Compute Library
 22.11
DeconvolutionLayerNode Class Referencefinal

Deconvolution Layer node. More...

#include <DeconvolutionLayerNode.h>

Collaboration diagram for DeconvolutionLayerNode:
[legend]

Public Member Functions

 DeconvolutionLayerNode (const descriptors::DeconvolutionLayerDescriptor &descriptor)
 Constructor. More...
 
PadStrideInfo deconvolution_info () const
 Deconvolution metadata accessor. More...
 
NodeType type () const override
 Returns node's type. More...
 
bool forward_descriptors () override
 Forwards descriptor information to outputs if possible. More...
 
TensorDescriptor configure_output (size_t idx) const override
 Calculates output configuration. More...
 
void accept (INodeVisitor &v) override
 Accepts a node visitor. More...
 
- Public Member Functions inherited from INode
 INode ()
 Constructor. More...
 
virtual ~INode ()=default
 Destructor. More...
 
 INode (const INode &)=delete
 Prevent instances of this class from being copied (As this class contains pointers) More...
 
INodeoperator= (const INode &)=delete
 Prevent instances of this class from being copy assigned (As this class contains pointers) More...
 
 INode (INode &&)=default
 Allow instances of this class to be moved. More...
 
INodeoperator= (INode &&)=default
 Allow instances of this class to be move assigned. More...
 
virtual Status validate () const
 Validate node. More...
 
std::string name () const
 Returns node's name. More...
 
NodeID id () const
 Returns node's ID. More...
 
const Graphgraph () const
 Returns node's Graph. More...
 
Graphgraph ()
 Returns node's Graph. More...
 
void set_graph (Graph *g)
 Sets the graph that this node is registered to. More...
 
void set_id (NodeID id)
 Sets the node id. More...
 
void set_common_node_parameters (NodeParams common_params)
 Sets common node parameters. More...
 
void set_requested_target (Target target)
 Sets target preference. More...
 
void set_assigned_target (Target target)
 Sets the final execution target. More...
 
void set_output_tensor (TensorID tid, size_t idx)
 Sets the output tensor of at a given index. More...
 
const std::vector< TensorID > & inputs () const
 Returns inputs of the node. More...
 
const std::vector< TensorID > & outputs () const
 Returns outputs of the node. More...
 
const std::vector< EdgeID > & input_edges () const
 Returns input edge set. More...
 
const std::set< EdgeID > & output_edges () const
 Returns output edge set. More...
 
TensorID input_id (size_t idx) const
 Returns the tensor ID of a given input of the node. More...
 
TensorID output_id (size_t idx) const
 Returns the tensor ID of a given output of the node. More...
 
Tensorinput (size_t idx) const
 Returns the tensor of a given input of the node. More...
 
Tensoroutput (size_t idx) const
 Returns the tensor of a given output of the node. More...
 
EdgeID input_edge_id (size_t idx) const
 Returns the edge ID of a given input of the node. More...
 
Edgeinput_edge (size_t idx) const
 Returns the edge of a given input of the node. More...
 
size_t num_inputs () const
 Returns number of inputs of the node. More...
 
size_t num_outputs () const
 Returns number of outputs of the node. More...
 
NodeParams common_node_params () const
 Returns common node parameters. More...
 
Target requested_target () const
 Returns requested target for this node. More...
 
Target assigned_target () const
 Returns assigned target for this node. More...
 
const std::list< std::unique_ptr< ConvPostOpInfo > > & post_op_info_list () const
 Post operator info list. More...
 
std::list< std::unique_ptr< ConvPostOpInfo > > & post_op_info_list ()
 Post operator info list. More...
 

Static Public Member Functions

static TensorDescriptor compute_output_descriptor (const TensorDescriptor &input_descriptor, const TensorDescriptor &weights_descriptor, const PadStrideInfo &info)
 Computes deconvolution output descriptor. More...
 

Detailed Description

Deconvolution Layer node.

Definition at line 35 of file DeconvolutionLayerNode.h.

Constructor & Destructor Documentation

◆ DeconvolutionLayerNode()

Constructor.

Parameters
[in]descriptorContains information used by this layer described in descriptors::DeconvolutionLayerDescriptor

Definition at line 35 of file DeconvolutionLayerNode.cpp.

