OWLViTOptions
Options & Configuration · AiDotNet.VisionLanguage.Grounding
Configuration options for OWL-ViT: open-vocabulary object detection via ViT + CLIP alignment.
Inheritance: ModelOptions → GenerativeVLMOptions → GroundingVLMOptions → OWLViTOptions
For Beginners
These options configure the OWLViT model. Default values follow the original paper settings.
Constructors
| Constructor | Summary |
|---|---|
OWLViTOptions() |
Initializes a new instance with default values. |
OWLViTOptions(OWLViTOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
int DetectionDim { get; set; } |
Gets or sets the detection-decoder feature width. |
int NumClassEmbeddings { get; set; } |
Gets or sets the class embedding dimension. |
int NumFusionLayers { get; set; } |
Gets or sets the number of cross-modal fusion layers. |
int NumTextLayers { get; set; } |
Gets or sets the number of layers of the CLIP text transformer that embeds the text queries (12). |
int TextEmbeddingDim { get; set; } |
Gets or sets the text-encoder feature width. |