MaxPool3DLayer<T>
Layers ยท AiDotNet.NeuralNetworks.Layers
Represents a 3D max pooling layer for downsampling volumetric data.
Inheritance: LayerBase<T> โ MaxPool3DLayer<T>
Implements: IShapeContract
For Beginners
Max pooling works like summarizing a 3D region by keeping only the largest value.
Think of it like this:
- You have a 3D grid of numbers
- You divide it into small cubes (e.g., 2x2x2)
- For each cube, you keep only the largest number
- This makes your data smaller while keeping the important features
This is useful because:
- It reduces the amount of computation needed
- It helps the network focus on the most important features
- It makes the network more robust to small position changes
How It Works
A 3D max pooling layer reduces the spatial dimensions (depth, height, width) of volumetric data while preserving the most prominent features. This helps reduce computational cost and provides translation invariance.
Constructors
| Constructor | Summary |
|---|---|
MaxPool3DLayer(int poolSize, int stride) |
Initializes a new instance of the MaxPool3DLayer class. |
Properties
| Property | Summary |
|---|---|
bool SupportsTraining { get; } |
Gets a value indicating whether this layer supports training (backpropagation). |
int PoolSize { get; set; } |
Gets the size of the pooling window (same for depth, height, width). |
int Stride { get; set; } |
Gets the stride (step size) for moving the pooling window. |
Methods
| Method | Summary |
|---|---|
IEnumerable<ActivationFunction> GetActivationTypes() |
Gets the activation function types used by this layer. |
IReadOnlyList<OutputAxisContract> OutputAxesFor(int inputRank) |
|
void ResetState() |
Resets the cached state from forward/backward passes. |