SNetwork class

A sequential model that stacks layers linearly.

SNetwork provides a high-level API for building, training, and evaluating neural networks, similar to Keras's Sequential model. It manages the network's layers, parameters, and the entire training lifecycle.

Inheritance

• Object
• Layer
• SNetwork

Constructors

SNetwork(List<Layer> layers, {String name = 'snetwork'})

Properties

hashCode → int

The hash code for this object.

no setter, inherited

layers ↔ List<Layer>

getter/setter pair

name ↔ String

getter/setter pair, override-getter

optimizer ↔ Optimizer

getter/setter pair

parameters → List<Tensor>

no setter, override

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

Methods

build(Tensor input) → void

inherited

call(Tensor input) → Tensor

inherited

compile({required Optimizer configuredOptimizer}) → void

evaluate(List<List<double>> inputs, List<List<double>> targets) → void

fit(List<List<double>> inputs, List<List<double>> targets, {int epochs = 100, bool averageWeight = false, bool debug = true}) → void

forward(Tensor input) → Tensor

override

getWeights() → Map<String, dynamic>

override

inspectGraph(List<double> inputData, List<double> targetData) → void

load(String filePath) → Future<void>

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

predict(Tensor input) → Tensor

save(String filePath) → Future<void>

setWeights(Map<String, dynamic> networkWeights) → void

override

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited