# tf_agents.networks.Network

<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#L110-L491) |

A class used to represent networks used by TF-Agents policies and agents.

#### View aliases


**Main aliases**

[`tf_agents.networks.network.Network`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/networks/Network)

<br />

    tf_agents.networks.Network(
        input_tensor_spec=None, state_spec=(), name=None
    )

### Used in the notebooks

| Used in the tutorials |
|---|
| - [Policies](https://www.tensorflow.org/agents/tutorials/3_policies_tutorial) - [Networks](https://www.tensorflow.org/agents/tutorials/8_networks_tutorial) |

The main differences between a TF-Agents Network and a Keras Layer include:
networks keep track of their underlying layers, explicitly represent RNN-like
state in inputs and outputs, and simplify variable creation and clone
operations.

When calling a network `net`, typically one passes data through it via:

    outputs, next_state = net(observation, network_state=...)
    outputs, next_state = net(observation, step_type=..., network_state=...)
    outputs, next_state = net(observation)  # net.call must fill an empty state
    outputs, next_state = net(observation, step_type=...)
    outputs, next_state = net(
        observation, step_type=..., network_state=..., learning=...)

etc.

To force construction of a network's variables:

    net.create_variables()
    net.create_variables(input_tensor_spec=...)  # To provide an input spec
    net.create_variables(training=True)  # Provide extra kwargs
    net.create_variables(input_tensor_spec, training=True)

To create a copy of the network:

    cloned_net = net.copy()
    cloned_net.variables  # Raises ValueError: cloned net does not share weights.
    cloned_net.create_variables(...)
    cloned_net.variables  # Now new variables have been created.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `input_tensor_spec` | A nest of [`tf.TypeSpec`](https://www.tensorflow.org/api_docs/python/tf/TypeSpec) representing the input observations. Optional. If not provided, `create_variables()` will fail unless a spec is provided. |
| `state_spec` | A nest of `tensor_spec.TensorSpec` representing the state needed by the network. Default is `()`, which means no state. |
| `name` | (Optional.) A string representing the name of the network. |

<br />

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `input_tensor_spec` | Returns the spec of the input to the network of type InputSpec. |
| `layers` | Get the list of all (nested) sub-layers used in this Network. |
| `state_spec` | <br /> <br /> |

<br />

## Methods

### `copy`

[View source](https://github.com/tensorflow/agents/blob/v0.19.0/tf_agents/networks/network.py#L341-L355)

    copy(
        **kwargs
    )

Create a shallow copy of this network.

> [!NOTE]
> **Note:** Network layer weights are *never* copied. This method recreates the `Network` instance with the same arguments it was initialized with (excepting any new kwargs).

<br />

<br />

<br />

| Args ||
|---|---|
| `**kwargs` | Args to override when recreating this network. Commonly overridden args include 'name'. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A shallow copy of this network. ||

<br />

### `create_variables`

[View source](https://github.com/tensorflow/agents/blob/v0.19.0/tf_agents/networks/network.py#L188-L252)

    create_variables(
        input_tensor_spec=None, **kwargs
    )

Force creation of the network's variables.

Return output specs.

<br />

<br />

<br />

| Args ||
|---|---|
| `input_tensor_spec` | (Optional). Override or provide an input tensor spec when creating variables. |
| `**kwargs` | Other arguments to `network.call()`, e.g. `training=True`. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| Output specs - a nested spec calculated from the outputs (excluding any batch dimensions). If any of the output elements is a tfp `Distribution`, the associated spec entry returned is a `DistributionSpec`. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ValueError` | If no `input_tensor_spec` is provided, and the network did not provide one during construction. |

<br />

### `get_initial_state`

[View source](https://github.com/tensorflow/agents/blob/v0.19.0/tf_agents/networks/network.py#L465-L476)

    get_initial_state(
        batch_size=None
    )

Returns an initial state usable by the network.

<br />

<br />

<br />

| Args ||
|---|---|
| `batch_size` | Tensor or constant: size of the batch dimension. Can be None in which case not dimensions gets added. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A nested object of type `self.state_spec` containing properly initialized Tensors. ||

<br />

### `get_layer`

[View source](https://github.com/tensorflow/agents/blob/v0.19.0/tf_agents/networks/network.py#L279-L314)

    get_layer(
        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).

<br />

<br />

<br />

| Args ||
|---|---|
| `name` | String, name of layer. |
| `index` | Integer, index of layer. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A layer instance. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ValueError` | In case of invalid layer name or index. |

<br />

### `summary`

[View source](https://github.com/tensorflow/agents/blob/v0.19.0/tf_agents/networks/network.py#L316-L339)

    summary(
        line_length=None, positions=None, print_fn=None
    )

Prints a string summary of the network.

<br />

<br />

<br />

| Args ||
|---|---|
| `line_length` | Total length of printed lines (e.g. set this to adapt the display to different terminal window sizes). |
| `positions` | Relative or absolute positions of log elements in each line. If not provided, defaults to `[.33, .55, .67, 1.]`. |
| `print_fn` | Print function to use. Defaults to `print`. It will be called on each line of the summary. You can set it to a custom function in order to capture the string summary. |

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ValueError` | if `summary()` is called before the model is built. |

<br />