MobileNetV3Configuration

Options & Configuration · AiDotNet.Configuration

Configuration options for MobileNetV3 neural network architectures.

For Beginners

MobileNetV3 comes in Large (more accurate) and Small (faster) variants. Choose based on whether you prioritize accuracy or speed.

How It Works

MobileNetV3 builds on MobileNetV2 with additional optimizations including squeeze-and-excitation blocks and hard-swish activation for improved accuracy.

Constructors

Constructor Summary
MobileNetV3Configuration(MobileNetV3Variant variant, int numClasses, MobileNetV3WidthMultiplier widthMultiplier, int inputHeight, int inputWidth, int inputChannels) Initializes a new instance of the MobileNetV3Configuration class.

Properties

Property Summary
MobileNetV3Variant Variant { get; } Gets the MobileNetV3 variant to use.
MobileNetV3WidthMultiplier WidthMultiplier { get; } Gets the width multiplier for the network.
double Alpha { get; } Gets the alpha value (width multiplier as a double).
int InputChannels { get; } Gets the number of input channels.
int InputHeight { get; } Gets the height of input images in pixels.
int InputWidth { get; } Gets the width of input images in pixels.
int NumClasses { get; } Gets the number of output classes for classification.
int[] InputShape { get; } Gets the computed input shape as [channels, height, width].

Methods

Method Summary
MobileNetV3Configuration CreateLarge(int numClasses) Creates a MobileNetV3-Large configuration (recommended default).
MobileNetV3Configuration CreateSmall(int numClasses) Creates a MobileNetV3-Small configuration for low-latency applications.