SelfSupervisedLearningAugmentationContext<T>
Models & Types · AiDotNet.SelfSupervisedLearning
Context for SSL augmentation operations.
For Beginners
This provides information and state for creating augmented views. SSL methods typically create multiple views of each input for contrastive/self-supervised learning.
Constructors
| Constructor | Summary |
|---|---|
SelfSupervisedLearningAugmentationContext() |
Properties
| Property | Summary |
|---|---|
Tensor<T> PrecomputedView { get; set; } |
Gets or sets optional pre-computed augmentations. |
bool IsFirstView { get; set; } |
Gets or sets whether this is the first view (used in multi-view methods). |
double StrengthMultiplier { get; set; } |
Gets or sets the augmentation strength multiplier. |
int TotalViews { get; set; } |
Gets or sets the total number of views being generated. |
int ViewIndex { get; set; } |
Gets or sets the view index for methods that use more than 2 views. |
int? Seed { get; set; } |
Gets or sets the random seed for reproducible augmentations. |