MPSRNNImageInferenceLayer(3)
NAME
MPSRNNImageInferenceLayer
SYNOPSIS
#import <MPSRNNLayer.h>
Inherits MPSCNNKernel.
Instance Methods
(nonnull instancetype) - initWithDevice:rnnDescriptor:
(nonnull instancetype) - initWithDevice:rnnDescriptors:
(nonnull instancetype) - initWithDevice:
(void) -
encodeSequenceToCommandBuffer:sourceImages:destinationImages:recurrentInputState:recurrentOutputStates:
(void) -
encodeBidirectionalSequenceToCommandBuffer:sourceSequence:destinationForwardImages:destinationBackwardImages:
(nullable instancetype) - initWithCoder:device:
(nonnull instancetype) - copyWithZone:device:
Properties
NSUInteger inputFeatureChannels
NSUInteger outputFeatureChannels
NSUInteger numberOfLayers
BOOL recurrentOutputIsTemporary
BOOL storeAllIntermediateStates
MPSRNNBidirectionalCombineMode bidirectionalCombineMode
Additional Inherited Members
Detailed Description
This depends on Metal.framework The MPSRNNImageInferenceLayer
specifies a recurrent neural network layer for inference on MPSImages.
Currently two types of recurrent layers are supported: ones that
operate with convolutions on images: MPSRNNImageInferenceLayer and one
that operates on matrices: MPSRNNMatrixInferenceLayer. The former can
be often used to implement the latter by using 1x1-images, but due to
image size restrictions and performance, it is advisable to use
MPSRNNMatrixInferenceLayer for linear recurrent layers. A
MPSRNNImageInferenceLayer is initialized using a MPSRNNLayerDescriptor,
which further specifies the recurrent network layer, or an array of
MPSRNNLayerDescriptors, which specifies a stack of recurrent layers,
that can operate in parallel a subset of the inputs in a sequence of
inputs and recurrent outputs. Note that currently stacks with
bidirectionally traversing encode functions do not support starting
from a previous set of recurrent states, but this can be achieved quite
easily by defining two separate unidirectional stacks of layers, and
running the same input sequence on them separately (one forwards and
one backwards) and ultimately combining the two result sequences as
desired with auxiliary functions.
Method Documentation
- (nonnull instancetype) copyWithZone: (nullable NSZone *) zone(nullable
id< MTLDevice >) device
Make a copy of this kernel for a new device -
See also:
MPSKernel
Parameters:
zone The NSZone in which to allocate the object
device The device for the new MPSKernel. If nil, then use
self.device.
Returns:
a pointer to a copy of this MPSKernel. This will fail, returning
nil if the device is not supported. Devices must be
MTLFeatureSet_iOS_GPUFamily2_v1 or later.
Reimplemented from MPSKernel.
- (void) encodeBidirectionalSequenceToCommandBuffer: (nonnull id<
MTLCommandBuffer >) commandBuffer(NSArray< MPSImage * > *__nonnull)
sourceSequence(NSArray< MPSImage * > *__nonnull)
destinationForwardImages(NSArray< MPSImage * > *__nullable)
destinationBackwardImages
Encode an MPSRNNImageInferenceLayer kernel stack for an input image
sequences into a command buffer bidirectionally. The operation proceeds
as follows: The first source image x0 is passed through all forward
traversing layers in the stack, ie. those that were initialized with
MPSRNNSequenceDirectionForward, recurrent input is assumed zero. This
produces forward output yf0 and recurrent states hf00, hf01, hf02, ...
hf0n, one for each forward layer. Then x1 is passed to forward layers
together with recurrent state hf00, hf01, ..., hf0n, which produces
yf1, and hf10,... This procedure is iterated until the last image in
the input sequence x_(N-1), which produces forward output yf(N-1). The
backwards layers iterate the same sequence backwards, starting from
input x_(N-1) (recurrent state zero), that produces yb(N-1) and
recurrent output hb(N-1)0, hf(N-1)1, ... hb(N-1)m, one for each
backwards traversing layer. Then the backwards layers handle input
x_(N-2) using recurrent state hb(N-1)0, ..., et cetera, until the first
image of the sequence is computed, producing output yb0. The result of
the operation is either pair of sequences ({yf0, yf1, ... , yf(N-1)},
{yb0, yb1, ... , yb(N-1)}) or a combined sequence, {(yf0 + yb0), ... ,
(yf(N-1) + yb(N-1)) }, where '+' stands either for sum, or
concatenation along feature channels, as specified by
bidirectionalCombineMode.
Parameters:
commandBuffer A valid MTLCommandBuffer to receive the encoded
filter
sourceSequence An array of valid MPSImage objects containing the
source image sequence (x0, x1, ... x_n-1).
destinationForwardImages An array of valid MPSImages to be
overwritten by result from forward input images. If
bidirectionalCombineMode is either
MPSRNNBidirectionalCombineModeAdd or
MPSRNNBidirectionalCombineModeConcatenate, then will contain the
combined results. destinationForwardImage may not alias with any of
the source images.
destinationBackwardImages If bidirectionalCombineMode is
MPSRNNBidirectionalCombineModeNone, then must be a valid MPSImage
that will be overwritten by result from backward input image.
Otherwise this parameter is ignored and can be nil.
destinationBackwardImages may not alias to any of the source
images.
