Creates the variables of the layer (optional, for subclass implementers). This is a method that implementers of subclasses of `Layer` or `Model` can override if they need a state-creation step in-between layer instantiation and layer call. This is typically used to create the weigh
(self, input_shape)
| 370 | self._initial_weights = None |
| 371 | |
| 372 | def build(self, input_shape): |
| 373 | """Creates the variables of the layer (optional, for subclass implementers). |
| 374 | |
| 375 | This is a method that implementers of subclasses of `Layer` or `Model` |
| 376 | can override if they need a state-creation step in-between |
| 377 | layer instantiation and layer call. |
| 378 | |
| 379 | This is typically used to create the weights of `Layer` subclasses. |
| 380 | |
| 381 | Arguments: |
| 382 | input_shape: Instance of `TensorShape`, or list of instances of |
| 383 | `TensorShape` if the layer expects a list of inputs |
| 384 | (one instance per input). |
| 385 | """ |
| 386 | self.built = True |
| 387 | |
| 388 | @doc_controls.for_subclass_implementers |
| 389 | def call(self, inputs, **kwargs): # pylint: disable=unused-argument |