Package apple.metalperformanceshaders

Class MPSCNNGradientKernel

  • All Implemented Interfaces:
    NSCoding, NSCopying, NSSecureCoding, NSObject
    Direct Known Subclasses:
    MPSCNNArithmeticGradient, MPSCNNBatchNormalizationGradient, MPSCNNBatchNormalizationStatisticsGradient, MPSCNNConvolutionGradient, MPSCNNConvolutionTransposeGradient, MPSCNNCrossChannelNormalizationGradient, MPSCNNDropoutGradient, MPSCNNGroupNormalizationGradient, MPSCNNInstanceNormalizationGradient, MPSCNNLocalContrastNormalizationGradient, MPSCNNLogSoftMaxGradient, MPSCNNNeuronGradient, MPSCNNPoolingGradient, MPSCNNSoftMaxGradient, MPSCNNSpatialNormalizationGradient, MPSCNNUpsamplingGradient, MPSNNGramMatrixCalculationGradient, MPSNNPadGradient, MPSNNReshapeGradient
    public class MPSCNNGradientKernel
extends MPSCNNBinaryKernel
    MPSCNNGradientKernel Gradient kernels are the backwards pass of a MPSCNNKernel used during training to calculate gradient back propagation. These take as arguments the gradient result from the next filter and the source image for the forward version of the filter. There is also a MPSNNGradientState passed from MPSCNNKernel to MPSCNNGradientKernel that contains information about the MPSCNNKernel parameters at the time it encoded and possibly also additional MTLResources to enable it to do its job. [@code] Training graph (partial): ---> input image ---------> MPSCNNKernel ------> resultImage ------>-->-->-->. \ | | '------. MPSNNGradientState loss estimation \ | | V V V <--- result gradient <- MPSCNNGradientKernel <--- input gradient <--<--<--<---' In general operation, starting with the input image, the sequence of events is: 1a) Invoke padding policy to find result size for MPSCNNKernel. This also configures some MPSCNNKernel parameters such as offset. 1b) Use the MPSImageDescriptor from 1a to make resultImage. 1c) Call MPSCNNKernel -encode... 2) stages 1a-c are repeated for other forward passes in the inference portion of the graph 3) We estimate the loss resulting from the whole inference computation so far (see MPSCNNLoss.h> 4) stages 5a-c are repeated for corresponding backward gradient passes in the graph 5a) Invoke padding policy on the MPSCNNGradientKernel shown above. This sets the MPSCNNGradientKernel parameters to correspond with those in the forward pass 5b) The result gradient for the MPSCNNGradientKernel is created from the MPSImageDescriptor from 5a 5c) Call MPSCNNGradientKernel -encode with the input image, input gradient, result gradient and MPSNNGradientState 6) pass the result gradient on to leftward gradient passes. [@endcode] For MPSCNNKernels that are trained, there may be other accompanying training kernels that need to be called in addition to the gradient kernel to update convolution weights or batch normalization parameters, for example. Steps 1a-c and 5a-c can be combined in a single -encode call. These return the result image or gradient out the left hand side. For purposes of inheritance the gradient image is the MPSCNNBinaryKernel primary image and the source image is the MPSCNNBinaryKernel secondary image. Various secondary properties such as kernel size are copies of the forward inference pass parameters of similar name are set automatically when -[MPSCNNGradientKernel destinationImageDescriptorForSourceImages:sourceStates:] is called.

    • Constructor Detail

      • MPSCNNGradientKernel

        protected MPSCNNGradientKernel​(org.moe.natj.general.Pointer peer)

    • Method Detail

      • accessInstanceVariablesDirectly

        public static boolean accessInstanceVariablesDirectly()

      • allocWithZone

        public static java.lang.Object allocWithZone​(org.moe.natj.general.ptr.VoidPtr zone)

      • automaticallyNotifiesObserversForKey

        public static boolean automaticallyNotifiesObserversForKey​(java.lang.String key)

