def __init__(self,
               axis=-1,
               epsilon=1e-3,
               center=True,
               scale=True,
               beta_initializer='zeros',
               gamma_initializer='ones',
               beta_regularizer=None,
               gamma_regularizer=None,
               beta_constraint=None,
               gamma_constraint=None,
               trainable=True,
               name=None,
               **kwargs):
    super(LayerNormalization, self).__init__(
        name=name, trainable=trainable, **kwargs)
    if isinstance(axis, (list, tuple)):
      self.axis = axis[:]
    elif isinstance(axis, int):
      self.axis = axis
    else:
      raise ValueError('Expected an int or a list/tuple of ints for the '
                       'argument \'axis\', but received instead: %s' % axis)

    self.epsilon = epsilon
    self.center = center
    self.scale = scale
    self.beta_initializer = initializers.get(beta_initializer)
    self.gamma_initializer = initializers.get(gamma_initializer)
    self.beta_regularizer = regularizers.get(beta_regularizer)
    self.gamma_regularizer = regularizers.get(gamma_regularizer)
    self.beta_constraint = constraints.get(beta_constraint)
    self.gamma_constraint = constraints.get(gamma_constraint)

    self.supports_masking = True

  def __init__(self,
               units,
               activation=None,
               use_bias=True,
               kernel_initializer='glorot_uniform',
               bias_initializer='zeros',
               kernel_regularizer=None,
               bias_regularizer=None,
               activity_regularizer=None,
               kernel_constraint=None,
               bias_constraint=None,
               **kwargs):
    if 'input_shape' not in kwargs and 'input_dim' in kwargs:
      kwargs['input_shape'] = (kwargs.pop('input_dim'),)

    super(Dense, self).__init__(
        activity_regularizer=regularizers.get(activity_regularizer), **kwargs)
    self.units = int(units)
    self.activation = activations.get(activation)
    self.use_bias = use_bias
    self.kernel_initializer = initializers.get(kernel_initializer)
    self.bias_initializer = initializers.get(bias_initializer)
    self.kernel_regularizer = regularizers.get(kernel_regularizer)
    self.bias_regularizer = regularizers.get(bias_regularizer)
    self.kernel_constraint = constraints.get(kernel_constraint)
    self.bias_constraint = constraints.get(bias_constraint)

    self.supports_masking = True
    self.input_spec = InputSpec(min_ndim=2)

  def __init__(self,
               axis=-1,
               momentum=0.99,
               epsilon=1e-3,
               center=True,
               scale=True,
               beta_initializer='zeros',
               gamma_initializer='ones',
               moving_mean_initializer='zeros',
               moving_variance_initializer='ones',
               beta_regularizer=None,
               gamma_regularizer=None,
               beta_constraint=None,
               gamma_constraint=None,
               renorm=False,
               renorm_clipping=None,
               renorm_momentum=0.99,
               fused=None,
               trainable=True,
               virtual_batch_size=None,
               adjustment=None,
               name=None,
               **kwargs):
    super(BatchNormalization, self).__init__(
        name=name, trainable=trainable, **kwargs)
    if isinstance(axis, list):
      self.axis = axis[:]
    else:
      self.axis = axis
    self.momentum = momentum
    self.epsilon = epsilon
    self.center = center
    self.scale = scale
    self.beta_initializer = initializers.get(beta_initializer)
    self.gamma_initializer = initializers.get(gamma_initializer)
    self.moving_mean_initializer = initializers.get(moving_mean_initializer)
    self.moving_variance_initializer = initializers.get(
        moving_variance_initializer)
    self.beta_regularizer = regularizers.get(beta_regularizer)
    self.gamma_regularizer = regularizers.get(gamma_regularizer)
    self.beta_constraint = constraints.get(beta_constraint)
    self.gamma_constraint = constraints.get(gamma_constraint)
    self.renorm = renorm
    self.virtual_batch_size = virtual_batch_size
    self.adjustment = adjustment
    if fused is None:
      fused = True
    self.supports_masking = True

    self.fused = fused
    self._bessels_correction_test_only = True

    if renorm:
      renorm_clipping = renorm_clipping or {}
      keys = ['rmax', 'rmin', 'dmax']
      if set(renorm_clipping) - set(keys):
        raise ValueError('renorm_clipping %s contains keys not in %s' %
                         (renorm_clipping, keys))
      self.renorm_clipping = renorm_clipping
      self.renorm_momentum = renorm_momentum