References arm_compute::graph::EmptyEdgeID, and arm_compute::graph::NullTensorID.

36  : descriptor(std::move(descriptor))
37 {
38  _input_edges.resize(3, EmptyEdgeID);
39  _outputs.resize(1, NullTensorID);
40 }
constexpr EdgeID EmptyEdgeID
Definition: Types.h:78
constexpr TensorID NullTensorID
Constant NodeID specifying an equivalent of null node.
Definition: Types.h:74

Member Function Documentation

◆ accept()

void accept ( INodeVisitor v)
overridevirtual

Accepts a node visitor.

Parameters
[in]vVisitor to accept

Implements INode.

Definition at line 105 of file DeconvolutionLayerNode.cpp.

References INodeVisitor::visit().

106 {
107  v.visit(*this);
108 }

◆ compute_output_descriptor()

TensorDescriptor compute_output_descriptor ( const TensorDescriptor input_descriptor,
const TensorDescriptor weights_descriptor,
const PadStrideInfo info 
)
static

Computes deconvolution output descriptor.

Parameters
[in]input_descriptorInput descriptor
[in]weights_descriptorWeights descriptor
[in]infoConvolution operation attributes
Returns
Output descriptor

Definition at line 47 of file DeconvolutionLayerNode.cpp.

References arm_compute::CHANNEL, arm_compute::test::validation::data_layout, arm_compute::deconvolution_output_dimensions(), arm_compute::graph::get_dimension_idx(), arm_compute::graph::get_dimension_size(), arm_compute::HEIGHT, input_height, input_width, TensorDescriptor::layout, TensorShape::set(), TensorDescriptor::shape, and arm_compute::WIDTH.

Referenced by DeconvolutionLayerNode::configure_output().

50 {
51  unsigned int output_width = 0;
52  unsigned int output_height = 0;
53 
54  const unsigned int input_width = get_dimension_size(input_descriptor, DataLayoutDimension::WIDTH);
55  const unsigned int input_height = get_dimension_size(input_descriptor, DataLayoutDimension::HEIGHT);
56  const unsigned int kernel_width = get_dimension_size(weights_descriptor, DataLayoutDimension::WIDTH);
57  const unsigned int kernel_height = get_dimension_size(weights_descriptor, DataLayoutDimension::HEIGHT);
58 
59  std::tie(output_width, output_height) = deconvolution_output_dimensions(input_width, input_height, kernel_width, kernel_height, info);
60 
61  const DataLayout data_layout = input_descriptor.layout;
62  TensorDescriptor output_descriptor = input_descriptor;
63  output_descriptor.shape.set(get_dimension_idx(data_layout, DataLayoutDimension::WIDTH), output_width);
64  output_descriptor.shape.set(get_dimension_idx(data_layout, DataLayoutDimension::HEIGHT), output_height);
65  output_descriptor.shape.set(get_dimension_idx(data_layout, DataLayoutDimension::CHANNEL), weights_descriptor.shape[3]);
66 
67  return output_descriptor;
68 }
size_t get_dimension_size(const TensorDescriptor &descriptor, const DataLayoutDimension data_layout_dimension)
Get size of a tensor&#39;s given dimension depending on its layout.
Definition: Utils.cpp:142
std::pair< unsigned int, unsigned int > deconvolution_output_dimensions(unsigned int in_width, unsigned int in_height, unsigned int kernel_width, unsigned int kernel_height, const PadStrideInfo &pad_stride_info)
Returns expected width and height of the deconvolution&#39;s output tensor.
Definition: Utils.cpp:409
const size_t input_height
Definition: impl.cpp:61
const size_t input_width
Definition: impl.cpp:62
ScaleKernelInfo info(interpolation_policy, default_border_mode, PixelValue(), sampling_policy, false)
DataLayout
[DataLayout enum definition]
Definition: Types.h:113
size_t get_dimension_idx(DataLayout data_layout, const DataLayoutDimension data_layout_dimension)
Get index of a tensor&#39;s given dimension depending on its layout.
Definition: Utils.cpp:148

◆ configure_output()

TensorDescriptor configure_output ( size_t  idx) const
overridevirtual

Calculates output configuration.

