VideoLISAOptions

Options & Configuration · AiDotNet.ComputerVision.Segmentation.Referring

Configuration options for VideoLISA video reasoning segmentation.

Inheritance: ModelOptions → NeuralNetworkOptions → ModelHyperparameterOptions → SegmentationModelOptions → TextQueriedSegmentationOptions → ReferringSegmentationOptions → VideoLISAOptions

For Beginners

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

Constructors

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

Properties

Property Summary
double LearningRate { get; set; } Gets or sets the AdamW learning rate used by native training.
double WeightDecay { get; set; } Gets or sets the AdamW weight-decay coefficient used by native training.
int DecoderDimension { get; set; } Gets or sets the hidden channel width of the promptable mask decoder.
int[] ChannelDimensions { get; set; } Gets or sets the output channel width of each visual-encoder stage.
int[] EncoderDepths { get; set; } Gets or sets the number of convolutional blocks in each visual-encoder stage.

Methods

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