AveragePooling2DLayer class

A 2D average pooling layer.

This layer downsamples an input feature map by taking the average value over a specified window (poolSize). It provides a smoother form of downsampling compared to MaxPooling2DLayer.

• Input: A Tensor<Matrix> representing a single feature map of shape [height, width].
• Output: A Tensor<Matrix> representing the downsampled feature map.

Example

SNetwork model = SNetwork([
  Conv2DLayer(16, 3, activation: ReLU()),
  AveragePooling2DLayer(poolSize: 2, stride: 2),
]);

Inheritance

• Object
• Layer
• AveragePooling2DLayer

Constructors

AveragePooling2DLayer({int poolSize = 2, int stride = 2})

Properties

hashCode → int

The hash code for this object.

no setter, inherited

inputHeight ↔ int

getter/setter pair

inputWidth ↔ int

getter/setter pair

name ↔ String

A user-friendly name for the layer (e.g., 'dense', 'lstm').

getter/setter pair, override-getter

parameters → List<Tensor>

A list of all trainable tensors (weights and biases) in the layer.

no setter, override

poolSize ↔ int

getter/setter pair

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

stride ↔ int

getter/setter pair

Methods

build(Tensor input) → void

Initializes the layer's parameters based on the shape of the first input.

override

call(Tensor input) → Tensor

The public, callable interface for the layer.

inherited

forward(Tensor input) → Tensor<Matrix>

The core logic of the layer's transformation.

override

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited