Class StochasticDepth

java.lang.Object

smile.vision.layer.StochasticDepth

All Implemented Interfaces:

Function<Tensor,Tensor>, Layer

public class StochasticDepth
extends Object
implements Layer

Stochastic Depth for randomly dropping residual branches of residual architectures, from "Deep Networks with Stochastic Depth".

Constructor Summary

Constructors

Constructor	Description
StochasticDepth(double p, String mode)	Constructor.

Method Summary

Modifier and Type	Method	Description
Tensor	forward(Tensor input)	Forward propagation (or forward pass) through the layer.
MemorySegment	module()	Returns the native ST_Module handle for this layer.

Methods inherited from class Object

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

Methods inherited from interface Function

andThen, compose

Methods inherited from interface Layer

apply, name, to, to

Constructor Details

StochasticDepth

public StochasticDepth(double p,
 String mode)

Constructor.

Parameters:

p - the drop probability. Must be in [0, 1].

mode - "batch" or "row". "batch" randomly zeroes the entire input, "row" zeroes randomly selected rows from the batch.

Method Details

module

public MemorySegment module()

Description copied from interface: Layer

Returns the native ST_Module handle for this layer.

Specified by:

module in interface Layer

Returns:

the native ST_Module handle.

forward

public Tensor forward(Tensor input)

Description copied from interface: Layer

Forward propagation (or forward pass) through the layer.

Specified by:

forward in interface Layer

Parameters:

input - the input tensor.

Returns:

the output tensor.