Class SequentialBlock

java.lang.Object

smile.deep.layer.LayerBlock

smile.deep.layer.SequentialBlock

All Implemented Interfaces:

Function<Tensor,Tensor>, Layer

Direct Known Subclasses:

Conv2dNormActivation

public class SequentialBlock
extends LayerBlock

A block of sequential layers. Layers will be added to it in the order they are passed in the constructor. The forward() method of SequentialBlock accepts any input and forwards it to the first layer it contains. It then "chains" outputs to inputs sequentially for each subsequent module, finally returning the output of the last layer.

Field Summary

Fields inherited from class LayerBlock

device, dtype, module

Constructor Summary

Constructors

Constructor	Description
SequentialBlock()	Constructor.
SequentialBlock(String name)	Constructor.
SequentialBlock(Layer... layers)	Constructor.

Method Summary

Modifier and Type	Method	Description
SequentialBlock	add(Layer layer)	Adds a layer to the sequential block.
Tensor	forward(Tensor input)	Forward propagation (or forward pass) through the layer.

Methods inherited from class LayerBlock

add, add, asTorch, device, dtype, eval, isTraining, load, save, to, to, toString, train

Methods inherited from class Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Methods inherited from interface Function

andThen, compose

Methods inherited from interface Layer

apply

Constructor Details

SequentialBlock

public SequentialBlock()

Constructor.

SequentialBlock

public SequentialBlock(String name)

Constructor.

Parameters:

name - the module name.

SequentialBlock

public SequentialBlock(Layer... layers)

Constructor.

Parameters:

layers - the neural network layers.

Method Details

add

public SequentialBlock add(Layer layer)

Adds a layer to the sequential block.

Parameters:

layer - a layer.

Returns:

this object.

forward

public Tensor forward(Tensor input)

Description copied from interface: Layer

Forward propagation (or forward pass) through the layer.

Parameters:

input - the input tensor.

Returns:

the output tensor.