Package apple.metalperformanceshaders

Class MPSMatrixFullyConnectedGradient

  • All Implemented Interfaces:
    NSCoding, NSCopying, NSSecureCoding, NSObject
    public class MPSMatrixFullyConnectedGradient
extends MPSMatrixBinaryKernel
    MPSMatrixFullyConnectedGradient [@dependency] This depends on Metal.framework. Computes the gradient of the fully connected layer with respect to either the weights and bias terms or the input feature vectors. An MPSMatrixFullyConnectedGradient kernel may be used to compute the gradients corresponding to a MPSMatrixFullyConnected kernel. The properties, input, and weight data must match those values used in the forward computation. This kernel does not compute the gradient of any non-identity activation function which may have been applied in the forward kernel. Such a kernel must be expressed using both MPSMatrixFullyConnected and MPSMatrixNeuron if a gradient is to be computed.

    • Constructor Detail

      • MPSMatrixFullyConnectedGradient

        protected MPSMatrixFullyConnectedGradient​(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)

      • alpha

        public double alpha()
        [@property] alpha Scale factor to apply to the product. This value should be equal to the corresponding value in the forward fully connected kernel.

      • 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()

      • copyWithZoneDevice

        public java.lang.Object copyWithZoneDevice​(org.moe.natj.general.ptr.VoidPtr zone,
                                           MTLDevice device)
        Make a copy of this kernel for a new device - @see MPSKernel
        Overrides:
        copyWithZoneDevice in class MPSKernel
        Parameters:
        zone - The NSZone in which to allocate the object
        device - The device for the new MPSKernel. If nil, then use self.device.
        Returns:
        A pointer to a copy of this MPSKernel. This will fail, returning nil if the device is not supported. Devices must be MTLFeatureSet_iOS_GPUFamily2_v1 or later.

      • debugDescription_static

        public static java.lang.String debugDescription_static()

      • description_static

        public static java.lang.String description_static()

      • encodeGradientForDataToCommandBufferGradientMatrixWeightMatrixResultGradientForDataMatrix

        public void encodeGradientForDataToCommandBufferGradientMatrixWeightMatrixResultGradientForDataMatrix​(MTLCommandBuffer commandBuffer,
                                                                                                      MPSMatrix gradientMatrix,
                                                                                                      MPSMatrix weightMatrix,
                                                                                                      MPSMatrix resultGradientForDataMatrix)
        Encode a MPSMatrixFullyConnectedGradient object to a command buffer and produce the gradient of the loss function with respect to the input data. This operation computes the resulting gradient of the loss function with respect to the forward kernel's input data. weightMatrix should contain the same values used to compute the result of the forward kernel.
        Parameters:
        commandBuffer - A valid MTLCommandBuffer to receive the encoded kernel.
        gradientMatrix - A valid MPSMatrix object which specifies the input gradient.
        weightMatrix - A valid MPSMatrix object which specifies the weight array.
        resultGradientForDataMatrix - A valid MPSMatrix object which specifies the result gradient.

      • encodeGradientForWeightsAndBiasToCommandBufferGradientMatrixInputMatrixResultGradientForWeightMatrixResultGradientForBiasVector

        public void encodeGradientForWeightsAndBiasToCommandBufferGradientMatrixInputMatrixResultGradientForWeightMatrixResultGradientForBiasVector​(MTLCommandBuffer commandBuffer,
                                                                                                                                            MPSMatrix gradientMatrix,
                                                                                                                                            MPSMatrix inputMatrix,
                                                                                                                                            MPSMatrix resultGradientForWeightMatrix,
                                                                                                                                            MPSVector resultGradientForBiasVector)
        Encode a MPSMatrixFullyConnectedGradient object to a command buffer and produce the gradient of the loss function with respect to the weight matrix and bias vector. This operation computes the resulting gradient of the loss function with respect to the forward kernel's weight data. inputMatrix should contain the same values used to compute the result of the forward kernel.
        Parameters:
        commandBuffer - A valid MTLCommandBuffer to receive the encoded kernel.
        gradientMatrix - A valid MPSMatrix object which specifies the input gradient.
        inputMatrix - A valid MPSMatrix object which specifies the input array.
        resultGradientForWeightMatrix - A valid MPSMatrix object which specifies the resulting gradients with respect to the weights.
        resultGradientForBiasVector - A valid MPSVector object which specifies the resulting gradients with respect to the bias terms. If NULL these values will not be returned.

      • hash_static

        public static long hash_static()

      • initWithCoderDevice

        public MPSMatrixFullyConnectedGradient initWithCoderDevice​(NSCoder aDecoder,
                                                           java.lang.Object device)
        NSSecureCoding compatability See @ref MPSKernel#initWithCoder.
        Overrides:
        initWithCoderDevice in class MPSMatrixBinaryKernel
        Parameters:
        aDecoder - The NSCoder subclass with your serialized MPSMatrixFullyConnectedGradient
        device - The MTLDevice on which to make the MPSMatrixFullyConnectedGradient object.
        Returns:
        A new MPSMatrixFullyConnected object, or nil if failure.

      • initWithDevice

        public MPSMatrixFullyConnectedGradient initWithDevice​(java.lang.Object device)
        Description copied from class: MPSKernel
        Standard init with default properties per filter type
        Overrides:
        initWithDevice in class MPSMatrixBinaryKernel
        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)

      • 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)

      • setAlpha

        public void setAlpha​(double value)
        [@property] alpha Scale factor to apply to the product. This value should be equal to the corresponding value in the forward fully connected kernel.

      • setSourceInputFeatureChannels

        public void setSourceInputFeatureChannels​(long value)
        [@property] sourceInputFeatureChannels The number of feature channels in the input to the forward fully connected layer. This is equivalent to the number of columns in the input matrix. This value should be equal to the corresponding value in the forward fully connected kernel.

      • setSourceNumberOfFeatureVectors

        public void setSourceNumberOfFeatureVectors​(long value)
        [@property] sourceNumberOfFeatureVectors The number of input vectors which make up the input array. This is equivalent to the number of rows in both the input matrix and the source gradient matrix. This value should be equal to the corresponding value in the forward fully connected kernel.

      • setSourceOutputFeatureChannels

        public void setSourceOutputFeatureChannels​(long value)
        [@property] sourceOutputFeatureChannels The number of feature channels in the output of the forward fully connected layer. This is equivalent to the number of columns in both the weight matrix and the source gradient matrix. This value should be equal to the corresponding value in the forward fully connected kernel.

      • setVersion_static

        public static void setVersion_static​(long aVersion)

      • sourceInputFeatureChannels

        public long sourceInputFeatureChannels()
        [@property] sourceInputFeatureChannels The number of feature channels in the input to the forward fully connected layer. This is equivalent to the number of columns in the input matrix. This value should be equal to the corresponding value in the forward fully connected kernel.

      • sourceNumberOfFeatureVectors

        public long sourceNumberOfFeatureVectors()
        [@property] sourceNumberOfFeatureVectors The number of input vectors which make up the input array. This is equivalent to the number of rows in both the input matrix and the source gradient matrix. This value should be equal to the corresponding value in the forward fully connected kernel.

      • sourceOutputFeatureChannels

        public long sourceOutputFeatureChannels()
        [@property] sourceOutputFeatureChannels The number of feature channels in the output of the forward fully connected layer. This is equivalent to the number of columns in both the weight matrix and the source gradient matrix. This value should be equal to the corresponding value in the forward fully connected kernel.

      • 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 MPSMatrixBinaryKernel

      • version_static

        public static long version_static()