convmixer

ConvMixer

For more info, refer to the original paper ConvMixer: Revisiting Convolution in Vision.

Functions

Name	Description
`build`	ConvMixer model from `ConvMixerParams`
`conv_mixer_block`	ConvMixer block
`conv_mixer_layer`	ConvMixer layer

Machine-readable model

conv_mixer_blockfunctionConvMixer block
conv_mixer_layerfunctionConvMixer: https://openreview.net/pdf?id=TVHS5Y4dNvM.
buildfunctionBuild a ConvMixer model.

conv_mixer_block(filters: int, kernel_size: int) -> Callable[[keras.KerasTensor], keras.KerasTensor]

ConvMixer block

Parameters

Parameters of conv_mixer_block
Name	Type	Default	Description
`filters`	`int`	Required	Number of filters
`kernel_size`	`int`	Required	Kernel size

conv_mixer_layer(x: keras.KerasTensor, params: ConvMixerParams) -> keras.KerasTensor

ConvMixer: https://openreview.net/pdf?id=TVHS5Y4dNvM.

Parameters

Parameters of conv_mixer_layer
Name	Type	Default	Description
`x`	`keras.KerasTensor`	Required	Input tensor
`params`	`ConvMixerParams`	Required	Model parameters.

Returns

Returns of conv_mixer_layer
Type	Description
`keras.KerasTensor`	keras.KerasTensor: Model output

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

Build a ConvMixer model.

Parameters

Parameters of build
Name	Type	Default	Description
`params`	`ConvMixerParams`	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

Returns of build
Type	Description
`keras.Model`	keras.Model: The model, named ``convmixer`` unless ``name`` is given.