      • cancelPreviousPerformRequestsWithTarget

        public static void cancelPreviousPerformRequestsWithTarget​(java.lang.Object aTarget)

      • cancelPreviousPerformRequestsWithTargetSelectorObject

        public static void cancelPreviousPerformRequestsWithTargetSelectorObject​(java.lang.Object aTarget,
                                                                         org.moe.natj.objc.SEL aSelector,
                                                                         java.lang.Object anArgument)

      • classFallbacksForKeyedArchiver

        public static NSArray<java.lang.String> classFallbacksForKeyedArchiver()

      • classForKeyedUnarchiver

        public static org.moe.natj.objc.Class classForKeyedUnarchiver()

      • debugDescription_static

        public static java.lang.String debugDescription_static()

      • description_static

        public static java.lang.String description_static()

      • encodeToCommandBufferSourceGradientSourceImageGradientState

        public MPSImage encodeToCommandBufferSourceGradientSourceImageGradientState​(MTLCommandBuffer commandBuffer,
                                                                            MPSImage sourceGradient,
                                                                            MPSImage sourceImage,
                                                                            MPSState gradientState)
        Encode a gradient filter and return a gradient During training, gradient filters are used to calculate the gradient associated with the loss for each feature channel in the forward pass source image. For those nodes that are trainable, these are then used to refine the value used in the trainable parameter. They consume a source gradient image which contains the gradients corresponding with the forward pass destination image, and calculate the gradients corresponding to the forward pass source image. A gradient filter consumes a MPSNNGradientState object which captured various forward pass properties such as offset and edgeMode at the time the forward pass was encoded. These are transferred to the MPSCNNBinaryKernel secondary image properties automatically when this method creates its destination image.
        Parameters:
        commandBuffer - The MTLCommandBuffer on which to encode
        sourceGradient - The gradient image from the "next" filter in the graph (in the inference direction)
        sourceImage - The image used as source image by the forward inference pass
        gradientState - The MPSNNGradientState or MPSNNBinaryGradientState subclass produced by the forward inference pass
        Returns:
        The result gradient from the gradient filter

      • encodeToCommandBufferSourceGradientSourceImageGradientStateDestinationGradient

        public void encodeToCommandBufferSourceGradientSourceImageGradientStateDestinationGradient​(MTLCommandBuffer commandBuffer,
                                                                                           MPSImage sourceGradient,
                                                                                           MPSImage sourceImage,
                                                                                           MPSState gradientState,
                                                                                           MPSImage destinationGradient)
        Encode a gradient filter and return a gradient During training, gradient filters are used to calculate the gradient associated with the loss for each feature channel in the forward pass source image. For those nodes that are trainable, these are then used to refine the value used in the trainable parameter. They consume a source gradient image which contains the gradients corresponding with the forward pass destination image, and calculate the gradients corresponding to the forward pass source image. A gradient filter consumes a MPSNNGradientState object which captured various forward pass properties such as offset and edgeMode at the time the forward pass was encoded. These are transferred to the MPSCNNBinaryKernel secondary image properties automatically when you use -[MPSCNNGradientKernel destinationImageDescriptorForSourceImages:sourceStates:]. If you do not call this method, then you are responsible for configuring all of the primary and secondary image properties in MPSCNNBinaryKernel. Please see class description for expected ordering of operations.
        Parameters:
        commandBuffer - The MTLCommandBuffer on which to encode
        sourceGradient - The gradient image from the "next" filter in the graph
        sourceImage - The image used as source image from the forward pass
        gradientState - The MPSNNGradientState and MPSNNBinaryGradientState subclass produced by the forward pass
        destinationGradient - The MPSImage into which to write the filter result

      • hash_static

        public static long hash_static()

      • initWithCoderDevice

        public MPSCNNGradientKernel initWithCoderDevice​(NSCoder aDecoder,
                                                java.lang.Object 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.
        Overrides:
        initWithCoderDevice in class MPSCNNBinaryKernel
        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.

