MPSCNNNeuronGradient(3) | MetalPerformanceShaders.framework | MPSCNNNeuronGradient(3) |
MPSCNNNeuronGradient
#import <MPSCNNNeuron.h>
Inherits MPSCNNGradientKernel.
(nonnull instancetype) - initWithDevice:
(nonnull instancetype) - initWithDevice:neuronDescriptor:
(nullable instancetype) - initWithCoder:device:
MPSCNNNeuronType neuronType
float a
float b
float c
NSData * data
This depends on Metal.framework This filter is a backward filter for the neuron activation function filter.
The following filter types are supported: MPSCNNNeuronTypeNone ///< df/dx = 1 MPSCNNNeuronTypeLinear ///< df/dx = a MPSCNNNeuronTypeReLU ///< df/dx = [ 1, if x >= 0 [ a, if x < 0 MPSCNNNeuronTypeSigmoid ///< df/dx = e^x / (e^x + 1)^2 MPSCNNNeuronTypeHardSigmoid ///< df/dx = [ a, if (x >= 0) and (x <= 1) [ 0, otherwise MPSCNNNeuronTypeTanH ///< df/dx = a * b * (1 - tanh^2(b * x)) MPSCNNNeuronTypeAbsolute ///< df/dx = sign(x) MPSCNNNeuronTypeSoftPlus ///< df/dx = (a * b * exp(b * x)) / (exp(b * x) + 1) MPSCNNNeuronTypeSoftSign ///< df/dx = 1 / (|x| + 1)^2 MPSCNNNeuronTypeELU ///< df/dx = [ a * exp(x), x < 0 [ 1, x >= 0 MPSCNNNeuronTypePReLU ///< df/dx = [ 1, if x >= 0 [ aV, if x < 0 MPSCNNNeuronTypeReLUN ///< df/dx = [ 1, if x >= 0 [ a, if x < 0 [ b, if x >= b MPSCNNNeuronTypePower ///< df/dx = a * c * (a * x + b)^(c - 1) MPSCNNNeuronTypeExponential ///< df/dx = [ a * exp(a * x + b), if c == -1 [ a * log(c) * c^(a * x + b), if c != -1 MPSCNNNeuronTypeLogarithm ///< df/dx = [ a / (a * in + b), if c == -1 [ a / (log(c) * (a * in + b)), if c != -1
The result of the above operation is multiplied with the gradient, computed by the preceeding filter (going backwards).
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.
Parameters:
Returns:
Reimplemented from MPSCNNGradientKernel.
Standard init with default properties per filter type
Parameters:
Returns:
Reimplemented from MPSCNNGradientKernel.
Initialize the neuron gradient filter with a neuron descriptor.
Parameters:
Returns:
Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code.
Mon Jul 9 2018 | Version MetalPerformanceShaders-119.3 |