Package smile.vision.layer

Class MBConv

java.lang.Object

smile.deep.layer.LayerBlock

smile.vision.layer.MBConv

All Implemented Interfaces:

Function<Tensor,Tensor>, Layer

public class MBConv
extends LayerBlock

Mobile inverted bottleneck convolution.

MBConv = expansion-conv1x1 + depthwise-conv3x3 + SENet + conv1x1 + add

Constructor Summary

Constructors

Constructor	Description
MBConv(MBConvConfig config, double stochasticDepthProb, IntFunction<Layer> normLayer)	Constructor.

Method Summary

Modifier and Type	Method	Description
Tensor	forward(Tensor input)	Forward propagation (or forward pass) through the layer.

Methods inherited from class smile.deep.layer.LayerBlock

add, add, asTorch, toString

Methods inherited from class java.lang.Object

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

Methods inherited from interface java.util.function.Function

andThen, compose

Methods inherited from interface smile.deep.layer.Layer

apply, isTraining

Constructor Details

MBConv

public MBConv(MBConvConfig config,
 double stochasticDepthProb,
 IntFunction<Layer> normLayer)

Constructor.

Parameters:

config - block configuration.

stochasticDepthProb - the probability of the input to be zeroed in stochastic depth layer.

normLayer - the functor to create the normalization layer.

Method Details

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.