MPSCNNPooling(3) | MetalPerformanceShaders.framework | MPSCNNPooling(3) |
MPSCNNPooling
#import <MPSCNNPooling.h>
Inherits MPSCNNKernel.
Inherited by MPSCNNDilatedPoolingMax, MPSCNNPoolingAverage, MPSCNNPoolingL2Norm, and MPSCNNPoolingMax.
(nonnull instancetype) -
initWithDevice:kernelWidth:kernelHeight:
(nonnull instancetype) -
initWithDevice:kernelWidth:kernelHeight:strideInPixelsX:strideInPixelsY:
(nullable instancetype) - initWithCoder:device:
(nonnull instancetype) - initWithDevice:
This depends on Metal.framework Pooling is a form of non-linear sub-sampling. Pooling partitions the input image into a set of rectangles (overlapping or non-overlapping) and, for each such sub-region, outputs a value. The pooling operation is used in computer vision to reduce the dimensionality of intermediate representations.
NSSecureCoding compatability See MPSKernel::initWithCoder.
Parameters:
Returns:
Reimplemented from MPSCNNKernel.
Reimplemented in MPSCNNDilatedPoolingMax, MPSCNNPoolingAverage, MPSCNNPoolingL2Norm, and MPSCNNPoolingMax.
Standard init with default properties per filter type
Parameters:
Returns:
Reimplemented from MPSCNNKernel.
Initialize a pooling filter
Parameters:
Returns:
Initialize a pooling filter
Parameters:
Returns:
Reimplemented in MPSCNNPoolingAverage, MPSCNNPoolingL2Norm, and MPSCNNPoolingMax.
Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code.
Mon Jul 9 2018 | Version MetalPerformanceShaders-119.3 |