MPSCNNMultiplyGradient(3) MetalPerformanceShaders.framework MPSCNNMultiplyGradient(3)
NAME
MPSCNNMultiplyGradient
SYNOPSIS
#import <MPSCNNMath.h>
Inherits MPSCNNArithmeticGradient.
Instance Methods
(nonnull instancetype) - initWithDevice:
Additional Inherited Members
Detailed Description
This depends on Metal.framework. Specifies the multiplication gradient operator. This arithmetic gradient filter requires the following
inputs: gradient image from the previous layer (going backwards) and either the primary or the secondary source image from the forward
pass. You will need a separate filter for the primary and secondary source images.
Without broadcasting, the arithmetic multiply gradient operation is an element-wise multiplication operation between the gradient image
from the previous layer (going backwards) and:
o The secondary source image from the forward pass for the primary source filter (for x * y, d/dx(x * y) = y).
o The primary source image from the forward pass for the secondary source filter (for x * y, d/dy(x * y) = x).
Setting the broadcasting parameters results in a reduction operation (sum) across all of the applicable broadcasting dimensions (rows,
columns, feature channels, or any combination thereof) to produce the destination image of the size that matches the primary/secondary
input images used in the forward pass.
Method Documentation
- (nonnull instancetype) initWithDevice: (nonnull id< MTLDevice >) device
Initialize the multiplication gradient operator.
Parameters:
device The device the filter will run on.
Returns:
A valid MPSCNNMultiplyGradient object or nil, if failure.
Reimplemented from MPSCNNArithmeticGradient.
Author
Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code.
Version MetalPerformanceShaders-100 Thu Feb 8 2018 MPSCNNMultiplyGradient(3)