- (void) encodeSequenceToCommandBuffer: (nonnull id< MTLCommandBuffer >)
commandBuffer(NSArray< MPSImage * > *__nonnull) sourceImages(NSArray<
MPSImage * > *__nonnull) destinationImages(MPSRNNRecurrentImageState
*__nullable) recurrentInputState(NSMutableArray<
MPSRNNRecurrentImageState * > *__nullable) recurrentOutputStates
Encode an MPSRNNImageInferenceLayer kernel (stack) for a sequence of
inputs into a command buffer. Note that when encoding using this
function the
See also:
layerSequenceDirection is ignored and the layer stack operates as
if all layers were forward feeding layers. In order to run
bidirectional sequences use
encodeBidirectionalSequenceToCommandBuffer:sourceSequence: or
alternatively run two layer stacks and combine results at the end
using utility functions.
Parameters:
commandBuffer A valid MTLCommandBuffer to receive the encoded
filter
sourceImages An array of valid MPSImage objects containing the
sequence of source images.
destinationImages An array valid MPSImages to be overwritten by
result image sequence. destinationImages may not alias
sourceImages.
recurrentInputState An optional state containing the output images
and memory cells (for LSTMs) of the layer obtained from the
previous input images in a sequence of inputs. Has to be the output
of a previous call to this function or nil (assumed zero). Note:
can be one of the states returned in recurrentOutputStates.
recurrentOutputStates An optional array that will contain the
recurrent output states. If nil then the recurrent output state is
discarded. If storeAllIntermediateStates is YES, then all
intermediate states of the sequence are returned in the array, the
first one corresponding to the first input in the sequence,
otherwise only the last recurrent output state is returned. If
recurrentOutputIsTemporary is YES and then all returned recurrent
states will be temporary.
See also:
MPSState:isTemporary. Example: In order to get a new state one can
do the following:
MPSRNNRecurrentImageState* recurrent0 = nil;
[filter encodeToCommandBuffer: cmdBuf
sourceImage: source0
destinationImage: destination0
recurrentInputState: nil
recurrentOutputState: &recurrent0];
Then use it for the next input in sequence:
[filter encodeToCommandBuffer: cmdBuf
sourceImage: source1
destinationImage: destination1
recurrentInputState: recurrent0
recurrentOutputState: &recurrent0];
And discard recurrent output of the third input:
[filter encodeToCommandBuffer: cmdBuf
sourceImage: source2
destinationImage: destination2
recurrentInputState: recurrent0
recurrentOutputState: nil];
- (nullable instancetype) initWithCoder: (NSCoder *__nonnull)
aDecoder(nonnull id< MTLDevice >) device
NSSecureCoding compatability See MPSKernel::initWithCoder.
Parameters:
aDecoder The NSCoder subclass with your serialized
MPSRNNImageInferenceLayer
device The MTLDevice on which to make the MPSRNNImageInferenceLayer
Returns:
A new MPSRNNImageInferenceLayer object, or nil if failure.
Reimplemented from MPSCNNKernel.
- (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 MPSCNNKernel.
- (nonnull instancetype) initWithDevice: (nonnull id< MTLDevice >)
device(nonnull const MPSRNNDescriptor *) rnnDescriptor
Initializes a convolutional RNN kernel
Parameters:
device The MTLDevice on which this MPSRNNImageLayer filter will be
used
rnnDescriptor The descriptor that defines the RNN layer
Returns:
A valid MPSRNNImageInferenceLayer object or nil, if failure.
- (nonnull instancetype) initWithDevice: (nonnull id< MTLDevice >)
device(NSArray< const MPSRNNDescriptor * > *__nonnull) rnnDescriptors
Initializes a kernel that implements a stack of convolutional RNN
layers
Parameters:
device The MTLDevice on which this MPSRNNImageLayer filter will be
used
rnnDescriptors An array of RNN descriptors that defines a stack of
RNN layers, starting at index zero. The number of layers in stack
is the number of entries in the array. All entries in the array
must be valid MPSRNNDescriptors.
Returns:
A valid MPSRNNImageInferenceLayer object or nil, if failure.
Property Documentation
- bidirectionalCombineMode [read], [write], [nonatomic], [assign]
Defines how to combine the output-results, when encoding bidirectional
layers using encodeBidirectionalSequenceToCommandBuffer. Defaults to
MPSRNNBidirectionalCombineModeNone.
- inputFeatureChannels [read], [nonatomic], [assign]
The number of feature channels per pixel in the input image.
- numberOfLayers [read], [nonatomic], [assign]
Number of layers in the filter-stack. This will be one when using
initWithDevice:rnnDescriptor to initialize this filter and the number
of entries in the array 'rnnDescriptors' when initializing this filter
with initWithDevice:rnnDescriptors.
- outputFeatureChannels [read], [nonatomic], [assign]
The number of feature channels per pixel in the output image.
- recurrentOutputIsTemporary [read], [write], [nonatomic], [assign]
How output states from encodeSequenceToCommandBuffer are constructed.
Defaults to NO. For reference
See also:
MPSState.
- storeAllIntermediateStates [read], [write], [nonatomic], [assign]
If YES then calls to encodeSequenceToCommandBuffer return every
recurrent state in the array: recurrentOutputStates. Defaults to NO.
Author
Generated automatically by Doxygen for
MetalPerformanceShaders.framework from the source code.
Version MetalPerformanceShaders-Thu2Jul 13 2017 MPSRNNImageInferenceLayer(3)
Mac OS X 10.12.6 - Generated Tue Oct 31 19:32:43 CDT 2017
