OpenVocabSAMOptions

Options & Configuration · AiDotNet.ComputerVision.Segmentation.OpenVocabulary

Configuration options for Open-Vocabulary SAM interactive recognition.

Inheritance: ModelOptions → NeuralNetworkOptions → ModelHyperparameterOptions → SegmentationModelOptions → TextQueriedSegmentationOptions → OpenVocabSAMOptions

For Beginners

These options configure the OpenVocabSAM model. Default values follow the original paper settings.

Constructors

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

Properties

Property Summary
double LearningRate { get; set; } Gets or sets the AdamW learning rate.
double WeightDecay { get; set; } Gets or sets the AdamW weight decay.
int DecoderDimension { get; set; } Gets or sets the CLIP2SAM FPN and mask-decoder channel dimension.
int NeckEmbeddingDimension { get; set; } Gets or sets the SAM2CLIP transformer-neck embedding dimension.
int[] ChannelDimensions { get; set; } Gets or sets the four CLIP RN50x16 feature-stage channel dimensions.
int[] StageDepths { get; set; } Gets or sets the four CLIP RN50x16 residual-stage depths.

Methods

Method Summary
void Validate() Throws when a value on this instance cannot produce a working model.