Package apple.metalperformanceshaders

Class MPSNNNeuronDescriptor

  • All Implemented Interfaces:
    NSCoding, NSCopying, NSSecureCoding, NSObject
    public class MPSNNNeuronDescriptor
extends NSObject
implements NSCopying, NSSecureCoding
    MPSNNNeuronDescriptor [@dependency] This depends on Metal.framework The MPSNNNeuronDescriptor specifies a neuron descriptor. Supported neuron types: Neuron type "none": f(x) = x Parameters: none ReLU neuron filter: f(x) = x >= 0 ? x : a * x This is called Leaky ReLU in literature. Some literature defines classical ReLU as max(0, x). If you want this behavior, simply pass a = 0. Parameters: a For default behavior, set the value of a to 0.0f. Linear neuron filter: f(x) = a * x + b Parameters: a, b For default behavior, set the value of a to 1.0f and the value of b to 0.0f. Sigmoid neuron filter: f(x) = 1 / (1 + e^-x) Parameters: none Hard Sigmoid filter: f(x) = clamp((x * a) + b, 0, 1) Parameters: a, b For default behavior, set the value of a to 0.2f and the value of b to 0.5f. Hyperbolic tangent (TanH) neuron filter: f(x) = a * tanh(b * x) Parameters: a, b For default behavior, set the value of a to 1.0f and the value of b to 1.0f. Absolute neuron filter: f(x) = fabs(x) Parameters: none Parametric Soft Plus neuron filter: f(x) = a * log(1 + e^(b * x)) Parameters: a, b For default behavior, set the value of a to 1.0f and the value of b to 1.0f. Parametric Soft Sign neuron filter: f(x) = x / (1 + abs(x)) Parameters: none Parametric ELU neuron filter: f(x) = x >= 0 ? x : a * (exp(x) - 1) Parameters: a For default behavior, set the value of a to 1.0f. Parametric ReLU (PReLU) neuron filter: Same as ReLU, except parameter aArray is per channel. For each pixel, applies the following function: f(x_i) = x_i, if x_i >= 0 = a_i * x_i if x_i < 0 i in [0...channels-1] i.e. parameters a_i are learned and applied to each channel separately. Compare this to ReLu where parameter a is shared across all channels. See https://arxiv.org/pdf/1502.01852.pdf for details. Parameters: aArray - Array of floats containing per channel value of PReLu parameter count - Number of float values in array aArray. ReLUN neuron filter: f(x) = min((x >= 0 ? x : a * x), b) Parameters: a, b As an example, the TensorFlow Relu6 activation layer can be implemented by setting the parameter b to 6.0f: https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/relu6. For default behavior, set the value of a to 1.0f and the value of b to 6.0f.

    • Constructor Detail

      • MPSNNNeuronDescriptor

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

    • Method Detail

      • a

        public float a()

      • 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)

      • b

        public float b()

      • c

        public float c()

      • 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()

      • cnnNeuronDescriptorWithType

        public static MPSNNNeuronDescriptor cnnNeuronDescriptorWithType​(int neuronType)
        Make a descriptor for a MPSCNNNeuron object.
        Parameters:
        neuronType - The type of a neuron filter.
        Returns:
        A valid MPSNNNeuronDescriptor object or nil, if failure.

      • cnnNeuronDescriptorWithTypeA

        public static MPSNNNeuronDescriptor cnnNeuronDescriptorWithTypeA​(int neuronType,
                                                                 float a)
        Make a descriptor for a MPSCNNNeuron object.
        Parameters:
        neuronType - The type of a neuron filter.
        a - Parameter "a".
        Returns:
        A valid MPSNNNeuronDescriptor object or nil, if failure.

      • cnnNeuronDescriptorWithTypeAB

        public static MPSNNNeuronDescriptor cnnNeuronDescriptorWithTypeAB​(int neuronType,
                                                                  float a,
                                                                  float b)
        Initialize the neuron descriptor.
        Parameters:
        neuronType - The type of a neuron filter.
        a - Parameter "a".
        b - Parameter "b".
        Returns:
        A valid MPSNNNeuronDescriptor object or nil, if failure.

      • cnnNeuronDescriptorWithTypeABC

        public static MPSNNNeuronDescriptor cnnNeuronDescriptorWithTypeABC​(int neuronType,
                                                                   float a,
                                                                   float b,
                                                                   float c)
        Make a descriptor for a MPSCNNNeuron object.
        Parameters:
        neuronType - The type of a neuron filter.
        a - Parameter "a".
        b - Parameter "b".
        c - Parameter "c".
        Returns:
        A valid MPSNNNeuronDescriptor object or nil, if failure.

      • cnnNeuronPReLUDescriptorWithDataNoCopy

        public static MPSNNNeuronDescriptor cnnNeuronPReLUDescriptorWithDataNoCopy​(NSData data,
                                                                           boolean noCopy)
        Make a descriptor for a neuron of type MPSCNNNeuronTypePReLU. The PReLU neuron is the same as a ReLU neuron, except parameter "a" is per feature channel.
        Parameters:
        data - A NSData containing a float array with the per feature channel value of PReLu parameter. The number of float values in this array usually corresponds to number of output channels in a convolution layer. The descriptor retains the NSData object.
        noCopy - An optimization flag that tells us whether the NSData allocation is suitable for use directly with no copying of the data into internal storage. This allocation has to match the same restrictions as listed for the newBufferWithBytesNoCopy:length:options:deallocator: method of MTLBuffer.
        Returns:
        A valid MPSNNNeuronDescriptor object for a neuron of type MPSCNNNeuronTypePReLU or nil, if failure

      • copyWithZone

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

      • data

        public NSData data()
        Note: data is retained, not copied

      • 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()

      • 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)

      • neuronType

        public int neuronType()

      • 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)

      • setA

        public void setA​(float value)

      • setB

        public void setB​(float value)

      • setC

        public void setC​(float value)

      • setData

        public void setData​(NSData value)
        Note: data is retained, not copied

      • setNeuronType

        public void setNeuronType​(int value)

      • 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

      • version_static

        public static long version_static()