Python tensorflow.python.layers.base.Layer() Examples

def output_mask(self):
    """Retrieves the output mask tensor(s) of a layer.

    Only applicable if the layer has exactly one inbound node,
    i.e. if it is connected to one incoming layer.

    Returns:
        Output mask tensor (potentially None) or list of output
        mask tensors.

    Raises:
        AttributeError: if the layer is connected to
        more than one incoming layers.
    """
    if len(self.inbound_nodes) != 1:
      raise AttributeError('Layer ' + self.name +
                           ' has multiple inbound nodes, '
                           'hence the notion of "layer output mask" '
                           'is ill-defined. '
                           'Use `get_output_mask_at(node_index)` '
                           'instead.')
    return self._get_node_attribute_at_index(0, 'output_masks', 'output mask') 

def __init__(self, cell, helper, initial_state, output_layer=None):
		"""Initialize CustomDecoder.
		Args:
			cell: An `RNNCell` instance.
			helper: A `Helper` instance.
			initial_state: A (possibly nested tuple of...) tensors and TensorArrays.
				The initial state of the RNNCell.
			output_layer: (Optional) An instance of `tf.layers.Layer`, i.e.,
				`tf.layers.Dense`. Optional layer to apply to the RNN output prior
				to storing the result or sampling.
		Raises:
			TypeError: if `cell`, `helper` or `output_layer` have an incorrect type.
		"""
		rnn_cell_impl.assert_like_rnncell(type(cell), cell)
		if not isinstance(helper, helper_py.Helper):
			raise TypeError("helper must be a Helper, received: %s" % type(helper))
		if (output_layer is not None
				and not isinstance(output_layer, layers_base.Layer)):
			raise TypeError(
					"output_layer must be a Layer, received: %s" % type(output_layer))
		self._cell = cell
		self._helper = helper
		self._initial_state = initial_state
		self._output_layer = output_layer 

def __init__(self, cell, helper, initial_state, output_layer=None):
		"""Initialize CustomDecoder.
		Args:
			cell: An `RNNCell` instance.
			helper: A `Helper` instance.
			initial_state: A (possibly nested tuple of...) tensors and TensorArrays.
				The initial state of the RNNCell.
			output_layer: (Optional) An instance of `tf.layers.Layer`, i.e.,
				`tf.layers.Dense`. Optional layer to apply to the RNN output prior
				to storing the result or sampling.
		Raises:
			TypeError: if `cell`, `helper` or `output_layer` have an incorrect type.
		"""
		rnn_cell_impl.assert_like_rnncell(type(cell), cell)
		if not isinstance(helper, helper_py.Helper):
			raise TypeError("helper must be a Helper, received: %s" % type(helper))
		if (output_layer is not None
				and not isinstance(output_layer, layers_base.Layer)):
			raise TypeError(
					"output_layer must be a Layer, received: %s" % type(output_layer))
		self._cell = cell
		self._helper = helper
		self._initial_state = initial_state
		self._output_layer = output_layer 

def __init__(self, cell, helper, initial_state, latent_vector, output_layer=None):
        """Initialize BasicDecoder.
        Args:
          cell: An `RNNCell` instance.
          helper: A `Helper` instance.
          initial_state: A (possibly nested tuple of...) tensors and TensorArrays.
            The initial state of the RNNCell.
          output_layer: (Optional) An instance of `tf.layers.Layer`, i.e.,
            `tf.layers.Dense`.  Optional layer to apply to the RNN output prior
            to storing the result or sampling.
        Raises:
          TypeError: if `cell`, `helper` or `output_layer` have an incorrect type.
        """
        if not rnn_cell_impl._like_rnncell(cell):  # pylint: disable=protected-access
            raise TypeError("cell must be an RNNCell, received: %s" % type(cell))
        if not isinstance(helper, helper_py.Helper):
            raise TypeError("helper must be a Helper, received: %s" % type(helper))
        if (output_layer is not None and not isinstance(output_layer, layers_base.Layer)):
            raise TypeError("output_layer must be a Layer, received: %s" % type(output_layer))
        self._cell = cell
        self._helper = helper
        self._initial_state = initial_state
        self._output_layer = output_layer
        self._latent_vector = latent_vector 

def call(self, inputs, forward=True):
    vs = variable_scope.get_variable_scope()
    vars_before = vs.global_variables()

    if forward:
      x1, x2 = inputs
      out = self._forward(x1, x2)
    else:
      y1, y2 = inputs
      out = self._backward(y1, y2)

