MobileNetV2Configuration
Options & Configuration · AiDotNet.Configuration
Configuration options for MobileNetV2 neural network architectures.
For Beginners
MobileNetV2 is optimized for mobile devices. The width multiplier lets you trade accuracy for speed - smaller values give faster but less accurate models.
How It Works
MobileNetV2 is designed for efficient mobile and edge deployment, using inverted residuals and linear bottlenecks to achieve high accuracy with low computational cost.
Constructors
| Constructor | Summary |
|---|---|
MobileNetV2Configuration(MobileNetV2WidthMultiplier widthMultiplier, int numClasses, int inputHeight, int inputWidth, int inputChannels) |
Initializes a new instance of the MobileNetV2Configuration class. |
Properties
| Property | Summary |
|---|---|
MobileNetV2WidthMultiplier 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 |
|---|---|
MobileNetV2Configuration CreateStandard(int numClasses) |
Creates a MobileNetV2 configuration with standard width (recommended default). |