 def __init__(self,
              filters,
              kernel_size,
              strides=1,
              padding='valid',
              data_format=None,
              activation=None,
              use_bias=True,
              kernel_initializer='glorot_uniform',
              bias_initializer='zeros',
              kernel_regularizer=None,
              bias_regularizer=None,
              activity_regularizer=None,
              kernel_constraint=None,
              bias_constraint=None,
              **kwargs):
   super(LocallyConnected1D, self).__init__(**kwargs)
   self.filters = filters
   self.kernel_size = conv_utils.normalize_tuple(kernel_size, 1, 'kernel_size')
   self.strides = conv_utils.normalize_tuple(strides, 1, 'strides')
   self.padding = conv_utils.normalize_padding(padding)
   if self.padding != 'valid':
     raise ValueError('Invalid border mode for LocallyConnected1D '
                      '(only "valid" is supported): ' + padding)
   self.data_format = conv_utils.normalize_data_format(data_format)
   self.activation = activations.get(activation)
   self.use_bias = use_bias
   self.kernel_initializer = initializers.get(kernel_initializer)
   self.bias_initializer = initializers.get(bias_initializer)
   self.kernel_regularizer = regularizers.get(kernel_regularizer)
   self.bias_regularizer = regularizers.get(bias_regularizer)
   self.activity_regularizer = regularizers.get(activity_regularizer)
   self.kernel_constraint = constraints.get(kernel_constraint)
   self.bias_constraint = constraints.get(bias_constraint)
   self.input_spec = InputSpec(ndim=3)

  def __init__(self,
               units,
               activation='tanh',
               recurrent_activation='hard_sigmoid',
               kernel_initializer='glorot_uniform',
               recurrent_initializer='orthogonal',
               bias_initializer='zeros',
               unit_forget_bias=True,
               kernel_regularizer=None,
               recurrent_regularizer=None,
               bias_regularizer=None,
               activity_regularizer=None,
               kernel_constraint=None,
               recurrent_constraint=None,
               bias_constraint=None,
               return_sequences=False,
               return_state=False,
               go_backwards=False,
               stateful=False,
               time_major=False,
               **kwargs):
    super(RNN, self).__init__(**kwargs)  # pylint: disable=bad-super-call
    self.units = units
    cell_spec = collections.namedtuple('cell', ['state_size', 'output_size'])
    self.cell = cell_spec(
        state_size=(self.units, self.units), output_size=self.units)
    self.activation = activations.get(activation)
    self.recurrent_activation = activations.get(recurrent_activation)
    self.kernel_initializer = initializers.get(kernel_initializer)
    self.recurrent_initializer = initializers.get(recurrent_initializer)
    self.bias_initializer = initializers.get(bias_initializer)
    self.unit_forget_bias = unit_forget_bias

    self.kernel_regularizer = regularizers.get(kernel_regularizer)
    self.recurrent_regularizer = regularizers.get(recurrent_regularizer)
    self.bias_regularizer = regularizers.get(bias_regularizer)
    self.activity_regularizer = regularizers.get(activity_regularizer)

    self.kernel_constraint = constraints.get(kernel_constraint)
    self.recurrent_constraint = constraints.get(recurrent_constraint)
    self.bias_constraint = constraints.get(bias_constraint)

    self.return_sequences = return_sequences
    self.return_state = return_state
    self.go_backwards = go_backwards
    self.stateful = stateful
    self.time_major = time_major
    self._num_constants = None
    self._num_inputs = None
    self._states = None
    self.input_spec = [InputSpec(ndim=3)]
    self.state_spec = [
        InputSpec(shape=(None, dim)) for dim in (self.units, self.units)
    ]

  def __init__(self,
               filters,
               kernel_size,
               strides=(1, 1),
               padding='valid',
               data_format=None,
               dilation_rate=(1, 1),
               activation='tanh',
               recurrent_activation='hard_sigmoid',
               use_bias=True,
               kernel_initializer='glorot_uniform',
               recurrent_initializer='orthogonal',
               bias_initializer='zeros',
               unit_forget_bias=True,
               kernel_regularizer=None,
               recurrent_regularizer=None,
               bias_regularizer=None,
               kernel_constraint=None,
               recurrent_constraint=None,
               bias_constraint=None,
               dropout=0.,
               recurrent_dropout=0.,
               **kwargs):
    super(ConvLSTM2DCell, self).__init__(**kwargs)
    self.filters = filters
    self.kernel_size = conv_utils.normalize_tuple(kernel_size, 2, 'kernel_size')
    self.strides = conv_utils.normalize_tuple(strides, 2, 'strides')
    self.padding = conv_utils.normalize_padding(padding)
    self.data_format = conv_utils.normalize_data_format(data_format)
    self.dilation_rate = conv_utils.normalize_tuple(dilation_rate, 2,
                                                    'dilation_rate')
    self.activation = activations.get(activation)
    self.recurrent_activation = activations.get(recurrent_activation)
    self.use_bias = use_bias

