XDecoderOptions
Options & Configuration · AiDotNet.ComputerVision.Segmentation.Foundation
Configuration options for the X-Decoder model.
Inheritance: ModelOptions → NeuralNetworkOptions → ModelHyperparameterOptions → PanopticSegmentationOptions → XDecoderOptions
For Beginners
X-Decoder is a generalist vision decoder that handles referring segmentation, open-vocabulary segmentation, and image captioning in one model. Options inherit from NeuralNetworkOptions.
Constructors
| Constructor | Summary |
|---|---|
XDecoderOptions() |
Initializes a new instance with default values. |
XDecoderOptions(XDecoderOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
XDecoderModelSize ModelSize { get; set; } |
Gets or sets the backbone size variant. |
int? NumStuffClasses { get; set; } |
Number of stuff (non-countable background) classes for panoptic segmentation. |
Methods
| Method | Summary |
|---|---|
void Validate() |
Throws if a value this model requires has been left unset or is inconsistent. |