STTNOptions
Options & Configuration · AiDotNet.Video.Options
Configuration options for the STTN (Spatial-Temporal Transformer Network) video inpainting model.
Inheritance: ModelOptions → STTNOptions
For Beginners
STTN options configure the spatial-temporal transformer inpainting network.
How It Works
References:
- Paper: “Learning Joint Spatial-Temporal Transformations for Video Inpainting” (Zeng et al., ECCV 2020)
STTN uses multi-scale spatial-temporal transformers to simultaneously search for and attend to relevant patches across space and time, filling masked regions with content from visible areas in the same and other frames.
Constructors
| Constructor | Summary |
|---|---|
STTNOptions() |
Initializes a new instance with default values. |
STTNOptions(STTNOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
OnnxModelOptions OnnxOptions { get; set; } |
ONNX runtime options for inference mode. |
VideoModelVariant Variant { get; set; } |
Model variant controlling capacity and speed trade-off. |
double DropoutRate { get; set; } |
Dropout rate for regularization. |
double LearningRate { get; set; } |
Learning rate for training. |
int NumFeatures { get; set; } |
Number of base feature channels. |
int NumHeads { get; set; } |
Number of attention heads for multi-head spatial-temporal attention. |
int NumScales { get; set; } |
Number of scales for multi-scale patch matching. |
int NumTransformerLayers { get; set; } |
Number of spatial-temporal transformer layers. |
string ModelPath { get; set; } |
Path to the ONNX model file for inference mode. |