NAME

MPSCNNNeuronPReLU

SYNOPSIS

#import <MPSCNNNeuron.h>

Inherits MPSCNNNeuron.

Instance Methods

(nonnull instancetype) - initWithDevice:a:count:
(nonnull instancetype) - initWithDevice:

Detailed Description

This depends on Metal.framework Specifies the parametric ReLU neuron filter. 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.

Method Documentation

- (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 MPSCNNNeuron.

- (nonnull instancetype) initWithDevice: (nonnull id< MTLDevice >) device(const float *_Nonnull) a(NSUInteger) count

Initialize the PReLU neuron filter

Parameters:

device The device the filter will run on
a Array of floats containing per channel value of PReLu parameter
count Number of float values in array a. This usually corresponds to number of output channels in convolution layer

Returns:

A valid MPSCNNNeuronPReLU object or nil, if failure.

Author

Generated automatically by Doxygen for MetalPerformanceShaders.framework from the source code.