VisionEncoderOptions

Options & Configuration ยท AiDotNet.VisionLanguage.Encoders

Base configuration options for standalone vision encoder models.

Inheritance: ModelOptions โ†’ VisionEncoderOptions

Known derived types: DINOv2Options, DINOv3Options, Florence2Options, InternViTOptions, PerceptionEncoderOptions, RADIOv25Options, SAMOptions, SigLIPSOOptions, ViTOptions

How It Works

Vision encoders extract feature representations from images without a paired text encoder. They are used as backbones for downstream VLMs, classification, detection, and segmentation tasks.

Constructors

Constructor Summary
VisionEncoderOptions() Initializes a new instance with default values.
VisionEncoderOptions(VisionEncoderOptions other) Initializes a new instance by copying from another instance.

Properties

Property Summary
OnnxModelOptions OnnxOptions { get; set; } Gets or sets ONNX runtime options.
double DropoutRate { get; set; } Gets or sets the dropout rate for regularization.
double LearningRate { get; set; } Gets or sets the initial learning rate.
double WeightDecay { get; set; } Gets or sets the weight decay for regularization.
double[] ImageMean { get; set; } Gets or sets the per-channel mean for image normalization.
double[] ImageStd { get; set; } Gets or sets the per-channel standard deviation for image normalization.
int EmbeddingDim { get; set; } Gets or sets the vision encoder embedding dimension.
int FfnMultiplier { get; set; } Gets or sets the feed-forward hidden dimension multiplier.
int ImageSize { get; set; } Gets or sets the input image size (height = width).
int NumHeads { get; set; } Gets or sets the number of attention heads.
int NumLayers { get; set; } Gets or sets the number of transformer layers.
int PatchSize { get; set; } Gets or sets the ViT patch size in pixels.
string ModelPath { get; set; } Gets or sets the path to the ONNX model file.