    self.kernel_initializer = initializers.get(kernel_initializer)
    self.recurrent_initializer = initializers.get(recurrent_initializer)
    self.bias_initializer = initializers.get(bias_initializer)
    self.unit_forget_bias = unit_forget_bias

    self.kernel_regularizer = regularizers.get(kernel_regularizer)
    self.recurrent_regularizer = regularizers.get(recurrent_regularizer)
    self.bias_regularizer = regularizers.get(bias_regularizer)

    self.kernel_constraint = constraints.get(kernel_constraint)
    self.recurrent_constraint = constraints.get(recurrent_constraint)
    self.bias_constraint = constraints.get(bias_constraint)

    self.dropout = min(1., max(0., dropout))
    self.recurrent_dropout = min(1., max(0., recurrent_dropout))
    self.state_size = (self.filters, self.filters)
    self._dropout_mask = None
    self._recurrent_dropout_mask = None

 def add_slot(self, var, slot_name, initializer="zeros"):
   """Add a new slot variable for `var`."""
   if slot_name not in self._slot_names:
     self._slot_names.append(slot_name)
   var_key = _var_key(var)
   slot_dict = self._slots.setdefault(var_key, {})
   weight = slot_dict.get(slot_name, None)
   if weight is None:
     if isinstance(initializer, six.string_types) or callable(initializer):
       initializer = initializers.get(initializer)
       initial_value = functools.partial(
           initializer, shape=var.shape, dtype=var.dtype)
     else:
       initial_value = initializer
     weight = tf_variables.Variable(
         name="%s/%s" % (var._shared_name, slot_name),  # pylint: disable=protected-access
         dtype=var.dtype,
         trainable=False,
         initial_value=initial_value)
     backend.track_variable(weight)
     slot_dict[slot_name] = weight
     self._restore_slot_variable(
         slot_name=slot_name, variable=var,
         slot_variable=weight)
     self._weights.append(weight)
   return weight

  def __init__(self,
               input_dim,
               output_dim,
               embeddings_initializer='uniform',
               embeddings_regularizer=None,
               activity_regularizer=None,
               embeddings_constraint=None,
               mask_zero=False,
               input_length=None,
               **kwargs):
    if 'input_shape' not in kwargs:
      if input_length:
        kwargs['input_shape'] = (input_length,)
      else:
        kwargs['input_shape'] = (None,)
    dtype = kwargs.pop('dtype', K.floatx())
    super(Embedding, self).__init__(dtype=dtype, **kwargs)

    self.input_dim = input_dim
    self.output_dim = output_dim
    self.embeddings_initializer = initializers.get(embeddings_initializer)
    self.embeddings_regularizer = regularizers.get(embeddings_regularizer)
    self.activity_regularizer = regularizers.get(activity_regularizer)
    self.embeddings_constraint = constraints.get(embeddings_constraint)
    self.mask_zero = mask_zero
    self.supports_masking = mask_zero
    self.input_length = input_length

  def _add_weight(self,
                  name,
                  shape=(),
                  dtype=None,
                  initializer='zeros'):
    """Adds a weight to this loss scale.

    Args:
      name: Variable name.
      shape: Variable shape.
      dtype: The type of the variable.
      initializer: The initializer to use.

    Returns:
      A variable.
    """
    if isinstance(initializer, six.string_types) or callable(initializer):
      initializer = initializers.get(initializer)
    variable = self._add_variable_with_custom_getter(
        name=name,
        shape=shape,
        getter=base_layer_utils.make_variable,
        overwrite=True,
        initializer=initializer,
        dtype=dtype,
        trainable=False,
        use_resource=True,
        synchronization=variables.VariableSynchronization.AUTO,
        # Set aggregation to NONE, as loss scaling variables should never be
        # aggregated.
        aggregation=variables.VariableAggregation.NONE)
    backend.track_variable(variable)
    return variable

  def __init__(self,
               norm_axis=None,
               params_axis=-1,
               epsilon=1e-12,
               center=True,
               scale=True,
               beta_initializer='zeros',
               gamma_initializer='ones',
               beta_regularizer=None,
               gamma_regularizer=None,
               beta_constraint=None,
               gamma_constraint=None,
               trainable=True,
               name=None,
               **kwargs):
    super(LayerNormalization, self).__init__(
        name=name, trainable=trainable, **kwargs)
    if isinstance(norm_axis, list):
      self.norm_axis = norm_axis[:]
    elif isinstance(norm_axis, int):
      self.norm_axis = norm_axis
    elif norm_axis is None:
      self.norm_axis = None
    else:
      raise TypeError('norm_axis must be int or list or None, type given: %s'
                      % type(norm_axis))