    # Add any created variables to the Layer's variable stores
    new_vars = vs.global_variables()[len(vars_before):]
    train_vars = vs.trainable_variables()
    for new_var in new_vars:
      if new_var in train_vars:
        self._trainable_weights.append(new_var)
      else:
        self._non_trainable_weights.append(new_var)

    return out 

def __init__(self, cell, helper, initial_state, output_layer=None):
		"""Initialize CustomDecoder.
		Args:
			cell: An `RNNCell` instance.
			helper: A `Helper` instance.
			initial_state: A (possibly nested tuple of...) tensors and TensorArrays.
				The initial state of the RNNCell.
			output_layer: (Optional) An instance of `tf.layers.Layer`, i.e.,
				`tf.layers.Dense`. Optional layer to apply to the RNN output prior
				to storing the result or sampling.
		Raises:
			TypeError: if `cell`, `helper` or `output_layer` have an incorrect type.
		"""
		if not rnn_cell_impl._like_rnncell(cell):  # pylint: disable=protected-access
			raise TypeError("cell must be an RNNCell, received: %s" % type(cell))
		if not isinstance(helper, helper_py.Helper):
			raise TypeError("helper must be a Helper, received: %s" % type(helper))
		if (output_layer is not None
				and not isinstance(output_layer, layers_base.Layer)):
			raise TypeError(
					"output_layer must be a Layer, received: %s" % type(output_layer))
		self._cell = cell
		self._helper = helper
		self._initial_state = initial_state
		self._output_layer = output_layer 

def input_spec(self):
    """Gets the model's input specs.

    Returns:
        A list of `InputSpec` instances (one per input to the model)
            or a single instance if the model has only one input.
    """
    specs = []
    for layer in getattr(self, 'input_layers', []):
      if layer.input_spec is None:
        specs.append(None)
      else:
        if not isinstance(layer.input_spec, list):
          raise TypeError('Layer ' + layer.name +
                          ' has an input_spec attribute that '
                          'is not a list. We expect a list. '
                          'Found input_spec = ' + str(layer.input_spec))
        specs += layer.input_spec
    if len(specs) == 1:
      return specs[0]
    return specs 

def __init__(self, cell, helper, initial_state, output_layer=None):
		"""Initialize CustomDecoder.
		Args:
			cell: An `RNNCell` instance.
			helper: A `Helper` instance.
			initial_state: A (possibly nested tuple of...) tensors and TensorArrays.
				The initial state of the RNNCell.
			output_layer: (Optional) An instance of `tf.layers.Layer`, i.e.,
				`tf.layers.Dense`. Optional layer to apply to the RNN output prior
				to storing the result or sampling.
		Raises:
			TypeError: if `cell`, `helper` or `output_layer` have an incorrect type.
		"""
		if not rnn_cell_impl._like_rnncell(cell):  # pylint: disable=protected-access
			raise TypeError("cell must be an RNNCell, received: %s" % type(cell))
		if not isinstance(helper, helper_py.Helper):
			raise TypeError("helper must be a Helper, received: %s" % type(helper))
		if (output_layer is not None
				and not isinstance(output_layer, layers_base.Layer)):
			raise TypeError(
					"output_layer must be a Layer, received: %s" % type(output_layer))
		self._cell = cell
		self._helper = helper
		self._initial_state = initial_state
		self._output_layer = output_layer 

def input_mask(self):
    """Retrieves the input mask tensor(s) of a layer.

    Only applicable if the layer has exactly one inbound node,
    i.e. if it is connected to one incoming layer.

    Returns:
        Input mask tensor (potentially None) or list of input
        mask tensors.

