GaussianNoise<T>
Models & Types · AiDotNet.Augmentation.Image
Adds Gaussian noise to an image.
Inheritance: AugmentationBase<T, ImageTensor<T>> → GaussianNoise<T>
For Beginners
Think of this like the “grain” you see in photos taken in low light. Adding random noise to training images teaches your model to focus on the real features rather than memorizing exact pixel values.
How It Works
Gaussian noise adds random values drawn from a normal (Gaussian) distribution to each pixel. This simulates sensor noise in cameras and helps the model become robust to noisy inputs.
When to use:
- When training data is too clean (synthetic or studio images)
- When deployed images may have sensor noise
- As a regularization technique to prevent overfitting
Constructors
| Constructor | Summary |
|---|---|
GaussianNoise(double mean, double minStd, double maxStd, double probability, double minValue, double maxValue) |
Creates a new Gaussian noise augmentation. |
Properties
| Property | Summary |
|---|---|
double MaxStd { get; } |
Gets the maximum standard deviation of the noise. |
double MaxValue { get; } |
Gets the maximum valid pixel value (for clamping). |
double Mean { get; } |
Gets the mean of the Gaussian distribution. |
double MinStd { get; } |
Gets the minimum standard deviation of the noise. |
double MinValue { get; } |
Gets the minimum valid pixel value (for clamping). |
Methods
| Method | Summary |
|---|---|
IDictionary<string, object> GetParameters() |