    if isinstance(params_axis, list):
      self.params_axis = params_axis[:]
    elif isinstance(params_axis, int):
      self.params_axis = params_axis
    else:
      raise TypeError('params_axis must be int or list, type given: %s'
                      % type(params_axis))

    self.epsilon = epsilon
    self.center = center
    self.scale = scale
    self.beta_initializer = initializers.get(beta_initializer)
    self.gamma_initializer = initializers.get(gamma_initializer)
    self.beta_regularizer = regularizers.get(beta_regularizer)
    self.gamma_regularizer = regularizers.get(gamma_regularizer)
    self.beta_constraint = constraints.get(beta_constraint)
    self.gamma_constraint = constraints.get(gamma_constraint)

    self.supports_masking = True

  def __init__(self,
               units,
               kernel_initializer='glorot_uniform',
               recurrent_initializer='orthogonal',
               bias_initializer='zeros',
               unit_forget_bias=True,
               kernel_regularizer=None,
               recurrent_regularizer=None,
               bias_regularizer=None,
               activity_regularizer=None,
               kernel_constraint=None,
               recurrent_constraint=None,
               bias_constraint=None,
               return_sequences=False,
               return_state=False,
               go_backwards=False,
               stateful=False,
               **kwargs):
    self.units = units
    cell_spec = collections.namedtuple('cell', 'state_size')
    self._cell = cell_spec(state_size=(self.units, self.units))
    super(CuDNNLSTM, self).__init__(
        return_sequences=return_sequences,
        return_state=return_state,
        go_backwards=go_backwards,
        stateful=stateful,
        **kwargs)

    self.kernel_initializer = initializers.get(kernel_initializer)
    self.recurrent_initializer = initializers.get(recurrent_initializer)
    self.bias_initializer = initializers.get(bias_initializer)
    self.unit_forget_bias = unit_forget_bias

    self.kernel_regularizer = regularizers.get(kernel_regularizer)
    self.recurrent_regularizer = regularizers.get(recurrent_regularizer)
    self.bias_regularizer = regularizers.get(bias_regularizer)
    self.activity_regularizer = regularizers.get(activity_regularizer)

    self.kernel_constraint = constraints.get(kernel_constraint)
    self.recurrent_constraint = constraints.get(recurrent_constraint)
    self.bias_constraint = constraints.get(bias_constraint)

 def __init__(self,
              alpha_initializer='zeros',
              alpha_regularizer=None,
              alpha_constraint=None,
              shared_axes=None,
              **kwargs):
   super(PReLU, self).__init__(**kwargs)
   self.supports_masking = True
   self.alpha_initializer = initializers.get(alpha_initializer)
   self.alpha_regularizer = regularizers.get(alpha_regularizer)
   self.alpha_constraint = constraints.get(alpha_constraint)
   if shared_axes is None:
     self.shared_axes = None
   elif not isinstance(shared_axes, (list, tuple)):
     self.shared_axes = [shared_axes]
   else:
     self.shared_axes = list(shared_axes)

  def add_weight(self,
                 name,
                 shape,
                 dtype=None,
                 initializer="zeros",
                 trainable=None,
                 synchronization=tf_variables.VariableSynchronization.AUTO,
                 aggregation=tf_variables.VariableAggregation.NONE):

    if dtype is None:
      dtype = dtypes.float32
    if isinstance(initializer, six.string_types) or callable(initializer):
      initializer = initializers.get(initializer)

    if synchronization == tf_variables.VariableSynchronization.ON_READ:
      if trainable:
        raise ValueError(
            "Synchronization value can be set to "
            "VariableSynchronization.ON_READ only for non-trainable variables. "
            "You have specified trainable=True and "
            "synchronization=VariableSynchronization.ON_READ.")
      else:
        # Set trainable to be false when variable is to be synced on read.
        trainable = False
    elif trainable is None:
      trainable = True

    variable = self._add_variable_with_custom_getter(
        name=name,
        shape=shape,
        getter=base_layer_utils.make_variable,
        overwrite=True,
        initializer=initializer,
        dtype=dtype,
        trainable=trainable,
        use_resource=True,
        synchronization=synchronization,
        aggregation=aggregation)
    backend.track_variable(variable)

    return variable