mpscnnmultiplygradient(3) [mojave man page]
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)
Check Out this Related Man Page
MPSCNNFullyConnectedGradient(3) MetalPerformanceShaders.framework MPSCNNFullyConnectedGradient(3) NAME
MPSCNNFullyConnectedGradient SYNOPSIS
#import <MPSCNNConvolution.h> Inherits MPSCNNConvolutionGradient. Instance Methods (nonnull instancetype) - initWithDevice:weights: (nullable instancetype) - initWithCoder:device: (nonnull instancetype) - initWithDevice: Additional Inherited Members Detailed Description This depends on Metal.framework Compute the gradient for fully connected layer. Method Documentation - (nullable instancetype) initWithCoder: (NSCoder *__nonnull) aDecoder(nonnull id< MTLDevice >) device NSSecureCoding compatability While the standard NSSecureCoding/NSCoding method -initWithCoder: should work, since the file can't know which device your data is allocated on, we have to guess and may guess incorrectly. To avoid that problem, use initWithCoder:device instead. Parameters: aDecoder The NSCoder subclass with your serialized MPSKernel device The MTLDevice on which to make the MPSKernel Returns: A new MPSKernel object, or nil if failure. Reimplemented from MPSCNNConvolutionGradient. - (nonnull instancetype) initWithDevice: (nonnull id< MTLDevice >) device Standard init with default properties per filter type Parameters: device The device that the filter will be used on. May not be NULL. Returns: A pointer to the newly initialized object. This will fail, returning nil if the device is not supported. Devices must be MTLFeatureSet_iOS_GPUFamily2_v1 or later. Reimplemented from MPSCNNConvolutionGradient. - (nonnull instancetype) initWithDevice: (nonnull id< MTLDevice >) device(nonnull id< MPSCNNConvolutionDataSource >) weights Initializes a convolution gradient (with respect to weights and bias) object. Parameters: device The MTLDevice on which this MPSCNNConvolutionGradient filter will be used weights A pointer to a object that conforms to the MPSCNNConvolutionDataSource protocol. Note that same data source as provided to forward convolution should be used. Returns: A valid MPSCNNConvolutionGradient object or nil, if failure. Reimplemented from MPSCNNConvolutionGradient. Author Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code. Version MetalPerformanceShaders-100 Thu Feb 8 2018 MPSCNNFullyConnectedGradient(3)