FoundationalVLMOptions
Options & Configuration ยท AiDotNet.VisionLanguage.Foundational
Base configuration options for foundational vision-language fusion models.
Inheritance: ModelOptions โ FoundationalVLMOptions
Known derived types: BridgeTowerOptions, LXMERTOptions, METEROptions, OscarOptions, UNITEROptions, ViLBERTOptions, ViLTOptions, VinVLOptions, VisualBERTOptions
For Beginners
These options configure the Foundational model. Default values follow the original paper settings.
Constructors
| Constructor | Summary |
|---|---|
FoundationalVLMOptions() |
Initializes a new instance with default values. |
FoundationalVLMOptions(FoundationalVLMOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
FusionType FusionType { get; set; } |
Gets or sets the fusion type. |
OnnxModelOptions OnnxOptions { get; set; } |
Gets or sets ONNX runtime options. |
VisualFeatureType VisualFeatureType { get; set; } |
Gets or sets the visual feature type. |
double DropoutRate { get; set; } |
Gets or sets the dropout rate. |
double LearningRate { get; set; } |
Gets or sets the learning rate. |
double WeightDecay { get; set; } |
Gets or sets the weight decay. |
double[] ImageMean { get; set; } |
Gets or sets the per-channel image normalization mean. |
double[] ImageStd { get; set; } |
Gets or sets the per-channel image normalization std. |
int FusionDim { get; set; } |
Gets or sets the fusion/hidden dimension. |
int ImageSize { get; set; } |
Gets or sets the input image size. |
int MaxSequenceLength { get; set; } |
Gets or sets the maximum text sequence length. |
int NumFusionLayers { get; set; } |
Gets or sets the number of cross-modal/fusion layers. |
int NumHeads { get; set; } |
Gets or sets the number of attention heads. |
int NumTextLayers { get; set; } |
Gets or sets the number of text encoder layers. |
int NumVisionLayers { get; set; } |
Gets or sets the number of vision encoder layers. |
int TextDim { get; set; } |
Gets or sets the text embedding dimension. |
int VisionDim { get; set; } |
Gets or sets the vision feature dimension. |
int VocabSize { get; set; } |
Gets or sets the vocabulary size. |
string ModelPath { get; set; } |
Gets or sets the ONNX model path. |