MPSCNNSubtractGradient(3) MetalPerformanceShaders.framework MPSCNNSubtractGradient(3)
NAME
MPSCNNSubtractGradient
SYNOPSIS
#import <MPSCNNMath.h>
Inherits MPSCNNArithmeticGradient.
Instance Methods
(nonnull instancetype) - initWithDevice:
Additional Inherited Members
Detailed Description
This depends on Metal.framework. Specifies the subtraction 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 subtract gradient operation for the primary source image is a copy operation on the input gradient
image (for x - y, d/dx(x - y) = 1). This copy operation can be optimized away by the graph interface.
For the secondary source image, the result is a negation of the gradient image from the previous layer (for x - y, d/dy(x - y) = -1).
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 subtraction gradient operator.
Parameters:
device The device the filter will run on.
Returns:
A valid MPSCNNSubtractGradient 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 MPSCNNSubtractGradient(3)
