MeshCNNOptions

Options & Configuration · AiDotNet.Models.Options

Configuration options for the MeshCNN neural network.

Inheritance: ModelOptions → NeuralNetworkOptions → MeshCNNOptions

For Beginners

These options control how the MeshCNN network is configured. The defaults are set to match the original paper and work well for most 3D shape classification and segmentation tasks.

How It Works

MeshCNN is a deep learning architecture for processing 3D mesh data. It operates directly on the mesh structure using edge convolutions and mesh pooling operations.

Constructors

Constructor Summary
MeshCNNOptions()

Properties

Property Summary
bool UseBatchNorm { get; set; } Gets or sets whether to use batch normalization after each conv layer.
bool UseGlobalAveragePooling { get; set; } Gets or sets whether to use global average pooling before FC layers.
double DropoutRate { get; set; } Gets or sets the dropout rate for regularization.
double LearningRate { get; set; } Gets or sets the initial learning rate for training.
int InputFeatures { get; set; } Gets or sets the number of input features per edge.
int NumClasses { get; set; } Gets or sets the number of output classes for classification.
int NumNeighbors { get; set; } Gets or sets the number of neighboring edges to consider for each edge.
int[] ConvChannels { get; set; } Gets or sets the channel sizes for each edge convolution block.
int[] FullyConnectedSizes { get; set; } Gets or sets the sizes of fully connected layers before output.
int[] PoolTargets { get; set; } Gets or sets the target edge counts after each pooling operation.