# tf_agents.networks.network.create_variables

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/agents/blob/v0.19.0/tf_agents/networks/network.py#L571-L670) |

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
    ) -> https://www.tensorflow.org/agents/api_docs/python/tf_agents/typing/types/NestedTensorSpec

Here `module` can be a [`tf_agents.networks.Network`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/networks/Network) or `Keras` layer.

<br />

<br />

<br />

| ## 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`. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| Output specs, a nested [`tf.TypeSpec`](https://www.tensorflow.org/api_docs/python/tf/TypeSpec) describing the output signature. If `module` returns a `tfp.Distribution`, then the associated nested object is a `tf_agents.specs.DistributionSpecV2` (which is not a true [`tf.TypeSpec`](https://www.tensorflow.org/api_docs/python/tf/TypeSpec) but contains enough information to create a nested [`tf.TypeSpec`](https://www.tensorflow.org/api_docs/python/tf/TypeSpec) using [`tf_agents.distributions.utils.parameters_to_dict`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/distributions/utils/parameters_to_dict)). ||

<br />

<br />

<br />

<br />

| ## 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`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/keras_layers/RNNWrapper). |

<br />