MPSCNNDropout(3) | MetalPerformanceShaders.framework | MPSCNNDropout(3) |
MPSCNNDropout
#import <MPSCNNDropout.h>
Inherits MPSCNNKernel.
(nonnull instancetype) - initWithDevice:
(nullable instancetype) - initWithCoder:device:
(nonnull instancetype) -
initWithDevice:keepProbability:seed:maskStrideInPixels:
(MPSCNNDropoutGradientState *__nullable) -
temporaryResultStateForCommandBuffer:sourceImage:sourceStates:destinationImage:
(MPSCNNDropoutGradientStateBatch *__nullable) -
temporaryResultStateBatchForCommandBuffer:
float keepProbability
NSUInteger seed
MTLSize maskStrideInPixels
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.
<NSSecureCoding> support
Reimplemented from MPSCNNKernel.
Standard init with default properties per filter type
Parameters:
Returns:
Reimplemented from MPSCNNKernel.
Standard init with default properties per filter type.
Parameters:
Returns:
The probability that each element in the input is kept. The valid range is (0.0f, 1.0f).
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.
The seed used to generate random numbers.
Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code.
Mon Jul 9 2018 | Version MetalPerformanceShaders-119.3 |