| MPSNNGradientFilterNode(3) | MetalPerformanceShaders.framework | MPSNNGradientFilterNode(3) |
MPSNNGradientFilterNode
#import <MPSNNGraphNodes.h>
Inherits MPSNNFilterNode.
Inherited by MPSCNNBatchNormalizationGradientNode, MPSCNNConvolutionGradientNode, MPSCNNCrossChannelNormalizationGradientNode, MPSCNNDropoutGradientNode, MPSCNNInstanceNormalizationGradientNode, MPSCNNLocalContrastNormalizationGradientNode, MPSCNNLogSoftMaxGradientNode, MPSCNNNeuronGradientNode, MPSCNNPoolingGradientNode, MPSCNNSoftMaxGradientNode, MPSCNNSpatialNormalizationGradientNode, MPSCNNUpsamplingBilinearGradientNode, MPSCNNUpsamplingNearestGradientNode, MPSNNArithmeticGradientNode, and MPSNNConcatenationGradientNode.
(MPSNNGradientFilterNode *__nonnull) -
gradientFilterWithSources:
(NSArray< MPSNNGradientFilterNode * > *__nonnull) -
gradientFiltersWithSources:
(MPSNNGradientFilterNode *__nonnull) - gradientFilterWithSource:
(NSArray< MPSNNGradientFilterNode * > *__nonnull) -
gradientFiltersWithSource:
For each MPSNNFilterNode, there is a corresponding MPSNNGradientFilterNode used for training that back propagates image gradients to refine the various parameters in each node. Generally, it takes as input a gradient corresponding to the result image from the MPSNNFilterNode and returns a gradient image corresponding to the source image of the MPSNNFilterNode. In addition, there is generally a MPSNNState produced by the MPSNNFilterNode that is consumed by the MPSNNGradientNode and the MPSNNGradientNode generally needs to look at the MPSNNFilterNode source image.
If you have a simple method to traverse your inference graph backwards, then -[MPSNNFilterNode gradientFilterWithSource:] is a simple way to construct these.
Return multiple gradient versions of the filter MPSNNFilters that consume multiple inputs generally result in multiple conjugate filters for the gradient computation at the end of training. For example, a single concatenation operation that concatenates multple images will result in an array of slice operators that carve out subsections of the input gradient image.
Reimplemented from MPSNNFilterNode.
Return multiple gradient versions of the filter MPSNNFilters that consume multiple inputs generally result in multiple conjugate filters for the gradient computation at the end of training. For example, a single concatenation operation that concatenates multple images will result in an array of slice operators that carve out subsections of the input gradient image.
Reimplemented from MPSNNFilterNode.
Return the gradient (backwards) version of this filter. The backwards training version of the filter will be returned. The non-gradient image and state arguments for the filter are automatically obtained from the target.
Parameters:
Reimplemented from MPSNNFilterNode.
Return the gradient (backwards) version of this filter. The backwards training version of the filter will be returned. The non-gradient image and state arguments for the filter are automatically obtained from the target.
Parameters:
Reimplemented from MPSNNFilterNode.
Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code.
| Mon Jul 9 2018 | Version MetalPerformanceShaders-119.3 |