CATSegOptions
Options & Configuration · AiDotNet.ComputerVision.Segmentation.OpenVocabulary
Configuration options for CAT-Seg cost aggregation open-vocabulary segmentation.
Inheritance: ModelOptions → NeuralNetworkOptions → ModelHyperparameterOptions → SegmentationModelOptions → TextQueriedSegmentationOptions → CATSegOptions
For Beginners
These options configure the CATSeg model. Default values follow the original paper settings.
Constructors
| Constructor | Summary |
|---|---|
CATSegOptions() |
Initializes a new instance with default values. |
CATSegOptions(CATSegOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
double LearningRate { get; set; } |
Gets or sets the base AdamW learning rate. |
double MaxGradientNorm { get; set; } |
Gets or sets the maximum global gradient norm used by AdamW. |
double WeightDecay { get; set; } |
Gets or sets the decoupled AdamW weight decay. |
Methods
| Method | Summary |
|---|---|
void Validate() |
Throws when a value on this instance cannot produce a working model. |