    Raises:
        AttributeError: if the layer is connected to
        more than one incoming layers.
    """
    if len(self.inbound_nodes) != 1:
      raise AttributeError('Layer ' + self.name +
                           ' has multiple inbound nodes, ' +
                           'hence the notion of "layer input mask" '
                           'is ill-defined. '
                           'Use `get_input_mask_at(node_index)` '
                           'instead.')
    return self._get_node_attribute_at_index(0, 'input_masks', 'input mask') 

def input(self):
    """Retrieves the input tensor(s) of a layer.

    Only applicable if the layer has exactly one inbound node,
    i.e. if it is connected to one incoming layer.

    Returns:
        Input tensor or list of input tensors.

    Raises:
        AttributeError: if the layer is connected to
        more than one incoming layers.
    """
    if len(self.inbound_nodes) > 1:
      raise AttributeError('Layer ' + self.name +
                           ' has multiple inbound nodes, '
                           'hence the notion of "layer input" '
                           'is ill-defined. '
                           'Use `get_input_at(node_index)` instead.')
    elif not self.inbound_nodes:
      raise AttributeError('Layer ' + self.name +
                           ' is not connected, no input to return.')
    return self._get_node_attribute_at_index(0, 'input_tensors', 'input') 

def compute_mask(self, inputs, mask=None):  # pylint: disable=unused-argument
    """Computes an output mask tensor.

    Arguments:
        inputs: Tensor or list of tensors.
        mask: Tensor or list of tensors.

    Returns:
        None or a tensor (or list of tensors,
            one per output tensor of the layer).
    """
    if not self.supports_masking:
      if mask is not None:
        if isinstance(mask, list):
          if any(m is not None for m in mask):
            raise TypeError('Layer ' + self.name + ' does not support masking, '
                            'but was passed an input_mask: ' + str(mask))
        else:
          raise TypeError('Layer ' + self.name + ' does not support masking, '
                          'but was passed an input_mask: ' + str(mask))
      # masking not explicitly supported: return None as mask
      return None
    # if masking is explicitly supported, by default
    # carry over the input mask
    return mask 

def __init__(self, cell, helper, initial_state, output_layer=None):
		"""Initialize CustomDecoder.
		Args:
			cell: An `RNNCell` instance.
			helper: A `Helper` instance.
			initial_state: A (possibly nested tuple of...) tensors and TensorArrays.
				The initial state of the RNNCell.
			output_layer: (Optional) An instance of `tf.layers.Layer`, i.e.,
				`tf.layers.Dense`. Optional layer to apply to the RNN output prior
				to storing the result or sampling.
		Raises:
			TypeError: if `cell`, `helper` or `output_layer` have an incorrect type.
		"""
		# rnn_cell_impl.assert_like_rnncell(type(cell), cell)
		if not isinstance(helper, helper_py.Helper):
			raise TypeError("helper must be a Helper, received: %s" % type(helper))
		if (output_layer is not None
				and not isinstance(output_layer, layers_base.Layer)):
			raise TypeError(
					"output_layer must be a Layer, received: %s" % type(output_layer))
		self._cell = cell
		self._helper = helper
		self._initial_state = initial_state
		self._output_layer = output_layer 

def compute_mask(self, inputs, mask=None):  # pylint: disable=unused-argument
    """Computes an output mask tensor.

    Arguments:
        inputs: Tensor or list of tensors.
        mask: Tensor or list of tensors.

    Returns:
        None or a tensor (or list of tensors,
            one per output tensor of the layer).
    """
    if not self.supports_masking:
      if mask is not None:
        if isinstance(mask, list):
          if any(m is not None for m in mask):
            raise TypeError('Layer ' + self.name + ' does not support masking, '
                            'but was passed an input_mask: ' + str(mask))
        else:
          raise TypeError('Layer ' + self.name + ' does not support masking, '
                          'but was passed an input_mask: ' + str(mask))
      # masking not explicitly supported: return None as mask
      return None
    # if masking is explicitly supported, by default
    # carry over the input mask
    return mask 

def call(self, inputs, forward=True):
    vs = variable_scope.get_variable_scope()
    vars_before = vs.global_variables()

    if forward:
      x1, x2 = inputs
      out = self._forward(x1, x2)
    else:
      y1, y2 = inputs
      out = self._backward(y1, y2)

