normalizer_params=normalizer_params,
                               weights_normalizer_fn=weights_normalizer_fn,
                               weights_normalizer_params=weights_normalizer_params,
                               weights_initializer=weights_initializer,
                               weights_regularizer=weights_regularizer,
                               biases_initializer=biases_initializer,
                               biases_regularizer=biases_regularizer,
                               reuse=reuse,
                               variables_collections=variables_collections,
                               outputs_collections=outputs_collections,
                               trainable=trainable,
                               scope=scope) 

def create_global_step(graph=None):
  """Create global step tensor in graph.

  Args:
    graph: The graph in which to create the global step. If missing, use default
        graph.

  Returns:
    Global step tensor.

  Raises:
    ValueError: if global step key is already defined.
  """
  graph = ops.get_default_graph() if graph is None else graph
  if get_global_step(graph) is not None:
    raise ValueError('"global_step" already exists.')
  # Create in proper graph and base name_scope.
  with graph.as_default() as g, g.name_scope(None):
    collections = [ops.GraphKeys.GLOBAL_VARIABLES, ops.GraphKeys.GLOBAL_STEP]
    return variable(
        ops.GraphKeys.GLOBAL_STEP,
        shape=[],
        dtype=dtypes.int64,
        initializer=init_ops.zeros_initializer(),
        trainable=False,
        collections=collections) 

def _wide_embedding_lookup_arguments(self, input_tensor):
    return _LinearEmbeddingLookupArguments(
        input_tensor=self.id_tensor(input_tensor),
        weight_tensor=self.weight_tensor(input_tensor),
        vocab_size=self.length,
        initializer=init_ops.zeros_initializer(),
        combiner=self.combiner) 

def _wide_embedding_lookup_arguments(self, input_tensor):
    return _LinearEmbeddingLookupArguments(
        input_tensor=input_tensor,
        weight_tensor=None,
        vocab_size=self.length,
        initializer=init_ops.zeros_initializer(),
        combiner=self.combiner)