MPSCNNBinaryFullyConnected
#import <MPSCNNConvolution.h>
Inherits MPSCNNBinaryConvolution.
(nonnull instancetype) -
initWithDevice:convolutionData:scaleValue:type:flags:
(nonnull instancetype) -
initWithDevice:convolutionData:outputBiasTerms:outputScaleTerms:inputBiasTerms:inputScaleTerms:type:flags:
(nullable instancetype) - initWithCoder:device:
(nonnull instancetype) - initWithDevice:
This depends on Metal.framework The
MPSCNNBinaryFullyConnected specifies a fully connected convolution
layer with binary weights and optionally binarized input image. See
MPSCNNFullyConnected for details on the fully connected layer and
MPSCNNBinaryConvolution for binary convolutions.
The default padding policy for MPSCNNBinaryConvolution is
different from most filters. It uses MPSNNPaddingMethodSizeValidOnly instead
of MPSNNPaddingMethodSizeSame.
- (nullable instancetype) initWithCoder: (NSCoder
*__nonnull) aDecoder(nonnull id< MTLDevice >) device
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:
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.
Reimplemented from MPSCNNBinaryConvolution.
- (nonnull instancetype) initWithDevice: (nonnull id<
MTLDevice >) device
Standard init with default properties per filter type
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.
Reimplemented from MPSCNNBinaryConvolution.
- (nonnull instancetype) initWithDevice: (nonnull id<
MTLDevice >) device(nonnull id< MPSCNNConvolutionDataSource >)
convolutionData(const float *__nullable) outputBiasTerms(const float
*__nullable) outputScaleTerms(const float *__nullable) inputBiasTerms(const
float *__nullable) inputScaleTerms(MPSCNNBinaryConvolutionType)
type(MPSCNNBinaryConvolutionFlags) flags
Initializes a binary fully connected kernel with binary weights as
well as both pre and post scaling terms.
Parameters:
device The MTLDevice on which this
MPSCNNBinaryFullyConnected filter will be used
convolutionData A pointer to a object that conforms to the
MPSCNNConvolutionDataSource protocol. The
MPSCNNConvolutionDataSource protocol declares the methods that an
instance of MPSCNNBinaryFullyConnected uses to obtain the weights and
the convolution descriptor. Each entry in the convolutionData:weights array is
a 32-bit unsigned integer value and each bit represents one filter weight
(given in machine byte order). The featurechannel indices increase from the
least significant bit within the 32-bits. The number of entries is = ceil(
inputFeatureChannels/32.0 ) * outputFeatureChannels * kernelHeight *
kernelWidth The layout of filter weight is so that it can be reinterpreted as
a 4D tensor (array) weight[ outputChannels ][ kernelHeight ][ kernelWidth ][
ceil( inputChannels / 32.0 ) ] (The ordering of the reduction from 4D tensor
to 1D is per C convention. The index based on inputchannels varies most
rapidly, followed by kernelWidth, then kernelHeight and finally outputChannels
varies least rapidly.)
outputBiasTerms A pointer to bias terms to be applied to the
convolution output. Each entry is a float value. The number of entries is =
numberOfOutputFeatureMaps. If nil then 0.0 is used for bias. The values stored
in the pointer are copied in and the array can be freed after this function
returns.
outputScaleTerms A pointer to scale terms to be applied to binary
convolution results per output feature channel. Each entry is a float value.
The number of entries is = numberOfOutputFeatureMaps. If nil then 1.0 is used.
The values stored in the pointer are copied in and the array can be freed
after this function returns.
inputBiasTerms A pointer to offset terms to be applied to the
input before convolution and before input scaling. Each entry is a float
value. The number of entries is 'inputFeatureChannels'. If NULL then 0.0 is
used for bias. The values stored in the pointer are copied in and the array
can be freed after this function returns.
inputScaleTerms A pointer to scale terms to be applied to the
input before convolution, but after input biasing. Each entry is a float
value. The number of entries is 'inputFeatureChannels'. If nil then 1.0 is
used. The values stored in the pointer are copied in and the array can be
freed after this function returns.
type What kind of binarization strategy is to be used.
flags See documentation above and documentation of
MPSCNNBinaryConvolutionFlags.
Returns:
A valid MPSCNNBinaryFullyConnected object
or nil, if failure.
Reimplemented from MPSCNNBinaryConvolution.
- (nonnull instancetype) initWithDevice: (nonnull id<
MTLDevice >) device(nonnull id< MPSCNNConvolutionDataSource >)
convolutionData(float) scaleValue(MPSCNNBinaryConvolutionType)
type(MPSCNNBinaryConvolutionFlags) flags
Initializes a binary fully connected kernel with binary weights
and a single scaling term.
Parameters:
device The MTLDevice on which this
MPSCNNBinaryFullyConnected filter will be used
convolutionData A pointer to a object that conforms to the
MPSCNNConvolutionDataSource protocol. The
MPSCNNConvolutionDataSource protocol declares the methods that an
instance of MPSCNNBinaryFullyConnected uses to obtain the weights and
bias terms as well as the convolution descriptor. Each entry in the
convolutionData:weights array is a 32-bit unsigned integer value and each bit
represents one filter weight (given in machine byte order). The featurechannel
indices increase from the least significant bit within the 32-bits. The number
of entries is = ceil( inputFeatureChannels/32.0 ) * outputFeatureChannels *
kernelHeight * kernelWidth The layout of filter weight is so that it can be
reinterpreted as a 4D tensor (array) weight[ outputChannels ][ kernelHeight ][
kernelWidth ][ ceil( inputChannels / 32.0 ) ] (The ordering of the reduction
from 4D tensor to 1D is per C convention. The index based on inputchannels
varies most rapidly, followed by kernelWidth, then kernelHeight and finally
outputChannels varies least rapidly.)
scaleValue A single floating point value used to scale the entire
convolution. Each entry is a float value. The number of entries is
'inputFeatureChannels'. If nil then 1.0 is used.
type What kind of binarization strategy is to be used.
flags See documentation above and documentation of
MPSCNNBinaryConvolutionFlags.
Returns:
A valid MPSCNNBinaryFullyConnected object
or nil, if failure.
Reimplemented from MPSCNNBinaryConvolution.
Generated automatically by Doxygen for
MetalPerformanceShaders.framework from the source code.