Method get_layer

tensorflow/python/keras/engine/network.py:500–531

Retrieves a layer based on either its name (unique) or index. If `name` and `index` are both provided, `index` will take precedence. Indices are based on order of horizontal graph traversal (bottom-up). Arguments: name: String, name of layer. index: Integer, index of la

(self, name=None, index=None)

        self._layers)

  def get_layer(self, name=None, index=None):
    """Retrieves a layer based on either its name (unique) or index.

    If `name` and `index` are both provided, `index` will take precedence.
    Indices are based on order of horizontal graph traversal (bottom-up).

    Arguments:
        name: String, name of layer.
        index: Integer, index of layer.

    Returns:
        A layer instance.

    Raises:
        ValueError: In case of invalid layer name or index.
    """
    # TODO(fchollet): We could build a dictionary based on layer names
    # since they are constant, but we have not done that yet.
    if index is not None:
      if len(self.layers) <= index:
        raise ValueError('Was asked to retrieve layer at index ' + str(index) +
                         ' but model only has ' + str(len(self.layers)) +
                         ' layers.')
      else:
        return self.layers[index]
    else:
      if not name:
        raise ValueError('Provide either a layer name or layer index.')
    for layer in self.layers:
      if layer.name == name:
        return layer
    raise ValueError('No such layer: ' + name)

  @property
  def trainable_weights(self):