# helia_edge.models.tsmixer

## TsMixer Model

### Overview

TsMixer is a fully MLP-based architecture for time series data.

For more info, refer to the original paper [TsMixer: An All-MLP Architecture for Time Series](https://arxiv.org/abs/2303.06053).

Parameters are in ``helia_edge.models.tsmixer_params``.

**Functions**

| Name | Description |
| --- | --- |
| `build` | TsMixer model from ``TsMixerParams`` |
| `ts_block` | Residual block of TsMixer |
| `norm_layer` | Normalization layer |
| `tsmixer_layer` | TsMixer layer |

## helia_edge.models.tsmixer.norm_layer

`function` · `python`

```python
norm_layer(norm: str, name: str) -> keras.Layer
```

Normalization layer

**Parameters**

| Name | Type | Default | Description |
| --- | --- | --- | --- |
| norm | str | Required | Normalization type |
| name | str | Required | Name |

**Returns**

| Name | Type | Description |
| --- | --- | --- |
|  | keras.Layer | keras.Layer: Layer |

Source: `helia_edge/models/tsmixer.py:25`

## helia_edge.models.tsmixer.ts_block

`function` · `python`

```python
ts_block(params: TsMixerBlockParams, name: str) -> keras.Layer
```

Residual block of TSMixer.

**Parameters**

| Name | Type | Default | Description |
| --- | --- | --- | --- |
| params | TsBlockParams | Required | Block parameters |
| name | str | Required | Name |

**Returns**

| Name | Type | Description |
| --- | --- | --- |
|  | keras.Layer | keras.Layer: Layer |

Source: `helia_edge/models/tsmixer.py:54`

## helia_edge.models.tsmixer.tsmixer_layer

`function` · `python`

```python
tsmixer_layer(inputs: keras.KerasTensor, params: any) -> keras.KerasTensor
```

TsMixer layer

**Parameters**

| Name | Type | Default | Description |
| --- | --- | --- | --- |
| inputs | keras.KerasTensor | Required | Input tensor |
| params | any | Required | Model parameters |

**Returns**

| Name | Type | Description |
| --- | --- | --- |
|  | keras.KerasTensor | keras.KerasTensor: Output tensor |

Source: `helia_edge/models/tsmixer.py:93`

## helia_edge.models.tsmixer.build

`function` · `python`

```python
build(
    params: TsMixerParams,
    input_shape: tuple[int | None, ...],
    *,
    batch_size: int | None = None,
    name: str | None = None,
) -> keras.Model
```

Build a TsMixer model.

**Parameters**

| Name | Type | Default | Description |
| --- | --- | --- | --- |
| params | TsMixerParams | Required | Model parameters. |
| input_shape | tuple[int \| None, ...] | Required | Input shape without the batch axis; None for a variable axis. |
| batch_size | int \| None | None | Static batch size; None for a dynamic batch. |
| name | str \| None | None | Model name; the family when None. |

**Returns**

| Name | Type | Description |
| --- | --- | --- |
|  | keras.Model | keras.Model: The model, named ``tsmixer`` unless ``name`` is given. |

Source: `helia_edge/models/tsmixer.py:117`