Package apple.metalperformanceshaders

Class MPSCNNLossDescriptor

  • All Implemented Interfaces:
    NSCopying, NSObject
    public class MPSCNNLossDescriptor
extends NSObject
implements NSCopying
    MPSCNNLossDescriptor [@dependency] This depends on Metal.framework. The MPSCNNLossDescriptor specifies a loss filter descriptor. The same descriptor can be used to initialize both the MPSCNNLoss and the MPSNNLossGradient filters.

    • Constructor Detail

      • MPSCNNLossDescriptor

        protected MPSCNNLossDescriptor​(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()

      • cnnLossDescriptorWithTypeReductionType

        public static MPSCNNLossDescriptor cnnLossDescriptorWithTypeReductionType​(int lossType,
                                                                          int reductionType)
        Make a descriptor for a MPSCNNLoss or MPSNNLossGradient object.
        Parameters:
        lossType - The type of a loss filter.
        reductionType - The type of a reduction operation to apply. This argument is ignored in the MPSNNLossGradient filter.
        Returns:
        A valid MPSCNNLossDescriptor object or nil, if failure.

      • copyWithZone

        public java.lang.Object copyWithZone​(org.moe.natj.general.ptr.VoidPtr zone)
        Specified by:
        copyWithZone in interface NSCopying

      • debugDescription_static

        public static java.lang.String debugDescription_static()

      • delta

        public float delta()
        [@property] delta The delta parameter. The default value is 1.0f. This parameter is valid only for the loss functions of the following type(s): MPSCNNLossTypeHuber. Given predictions and labels (ground truth), it is applied in the following way: if (|predictions - labels| <= delta, loss = 0.5f * predictions^2 if (|predictions - labels| > delta, loss = 0.5 * delta^2 + delta * (|predictions - labels| - delta)

      • description_static

        public static java.lang.String description_static()

      • epsilon

        public float epsilon()
        [@property] epsilon The epsilon parameter. The default value is 1e-7. This parameter is valid only for the loss functions of the following type(s): MPSCNNLossTypeLog. Given predictions and labels (ground truth), it is applied in the following way: -(labels * log(predictions + epsilon)) - ((1 - labels) * log(1 - predictions + epsilon))

      • hash_static

        public static long hash_static()

      • 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)

      • labelSmoothing

        public float labelSmoothing()
        [@property] labelSmoothing The label smoothing parameter. The default value is 0.0f. This parameter is valid only for the loss functions of the following type(s): MPSCNNLossFunctionTypeSoftmaxCrossEntropy, MPSCNNLossFunctionTypeSigmoidCrossEntropy. MPSCNNLossFunctionTypeSoftmaxCrossEntropy: given labels (ground truth), it is applied in the following way: labels = labelSmoothing > 0 ? labels * (1 - labelSmoothing) + labelSmoothing / numberOfClasses : labels MPSCNNLossFunctionTypeSigmoidCrossEntropy: given labels (ground truth), it is applied in the following way: labels = labelSmoothing > 0 ? labels * (1 - labelSmoothing) + 0.5 * labelSmoothing : labels

      • lossType

        public int lossType()
        [@property] lossType The type of a loss filter. This parameter specifies the type of a loss filter.

      • new_objc

        public static java.lang.Object new_objc()

      • numberOfClasses

        public long numberOfClasses()
        [@property] numberOfClasses The number of classes parameter. The default value is 1. This parameter is valid only for the loss functions of the following type(s): MPSCNNLossFunctionTypeSoftmaxCrossEntropy. Given labels (ground truth), it is applied in the following way: labels = labelSmoothing > 0 ? labels * (1 - labelSmoothing) + labelSmoothing / numberOfClasses : labels

      • reductionType

        public int reductionType()
        [@property] reductionType The type of a reduction operation performed in the loss filter. This parameter specifies the type of a reduction operation performed in the loss filter.

      • resolveClassMethod

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

      • resolveInstanceMethod

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

      • setDelta

        public void setDelta​(float value)
        [@property] delta The delta parameter. The default value is 1.0f. This parameter is valid only for the loss functions of the following type(s): MPSCNNLossTypeHuber. Given predictions and labels (ground truth), it is applied in the following way: if (|predictions - labels| <= delta, loss = 0.5f * predictions^2 if (|predictions - labels| > delta, loss = 0.5 * delta^2 + delta * (|predictions - labels| - delta)

      • setEpsilon

        public void setEpsilon​(float value)
        [@property] epsilon The epsilon parameter. The default value is 1e-7. This parameter is valid only for the loss functions of the following type(s): MPSCNNLossTypeLog. Given predictions and labels (ground truth), it is applied in the following way: -(labels * log(predictions + epsilon)) - ((1 - labels) * log(1 - predictions + epsilon))

      • setLabelSmoothing

        public void setLabelSmoothing​(float value)
        [@property] labelSmoothing The label smoothing parameter. The default value is 0.0f. This parameter is valid only for the loss functions of the following type(s): MPSCNNLossFunctionTypeSoftmaxCrossEntropy, MPSCNNLossFunctionTypeSigmoidCrossEntropy. MPSCNNLossFunctionTypeSoftmaxCrossEntropy: given labels (ground truth), it is applied in the following way: labels = labelSmoothing > 0 ? labels * (1 - labelSmoothing) + labelSmoothing / numberOfClasses : labels MPSCNNLossFunctionTypeSigmoidCrossEntropy: given labels (ground truth), it is applied in the following way: labels = labelSmoothing > 0 ? labels * (1 - labelSmoothing) + 0.5 * labelSmoothing : labels

      • setLossType

        public void setLossType​(int value)
        [@property] lossType The type of a loss filter. This parameter specifies the type of a loss filter.

      • setNumberOfClasses

        public void setNumberOfClasses​(long value)
        [@property] numberOfClasses The number of classes parameter. The default value is 1. This parameter is valid only for the loss functions of the following type(s): MPSCNNLossFunctionTypeSoftmaxCrossEntropy. Given labels (ground truth), it is applied in the following way: labels = labelSmoothing > 0 ? labels * (1 - labelSmoothing) + labelSmoothing / numberOfClasses : labels

      • setReductionType

        public void setReductionType​(int value)
        [@property] reductionType The type of a reduction operation performed in the loss filter. This parameter specifies the type of a reduction operation performed in the loss filter.

      • setVersion_static

        public static void setVersion_static​(long aVersion)

      • setWeight

        public void setWeight​(float value)
        [@property] weight The scale factor to apply to each element of a result. Each element of a result is multiplied by the weight value. The default value is 1.0f.

      • superclass_static

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

      • version_static

        public static long version_static()

      • weight

        public float weight()
        [@property] weight The scale factor to apply to each element of a result. Each element of a result is multiplied by the weight value. The default value is 1.0f.

      • reduceAcrossBatch

        public boolean reduceAcrossBatch()
        [@property] reduceAcrossBatch If set to YES then the reduction operation is applied also across the batch-index dimension, ie. the loss value is summed over images in the batch and the result of the reduction is written on the first loss image in the batch while the other loss images will be set to zero. If set to NO, then no reductions are performed across the batch dimension and each image in the batch will contain the loss value associated with that one particular image. NOTE: If reductionType == MPSCNNReductionTypeNone, then this flag has no effect on results, that is no reductions are done in this case. NOTE: If reduceAcrossBatch is set to YES and reductionType == MPSCNNReductionTypeMean then the final forward loss value is computed by first summing over the components and then by dividing the result with: number of feature channels * width * height * number of images in the batch. The default value is NO.

      • setReduceAcrossBatch

        public void setReduceAcrossBatch​(boolean value)
        [@property] reduceAcrossBatch If set to YES then the reduction operation is applied also across the batch-index dimension, ie. the loss value is summed over images in the batch and the result of the reduction is written on the first loss image in the batch while the other loss images will be set to zero. If set to NO, then no reductions are performed across the batch dimension and each image in the batch will contain the loss value associated with that one particular image. NOTE: If reductionType == MPSCNNReductionTypeNone, then this flag has no effect on results, that is no reductions are done in this case. NOTE: If reduceAcrossBatch is set to YES and reductionType == MPSCNNReductionTypeMean then the final forward loss value is computed by first summing over the components and then by dividing the result with: number of feature channels * width * height * number of images in the batch. The default value is NO.