FlattenLayer class

A utility layer that flattens a multi-dimensional tensor into a 1D vector.

A FlattenLayer has no trainable parameters. Its primary role is to act as a bridge between layers that output multi-dimensional data (like ConvLSTMLayer or Conv2D) and layers that expect a 1D vector input (like DenseLayer).

Example

SNetwork model = SNetwork([
  ConvLSTMLayer(8, 3), // Outputs a 2D feature map
  FlattenLayer(),      // Flattens the map into a vector
  DenseLayer(1),       // Processes the vector
]);

Inheritance

• Object
• Layer
• FlattenLayer

Constructors

FlattenLayer()

Properties

hashCode → int

The hash code for this object.

no setter, inherited

inputCols ↔ int

getter/setter pair

inputRows ↔ 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>

Returns an empty list as this layer has no trainable parameters.

no setter, override

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

Methods

build(Tensor input) → void

Records the input dimensions, which are needed for the backward pass.

override

call(Tensor input) → Tensor

The public, callable interface for the layer.

inherited

forward(Tensor input) → Tensor<Vector>

Unrolls the input matrix into a single, long vector.

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