<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/mixing.py#L147-L194) |

Hartley Transform layer.

    tfm.nlp.layers.HartleyTransformLayer(
        use_fft: bool = False, name: str = 'hartley_transform', **kwargs
    )

Applies 2D Hartley Transform over final two dimensions of `query` inputs -
typically the sequence and hidden dimensions.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `use_fft` | Whether to use Fast Fourier Transform (True) or the Discrete Fourier Transform (DFT) matrix (False) to compute the Hartley Transform. See _pick_fourier_transform() for recommendations on when to use FFT or DFT. |
| `name` | Name for layer. |
| `**kwargs` | Keyword arguments. |

<br />

## Methods

### `call`

[View source](https://github.com/tensorflow/models/blob/v2.20.0/official/nlp/modeling/layers/mixing.py#L178-L194)

    call(
        query: tf.Tensor, value: tf.Tensor, **kwargs
    ) -> tf.Tensor

Applies layer to `query`.

<br />

<br />

<br />

| Args ||
|---|---|
| `query` | Batch of input embeddings, typically of shape \[batch_size, max_seq_length, hidden_dim\]. |
| `value` | Unused. Included to match attention layer API. |
| `**kwargs` | Optional arguments to catch unused attention keyword arguments. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| Real part of discrete Hartley Transform of `query` inputs with shape \[batch_size, max_seq_length, hidden_dim\]. ||

<br />