VoxelModelOptions

Options & Configuration · AiDotNet.Models.Options

Shared hyperparameters for the volumetric models that work on a 3D voxel grid.

Inheritance: ModelOptions → NeuralNetworkOptions → ModelHyperparameterOptions → VoxelModelOptions

Known derived types: UNet3DOptions, VoxelCNNOptions

For Beginners

A voxel is a pixel in three dimensions. These models take a cube of voxels as input, so the two settings they share are how finely that cube is divided and how wide the first layer is.

How It Works

The block count is not here: VoxelCNN counts convolution blocks and UNet3D counts encoder blocks, and those names describe genuinely different structures, so each keeps its own.

Properties

Property Summary
double LearningRate { get; set; } Gets or sets the learning rate used when the model creates its own optimizer.
int BaseFilters { get; set; } Gets or sets the number of filters in the first convolution layer.
int VoxelResolution { get; set; } Gets or sets the number of voxels along each edge of the input cube.