    # Add any created variables to the Layer's variable stores
    new_vars = vs.global_variables()[len(vars_before):]
    train_vars = vs.trainable_variables()
    for new_var in new_vars:
      if new_var in train_vars:
        self._trainable_weights.append(new_var)
      else:
        self._non_trainable_weights.append(new_var)

    return out 

def __init__(self, cell, helper, initial_state, latent_vector, output_layer=None):
        """Initialize BasicDecoder.
        Args:
          cell: An `RNNCell` instance.
          helper: A `Helper` instance.
          initial_state: A (possibly nested tuple of...) tensors and TensorArrays.
            The initial state of the RNNCell.
          latent_vector: A hidden state intended to be concatenated with the
            hidden state at every time-step of decoding
          output_layer: (Optional) An instance of `tf.layers.Layer`, i.e.,
            `tf.layers.Dense`.  Optional layer to apply to the RNN output prior
            to storing the result or sampling.
        Raises:
          TypeError: if `cell`, `helper` or `output_layer` have an incorrect type.
        """
        rnn_cell_impl.assert_like_rnncell("cell must be an RNNCell, received: %s" % type(cell), cell)
        if not isinstance(helper, helper_py.Helper):
            raise TypeError("helper must be a Helper, received: %s" % type(helper))
        if output_layer is not None and not isinstance(output_layer, layers_base.Layer):
            raise TypeError("output_layer must be a Layer, received: %s" % type(output_layer))
        self._cell = cell
        self._helper = helper
        self._initial_state = initial_state
        self._output_layer = output_layer
        self._latent_vector = latent_vector 

def build(self, _):
    # This tells the parent Layer object that it's OK to call
    # self.add_variable() inside the call() method.
    pass 

def build(self, _):
    # This tells the parent Layer object that it's OK to call
    # self.add_variable() inside the call() method.
    pass 

def build(self, _):
    # This tells the parent Layer object that it's OK to call
    # self.add_variable() inside the call() method.
    pass 

def build(self, _):
    # This tells the parent Layer object that it's OK to call
    # self.add_variable() inside the call() method.
    pass 

def build(self, _):
        # This tells the parent Layer object that it's OK to call
        # self.add_variable() inside the call() method.
        pass 

def build(self, _):
    # This tells the parent Layer object that it's OK to call
    # self.add_variable() inside the call() method.
    pass 

def build(self, _):
        # This tells the parent Layer object that it's OK to call
        # self.add_variable() inside the call() method.
        pass 

def build(self, _):
        # This tells the parent Layer object that it's OK to call
        # self.add_variable() inside the call() method.
        pass 

def build(self, _):
    # This tells the parent Layer object that it's OK to call
    # self.add_variable() inside the call() method.
    pass 

def __call__(self, inputs, **kwargs):
    """Wrapper around self.call(), for handling internal references.

    If a Keras tensor is passed:
        - We call self._add_inbound_node().
        - If necessary, we `build` the layer to match
            the shape of the input(s).
        - We update the _keras_history of the output tensor(s)
            with the current layer.
            This is done as part of _add_inbound_node().

    Arguments:
        inputs: Can be a tensor or list/tuple of tensors.
        **kwargs: Additional keyword arguments to be passed to `call()`.

    Returns:
        Output of the layer's `call` method.

    Raises:
        ValueError: in case the layer is missing shape information
            for its `build` call.
    """
    # Actually call the layer (optionally building it).
    output = super(Layer, self).__call__(inputs, **kwargs)

    # Update learning phase info.
    output_tensors = _to_list(output)
    uses_lp = any(
        [getattr(x, '_uses_learning_phase', False) for x in _to_list(inputs)])
    uses_lp = getattr(self, 'uses_learning_phase', False) or uses_lp
    for i in range(len(output_tensors)):
      output_tensors[i]._uses_learning_phase = getattr(
          output_tensors[i], '_uses_learning_phase', False) or uses_lp

    # Optionally load weight values that were specified at layer instantiation.
    if hasattr(self, '_initial_weights') and self._initial_weights is not None:
      self.set_weights(self._initial_weights)
      del self._initial_weights
    return output 

def set_weights(self, weights):
    """Sets the weights of the layer, from Numpy arrays.

