Create variables in module
given input_spec
; return output_spec
.
tf_agents.networks.network.create_variables(
module: typing.Union[Network, tf.keras.layers.Layer],
input_spec: typing.Optional[types.NestedTensorSpec] = None,
**kwargs
) -> tf_agents.typing.types.NestedTensorSpec
Here module
can be a tf_agents.networks.Network
or Keras
layer.
Args |
module
|
The instance we would like to create layers on.
|
input_spec
|
The input spec (excluding batch dimensions).
|
**kwargs
|
Extra arguments to module.__call__ , e.g. training=True .
|
Raises |
ValueError
|
If module is a generic Keras layer but input_spec is None .
|
TypeError
|
If module is a tf.keras.layers.{RNN,LSTM,GRU,...} . These
must be wrapped in tf_agents.keras_layers.RNNWrapper .
|