DiffCutSegmentationOptions
Options & Configuration · AiDotNet.ComputerVision.Segmentation.Diffusion
Configuration options for DiffCut diffusion-based zero-shot segmentation.
Inheritance: ModelOptions → NeuralNetworkOptions → ModelHyperparameterOptions → SegmentationModelOptions → DiffCutSegmentationOptions
For Beginners
These options configure the DiffCut model. Default values follow the original paper settings.
Constructors
| Constructor | Summary |
|---|---|
DiffCutSegmentationOptions() |
Initializes a new instance with default values. |
DiffCutSegmentationOptions(DiffCutSegmentationOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
int DecoderDimension { get; set; } |
Gets or sets the feature width of the native segmentation decoder. |
int[] ChannelDimensions { get; set; } |
Gets or sets the Stable-Diffusion U-Net encoder widths used by the native approximation. |
int[] StageDepths { get; set; } |
Gets or sets the number of residual blocks in each native encoder stage. |
Methods
| Method | Summary |
|---|---|
void Validate() |
Throws when a value on this instance cannot produce a working model. |