    Arguments:
        weights: a list of Numpy arrays. The number
            of arrays and their shape must match
            number of the dimensions of the weights
            of the layer (i.e. it should match the
            output of `get_weights`).

    Raises:
        ValueError: If the provided weights list does not match the
            layer's specifications.
    """
    params = self.weights
    if len(params) != len(weights):
      raise ValueError('You called `set_weights(weights)` on layer "' +
                       self.name + '" with a  weight list of length ' +
                       str(len(weights)) + ', but the layer was expecting ' +
                       str(len(params)) + ' weights. Provided weights: ' +
                       str(weights)[:50] + '...')
    if not params:
      return
    weight_value_tuples = []
    param_values = K.batch_get_value(params)
    for pv, p, w in zip(param_values, params, weights):
      if pv.shape != w.shape:
        raise ValueError('Layer weight shape ' + str(pv.shape) +
                         ' not compatible with '
                         'provided weight shape ' + str(w.shape))
      weight_value_tuples.append((p, w))
    K.batch_set_value(weight_value_tuples) 

def build(self, _):
    # This tells the parent Layer object that it's OK to call
    # self.add_variable() inside the call() method.
    pass 

def build(self, _):
    # This tells the parent Layer object that it's OK to call
    # self.add_variable() inside the call() method.
    pass 

def set_weights(self, weights):
    """Sets the weights of the layer, from Numpy arrays.

    Arguments:
        weights: a list of Numpy arrays. The number
            of arrays and their shape must match
            number of the dimensions of the weights
            of the layer (i.e. it should match the
            output of `get_weights`).

    Raises:
        ValueError: If the provided weights list does not match the
            layer's specifications.
    """
    params = self.weights
    if len(params) != len(weights):
      raise ValueError('You called `set_weights(weights)` on layer "' +
                       self.name + '" with a  weight list of length ' +
                       str(len(weights)) + ', but the layer was expecting ' +
                       str(len(params)) + ' weights. Provided weights: ' +
                       str(weights)[:50] + '...')
    if not params:
      return
    weight_value_tuples = []
    param_values = K.batch_get_value(params)
    for pv, p, w in zip(param_values, params, weights):
      if pv.shape != w.shape:
        raise ValueError('Layer weight shape ' + str(pv.shape) +
                         ' not compatible with '
                         'provided weight shape ' + str(w.shape))
      weight_value_tuples.append((p, w))
    K.batch_set_value(weight_value_tuples) 

def __init__(self, cell, helper, initial_state, output_layer=None):
    """Initialize BasicDecoder.

    Args:
      cell: An `RNNCell` instance.
      helper: A `Helper` instance.
      initial_state: A (possibly nested tuple of...) tensors and TensorArrays.
        The initial state of the RNNCell.
      output_layer: (Optional) An instance of `tf.layers.Layer`, i.e.,
        `tf.layers.Dense`.  Optional layer to apply to the RNN output prior
        to storing the result or sampling.

    Raises:
      TypeError: if `cell`, `helper` or `output_layer` have an incorrect type.
    """
    if not rnn_cell_impl._like_rnncell(cell):  # pylint: disable=protected-access
      raise TypeError("cell must be an RNNCell, received: %s" % type(cell))
    if not isinstance(helper, helper_py.Helper):
      raise TypeError("helper must be a Helper, received: %s" % type(helper))
    if (output_layer is not None
        and not isinstance(output_layer, layers_base.Layer)):
      raise TypeError(
          "output_layer must be a Layer, received: %s" % type(output_layer))
    self._cell = cell
    self._helper = helper
    self._initial_state = initial_state
    self._output_layer = output_layer