      • initWithDevice

        public MPSCNNGradientKernel initWithDevice​(java.lang.Object device)
        Standard init with default properties per filter type
        Overrides:
        initWithDevice in class MPSCNNBinaryKernel
        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.

      • instanceMethodSignatureForSelector

        public static NSMethodSignature instanceMethodSignatureForSelector​(org.moe.natj.objc.SEL aSelector)

      • instancesRespondToSelector

        public static boolean instancesRespondToSelector​(org.moe.natj.objc.SEL aSelector)

      • isSubclassOfClass

        public static boolean isSubclassOfClass​(org.moe.natj.objc.Class aClass)

      • kernelOffsetX

        public long kernelOffsetX()
        [@property] kernelOffsetX Offset in the kernel reference frame to position the kernel in the X dimension In some cases, the input gradient must be upsampled with zero insertion to account for things like strides in the forward MPSCNNKernel pass. As such, the offset, which describes a X,Y offset in the source coordinate space is insufficient to fully describe the offset applied to a kernel. The kernel offset is the offset after upsampling. Both the source offset and kernel offset are additive: effective offset = source offset * stride + kernel offset. The offset is applied to the (upsampled) source gradient

      • kernelOffsetY

        public long kernelOffsetY()
        [@property] kernelOffsetY Offset in the kernel reference frame to position the kernel in the Y dimension In some cases, the input gradient must be upsampled with zero insertion to account for things like strides in the forward MPSCNNKernel pass. As such, the offset, which describes a X,Y offset in the source coordinate space is insufficient to fully describe the offset applied to a kernel. The kernel offset is the offset after upsampling. Both the source offset and kernel offset are additive: effective offset = source offset * stride + kernel offset. The offset is applied to the (upsampled) source gradient

      • keyPathsForValuesAffectingValueForKey

        public static NSSet<java.lang.String> keyPathsForValuesAffectingValueForKey​(java.lang.String key)

      • new_objc

        public static java.lang.Object new_objc()

      • resolveClassMethod

        public static boolean resolveClassMethod​(org.moe.natj.objc.SEL sel)

      • resolveInstanceMethod

        public static boolean resolveInstanceMethod​(org.moe.natj.objc.SEL sel)

      • setKernelOffsetX

        public void setKernelOffsetX​(long value)
        [@property] kernelOffsetX Offset in the kernel reference frame to position the kernel in the X dimension In some cases, the input gradient must be upsampled with zero insertion to account for things like strides in the forward MPSCNNKernel pass. As such, the offset, which describes a X,Y offset in the source coordinate space is insufficient to fully describe the offset applied to a kernel. The kernel offset is the offset after upsampling. Both the source offset and kernel offset are additive: effective offset = source offset * stride + kernel offset. The offset is applied to the (upsampled) source gradient

      • setKernelOffsetY

        public void setKernelOffsetY​(long value)
        [@property] kernelOffsetY Offset in the kernel reference frame to position the kernel in the Y dimension In some cases, the input gradient must be upsampled with zero insertion to account for things like strides in the forward MPSCNNKernel pass. As such, the offset, which describes a X,Y offset in the source coordinate space is insufficient to fully describe the offset applied to a kernel. The kernel offset is the offset after upsampling. Both the source offset and kernel offset are additive: effective offset = source offset * stride + kernel offset. The offset is applied to the (upsampled) source gradient

      • setVersion_static

        public static void setVersion_static​(long aVersion)

      • superclass_static

        public static org.moe.natj.objc.Class superclass_static()

      • supportsSecureCoding

        public static boolean supportsSecureCoding()

      • _supportsSecureCoding

        public boolean _supportsSecureCoding()
        Description copied from interface: NSSecureCoding
        This property must return YES on all classes that allow secure coding. Subclasses of classes that adopt NSSecureCoding and override initWithCoder: must also override this method and return YES. The Secure Coding Guide should be consulted when writing methods that decode data.
        Specified by:
        _supportsSecureCoding in interface NSSecureCoding
        Overrides:
        _supportsSecureCoding in class MPSCNNBinaryKernel

      • version_static

        public static long version_static()