<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/models/blob/v2.20.0/official/nlp/modeling/layers/multi_channel_attention.py#L106-L176) |

Multi-channel Attention layer.

    tfm.nlp.layers.MultiChannelAttention(
        num_heads,
        key_dim,
        value_dim=None,
        dropout=0.0,
        use_bias=True,
        output_shape=None,
        attention_axes=None,
        kernel_initializer='glorot_uniform',
        bias_initializer='zeros',
        kernel_regularizer=None,
        bias_regularizer=None,
        activity_regularizer=None,
        kernel_constraint=None,
        bias_constraint=None,
        **kwargs
    )

Introduced in, [Generating Representative Headlines for News Stories](https://arxiv.org/abs/2001.09386). Expects multiple cross-attention
target sequences.

<br />

<br />

<br />

| ## Call args ||
|---|---|
| `query` | Query `Tensor` of shape `[B, T, dim]`. |
| `value` | Value `Tensor` of shape `[B, A, S, dim]`, where A denotes the |
| `context_attention_weights` | Context weights of shape `[B, N, T, A]`, where N is the number of attention heads. Combines multi-channel sources context tensors according to the distribution among channels. |
| `key` | Optional key `Tensor` of shape `[B, A, S, dim]`. If not given, will use `value` for both `key` and `value`, which is the most common case. |
| `attention_mask` | A boolean mask of shape `[B, T, S]`, that prevents attention to certain positions. |

<br />

## Methods

### `call`

[View source](https://github.com/tensorflow/models/blob/v2.20.0/official/nlp/modeling/layers/multi_channel_attention.py#L129-L176)

    call(
        query, value, key=None, context_attention_weights=None, attention_mask=None
    )

This is where the layer's logic lives.

The `call()` method may not create state (except in its first
invocation, wrapping the creation of variables or other resources in
[`tf.init_scope()`](https://www.tensorflow.org/api_docs/python/tf/init_scope)). It is recommended to create state, including
[`tf.Variable`](https://www.tensorflow.org/api_docs/python/tf/Variable) instances and nested `Layer` instances,
in `__init__()`, or in the `build()` method that is
called automatically before `call()` executes for the first time.

<br />

<br />

<br />

| Args ||
|---|---|
| `inputs` | Input tensor, or dict/list/tuple of input tensors. The first positional `inputs` argument is subject to special rules: <br /> - `inputs` must be explicitly passed. A layer cannot have zero arguments, and `inputs` cannot be provided via the default value of a keyword argument. - NumPy array or Python scalar values in `inputs` get cast as tensors. - TF-Keras mask metadata is only collected from `inputs`. - Layers are built (`build(input_shape)` method) using shape info from `inputs` only. - `input_spec` compatibility is only checked against `inputs`. - Mixed precision input casting is only applied to `inputs`. If a layer has tensor arguments in `*args` or `**kwargs`, their casting behavior in mixed precision should be handled manually. - The SavedModel input specification is generated using `inputs` only. - Integration with various ecosystem packages like TFMOT, TFLite, TF.js, etc is only supported for `inputs` and not for tensors in positional and keyword arguments. |
| `*args` | Additional positional arguments. May contain tensors, although this is not recommended, for the reasons above. |
| `**kwargs` | Additional keyword arguments. May contain tensors, although this is not recommended, for the reasons above. The following optional keyword arguments are reserved: - `training`: Boolean scalar tensor of Python boolean indicating whether the `call` is meant for training or inference. - `mask`: Boolean input mask. If the layer's `call()` method takes a `mask` argument, its default value will be set to the mask generated for `inputs` by the previous layer (if `input` did come from a layer that generated a corresponding mask, i.e. if it came from a TF-Keras layer with masking support). |

<br />

<br />

<br />

| Returns ||
|---|---|
| A tensor or list/tuple of tensors. ||

<br />