SpatialTransform<T>
Models & Types · AiDotNet.Augmentation.Video
Applies spatial transformations (flips, rotations) consistently to all frames.
Inheritance: AugmentationBase<T, ImageTensor<T>[]> → VideoAugmenterBase<T> → SpatialVideoAugmenterBase<T> → SpatialTransform<T>
For Beginners
Spatial transform applies image augmentations like horizontal flip or rotation to all frames in the video consistently. This ensures the transformation is coherent across the entire video.
How It Works
Available transforms:
- Horizontal flip (mirror left-right)
- Vertical flip (mirror top-bottom)
- 90° rotation (clockwise)
- 180° rotation
- 270° rotation (counter-clockwise)
Constructors
| Constructor | Summary |
|---|---|
SpatialTransform(double horizontalFlipProbability, double verticalFlipProbability, double probability, double frameRate) |
Creates a new spatial transform augmentation. |
Properties
| Property | Summary |
|---|---|
bool EnableHorizontalFlip { get; set; } |
Gets or sets whether to enable horizontal flip. |
bool EnableRotation90 { get; set; } |
Gets or sets whether to enable 90° rotations. |
bool EnableVerticalFlip { get; set; } |
Gets or sets whether to enable vertical flip. |
double HorizontalFlipProbability { get; } |
Gets the probability of horizontal flip (when enabled). |
double VerticalFlipProbability { get; } |
Gets the probability of vertical flip (when enabled). |
Methods
| Method | Summary |
|---|---|
IDictionary<string, object> GetParameters() |