Package ai.djl.basicmodelzoo.cv.classification

Class MobileNetV2

java.lang.Object

ai.djl.basicmodelzoo.cv.classification.MobileNetV2

public final class MobileNetV2
extends Object

MobileNetV2 contains a generic implementation of MobilenetV2 adapted from https://github.com/weiaicunzai/pytorch-cifar100/blob/master/models/mobilenetv2.py (Original author weiaicunzai).

see https://arxiv.org/pdf/1801.04381.pdf for more information about MobileNetV2

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static final class	MobileNetV2.Builder	The Builder to construct a MobileNetV2 object.

Field Summary

Fields

Modifier and Type	Field	Description
static final int	FILTERLENGTH
static final int	MULTILENGTH
static final int	REPEATLENGTH
static final int	STRIDELENGTH

Method Summary

Modifier and Type	Method	Description
static MobileNetV2.Builder	builder()	Creates a builder to build a MobileNetV2.
static ai.djl.nn.Block	linearBottleNeck(int inputChannels, int outputChannels, int stride, int t, float batchNormMomentum)	Builds a Block that represent an inverted residual Unit used in the implementation of the MobileNetV2 Model.
static ai.djl.nn.Block	makeStage(int repeat, int inputChannels, int outputChannels, int stride, int t, float batchNormMomentum)	Builds a Block that represent multiple repeats of an inverted residual Unit.
static ai.djl.nn.Block	mobilenetV2(MobileNetV2.Builder builder)	Creates a new Block of MobileNetV2 with the arguments from the given MobileNetV2.Builder.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Details

FILTERLENGTH

public static final int FILTERLENGTH

See Also:

• Constant Field Values

REPEATLENGTH

public static final int REPEATLENGTH

See Also:

• Constant Field Values

STRIDELENGTH

public static final int STRIDELENGTH

See Also:

• Constant Field Values

MULTILENGTH

public static final int MULTILENGTH

See Also:

• Constant Field Values

Method Details

linearBottleNeck

public static ai.djl.nn.Block linearBottleNeck(int inputChannels,
 int outputChannels,
 int stride,
 int t,
 float batchNormMomentum)

Builds a Block that represent an inverted residual Unit used in the implementation of the MobileNetV2 Model.

Parameters:

inputChannels - number of inputChannels of the block

outputChannels - number of outputChannels of the block

stride - control the stride of a depthWise kernel

t - the multiTime of the first pointWise Block

batchNormMomentum - the momentum of batchNormLayer

Returns:

a Block that represent an inverted residual Unit

makeStage

public static ai.djl.nn.Block makeStage(int repeat,
 int inputChannels,
 int outputChannels,
 int stride,
 int t,
 float batchNormMomentum)

Builds a Block that represent multiple repeats of an inverted residual Unit.

Parameters:

repeat - the repeatTimes of an inverted residual Block

inputChannels - number of inputChannels of the block

outputChannels - number of outputChannels of the block

stride - the stride of an inverted residual Unit

t - the multipleTime of a pointWise Kernel

batchNormMomentum - the momentum of batchNormLayer

Returns:

a Block that represent several repeated inverted residual Units

mobilenetV2

public static ai.djl.nn.Block mobilenetV2(MobileNetV2.Builder builder)

Creates a new Block of MobileNetV2 with the arguments from the given MobileNetV2.Builder.

Parameters:

builder - the MobileNetV2.Builder with the necessary arguments

Returns:

a Block that represents the required MobileNetV2 model

builder

public static MobileNetV2.Builder builder()

Creates a builder to build a MobileNetV2.

Returns:

a new builder