Class MPSCNNDropout

  • All Implemented Interfaces:
    NSCoding, NSCopying, NSSecureCoding, NSObject

    public class MPSCNNDropout
    extends MPSCNNKernel
    MPSCNNDropout [@dependency] This depends on Metal.framework Dropout is a regularization technique used to prevent neural networks from overfitting during training. With probability keepProbability, this filter outputs the input element scaled by 1 / keepProbability. Otherwise, it outputs 0. Each input element is kept or dropped independently. The scaling is performed to keep the energy of the output unchanged.
    • Constructor Detail

      • MPSCNNDropout

        protected MPSCNNDropout​(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()
      • hash_static

        public static long hash_static()
      • initWithCoderDevice

        public MPSCNNDropout initWithCoderDevice​(NSCoder aDecoder,
                                                 java.lang.Object device)
        support
        Overrides:
        initWithCoderDevice in class MPSCNNKernel
        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 MPSCNNDropout initWithDevice​(java.lang.Object device)
        Description copied from class: MPSCNNKernel
        Standard init with default properties per filter type
        Overrides:
        initWithDevice in class MPSCNNKernel
        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.
      • initWithDeviceKeepProbabilitySeedMaskStrideInPixels

        public MPSCNNDropout initWithDeviceKeepProbabilitySeedMaskStrideInPixels​(MTLDevice device,
                                                                                 float keepProbability,
                                                                                 long seed,
                                                                                 MTLSize maskStrideInPixels)
        Standard init with default properties per filter type.
        Parameters:
        device - The device that the filter will be used on.
        keepProbability - The probability that each element in the input is kept. The valid range is (0.0f, 1.0f).
        seed - The seed used to generate random numbers.
        maskStrideInPixels - The mask stride in the x, y, and z dimensions, which allows for the broadcasting of mask data. The only valid values are 0 and 1 for each dimension. For no broadcasting, set the values for each dimension to 1. For broadcasting, set desired values to 0.
        Returns:
        A valid MPSCNNDropout object or nil, if failure.
      • 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)
      • keepProbability

        public float keepProbability()
        [@property] keepProbability The probability that each element in the input is kept. The valid range is (0.0f, 1.0f).
      • keyPathsForValuesAffectingValueForKey

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

        public MTLSize maskStrideInPixels()
        [@property] maskStrideInPixels The mask stride in the x, y, and x dimensions, which allows for the broadcasting the mask data. The only valid values are 0 and 1 for each dimension. For no broadcasting, set the values for each dimension to 1. For broadcasting, set desired values to 0.
      • 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)
      • resultStateForSourceImageSourceStatesDestinationImage

        public MPSCNNDropoutGradientState resultStateForSourceImageSourceStatesDestinationImage​(MPSImage sourceImage,
                                                                                                NSArray<? extends MPSState> sourceStates,
                                                                                                MPSImage destinationImage)
        Description copied from class: MPSCNNKernel
        Allocate a MPSState (subclass) to hold the results from a -encodeBatchToCommandBuffer... operation A graph may need to allocate storage up front before executing. This may be necessary to avoid using too much memory and to manage large batches. The function should allocate any MPSState objects that will be produced by an -encode call with the indicated sourceImages and sourceStates inputs. Though the states can be further adjusted in the ensuing -encode call, the states should be initialized with all important data and all MTLResource storage allocated. The data stored in the MTLResource need not be initialized, unless the ensuing -encode call expects it to be. The MTLDevice used by the result is derived from the source image. The padding policy will be applied to the filter before this is called to give it the chance to configure any properties like MPSCNNKernel.offset. CAUTION: The kernel must have all properties set to values that will ultimately be passed to the -encode call that writes to the state, before -resultStateForSourceImages:sourceStates:destinationImage: is called or behavior is undefined. Please note that -destinationImageDescriptorForSourceImages:sourceStates: will alter some of these properties automatically based on the padding policy. If you intend to call that to make the destination image, then you should call that before -resultStateForSourceImages:sourceStates:destinationImage:. This will ensure the properties used in the encode call and in the destination image creation match those used to configure the state. The following order is recommended: // Configure MPSCNNKernel properties first kernel.edgeMode = MPSImageEdgeModeZero; kernel.destinationFeatureChannelOffset = 128; // concatenation without the copy ... // ALERT: will change MPSCNNKernel properties MPSImageDescriptor * d = [kernel destinationImageDescriptorForSourceImage: source sourceStates: states]; MPSTemporaryImage * dest = [MPSTemporaryImage temporaryImageWithCommandBuffer: cmdBuf imageDescriptor: d]; // Now that all properties are configured properly, we can make the result state // and call encode. MPSState * __nullable destState = [kernel resultStateForSourceImage: source sourceStates: states destinationImage: dest]; // This form of -encode will be declared by the MPSCNNKernel subclass [kernel encodeToCommandBuffer: cmdBuf sourceImage: source destinationState: destState destinationImage: dest ]; Default: returns nil
        Overrides:
        resultStateForSourceImageSourceStatesDestinationImage in class MPSCNNKernel
        Parameters:
        sourceImage - The MPSImage consumed by the associated -encode call.
        sourceStates - The list of MPSStates consumed by the associated -encode call, for a batch size of 1.
        destinationImage - The destination image for the encode call
        Returns:
        The list of states produced by the -encode call for batch size of 1. When the batch size is not 1, this function will be called repeatedly unless -isResultStateReusedAcrossBatch returns YES. If -isResultStateReusedAcrossBatch returns YES, then it will be called once per batch and the MPSStateBatch array will contain MPSStateBatch.length references to the same object.
      • seed

        public long seed()
        [@property] seed The seed used to generate random numbers.
      • 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 MPSCNNKernel
      • temporaryResultStateForCommandBufferSourceImageSourceStatesDestinationImage

        public MPSCNNDropoutGradientState temporaryResultStateForCommandBufferSourceImageSourceStatesDestinationImage​(MTLCommandBuffer commandBuffer,
                                                                                                                      MPSImage sourceImage,
                                                                                                                      NSArray<? extends MPSState> sourceStates,
                                                                                                                      MPSImage destinationImage)
        Description copied from class: MPSCNNKernel
        Allocate a temporary MPSState (subclass) to hold the results from a -encodeBatchToCommandBuffer... operation A graph may need to allocate storage up front before executing. This may be necessary to avoid using too much memory and to manage large batches. The function should allocate any MPSState objects that will be produced by an -encode call with the indicated sourceImages and sourceStates inputs. Though the states can be further adjusted in the ensuing -encode call, the states should be initialized with all important data and all MTLResource storage allocated. The data stored in the MTLResource need not be initialized, unless the ensuing -encode call expects it to be. The MTLDevice used by the result is derived from the command buffer. The padding policy will be applied to the filter before this is called to give it the chance to configure any properties like MPSCNNKernel.offset. CAUTION: The kernel must have all properties set to values that will ultimately be passed to the -encode call that writes to the state, before -resultStateForSourceImages:sourceStates:destinationImage: is called or behavior is undefined. Please note that -destinationImageDescriptorForSourceImages:sourceStates:destinationImage: will alter some of these properties automatically based on the padding policy. If you intend to call that to make the destination image, then you should call that before -resultStateForSourceImages:sourceStates:destinationImage:. This will ensure the properties used in the encode call and in the destination image creation match those used to configure the state. The following order is recommended: // Configure MPSCNNKernel properties first kernel.edgeMode = MPSImageEdgeModeZero; kernel.destinationFeatureChannelOffset = 128; // concatenation without the copy ... // ALERT: will change MPSCNNKernel properties MPSImageDescriptor * d = [kernel destinationImageDescriptorForSourceImage: source sourceStates: states]; MPSTemporaryImage * dest = [MPSTemporaryImage temporaryImageWithCommandBuffer: cmdBuf imageDescriptor: d]; // Now that all properties are configured properly, we can make the result state // and call encode. MPSState * __nullable destState = [kernel temporaryResultStateForCommandBuffer: cmdBuf sourceImage: source sourceStates: states]; // This form of -encode will be declared by the MPSCNNKernel subclass [kernel encodeToCommandBuffer: cmdBuf sourceImage: source destinationState: destState destinationImage: dest ]; Default: returns nil
        Overrides:
        temporaryResultStateForCommandBufferSourceImageSourceStatesDestinationImage in class MPSCNNKernel
        Parameters:
        commandBuffer - The command buffer to allocate the temporary storage against The state will only be valid on this command buffer.
        sourceImage - The MPSImage consumed by the associated -encode call.
        sourceStates - The list of MPSStates consumed by the associated -encode call, for a batch size of 1.
        destinationImage - The destination image for the encode call
        Returns:
        The list of states produced by the -encode call for batch size of 1. When the batch size is not 1, this function will be called repeatedly unless -isResultStateReusedAcrossBatch returns YES. If -isResultStateReusedAcrossBatch returns YES, then it will be called once per batch and the MPSStateBatch array will contain MPSStateBatch.length references to the same object.
      • version_static

        public static long version_static()