mobilenet

MobileNet Models API

This module provides utility functions to generate MobileNet models.

Parameters are in helia_edge.models.mobilenet_params.

Functions

Name	Description
build	MobileNetV1 model from MobileNetV1Params
mobilenetv1_layer	Modified MobileNetV1 layer

Machine-readable model

• mobilenetv1_layerfunctionModified MobileNetV1 MLPerf Tiny model for VWW: https://github.com/SiliconLabs/platformmlmodels/blob/master/eembc/Persondetection/mobilenetv1eembc.py
• buildfunctionBuild a MobileNetV1 model.

function

mobilenetv1_layer

Python

Modified MobileNetV1 MLPerf Tiny model for VWW: https://github.com/SiliconLabs/platformmlmodels/blob/master/eembc/Persondetection/mobilenetv1eembc.py

helia_edge/models/mobilenet.py:21

mobilenetv1_layer(x: keras.KerasTensor, params: MobileNetV1Params) -> keras.KerasTensor

Modified MobileNetV1 MLPerf Tiny model for VWW: https://github.com/SiliconLabs/platform_ml_models/blob/master/eembc/Person_detection/mobilenet_v1_eembc.py

Parameters

Parameters of mobilenetv1_layer

Name	Type	Default	Description
x	keras.KerasTensor	Required	Model input
params	MobileNetV1Params	Required	Model parameters

Returns

Returns of mobilenetv1_layer

Type	Description
keras.KerasTensor	keras.KerasTensor: Model output

function

build

Python

Build a MobileNetV1 model.

helia_edge/models/mobilenet.py:270

build(
    params: MobileNetV1Params,
    input_shape: tuple[int | None, ...],
    *,
    batch_size: int | None = None,
    name: str | None = None,
) -> keras.Model

Build a MobileNetV1 model.

Parameters

Parameters of build

Name	Type	Default	Description
params	MobileNetV1Params	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 ``mobilenet`` unless ``name`` is given.