Parameters
[in]idxOutput index to configure
Returns
Output descriptor configuration

Implements INode.

Definition at line 82 of file DeconvolutionLayerNode.cpp.

References ARM_COMPUTE_ERROR_ON, ARM_COMPUTE_UNUSED, DeconvolutionLayerNode::compute_output_descriptor(), Tensor::desc(), QuantizationInfo::empty(), DeconvolutionLayerDescriptor::info, INode::input(), DeconvolutionLayerDescriptor::out_quant_info, arm_compute::test::validation::output_info, TensorDescriptor::set_quantization_info(), and arm_compute::test::validation::src.

Referenced by DeconvolutionLayerNode::forward_descriptors().

83 {
84  ARM_COMPUTE_UNUSED(idx);
85  const Tensor *src = input(0);
86  const Tensor *weights = input(1);
87 
88  ARM_COMPUTE_ERROR_ON(src == nullptr || weights == nullptr);
89 
90  TensorDescriptor output_info = compute_output_descriptor(src->desc(), weights->desc(), descriptor.info);
91 
92  if(!descriptor.out_quant_info.empty())
93  {
94  output_info.set_quantization_info(descriptor.out_quant_info);
95  }
96 
97  return output_info;
98 }
#define ARM_COMPUTE_ERROR_ON(cond)
If the condition is true then an error message is printed and an exception thrown.
Definition: Error.h:466
SimpleTensor< float > src
Definition: DFT.cpp:155
PadStrideInfo info
Padding and stride information.
static TensorDescriptor compute_output_descriptor(const TensorDescriptor &input_descriptor, const TensorDescriptor &weights_descriptor, const PadStrideInfo &info)
Computes deconvolution output descriptor.
#define ARM_COMPUTE_UNUSED(...)
To avoid unused variables warnings.
Definition: Error.h:152
TensorDescriptor & set_quantization_info(QuantizationInfo tensor_quant_info)
Sets tensor descriptor quantization info.
bool empty() const
Indicates whether this QuantizationInfo has valid settings or not.
Tensor * input(size_t idx) const
Returns the tensor of a given input of the node.
Definition: INode.cpp:151
QuantizationInfo out_quant_info
Output quantization information.

◆ deconvolution_info()

PadStrideInfo deconvolution_info ( ) const

Deconvolution metadata accessor.

Returns
Deconvolution information

Definition at line 42 of file DeconvolutionLayerNode.cpp.

References DeconvolutionLayerDescriptor::info.

43 {
44  return descriptor.info;
45 }
PadStrideInfo info
Padding and stride information.

◆ forward_descriptors()

bool forward_descriptors ( )
overridevirtual

Forwards descriptor information to outputs if possible.

Returns
True if descriptor information could be forwarded otherwise false

Implements INode.

Definition at line 70 of file DeconvolutionLayerNode.cpp.

References ARM_COMPUTE_ERROR_ON, DeconvolutionLayerNode::configure_output(), Tensor::desc(), arm_compute::test::validation::dst, INode::input_id(), arm_compute::graph::NullTensorID, INode::output(), and INode::output_id().

71 {
72  if((input_id(0) != NullTensorID) && (input_id(1) != NullTensorID) && (output_id(0) != NullTensorID))
73  {
74  Tensor *dst = output(0);
75  ARM_COMPUTE_ERROR_ON(dst == nullptr);
76  dst->desc() = configure_output(0);
77  return true;
78  }
79  return false;
80 }
#define ARM_COMPUTE_ERROR_ON(cond)
If the condition is true then an error message is printed and an exception thrown.
Definition: Error.h:466
Tensor * output(size_t idx) const
Returns the tensor of a given output of the node.
Definition: INode.cpp:159
TensorID input_id(size_t idx) const
Returns the tensor ID of a given input of the node.
Definition: INode.cpp:138
TensorDescriptor configure_output(size_t idx) const override
Calculates output configuration.
TensorID output_id(size_t idx) const
Returns the tensor ID of a given output of the node.
Definition: INode.cpp:145
constexpr TensorID NullTensorID
Constant NodeID specifying an equivalent of null node.
Definition: Types.h:74

◆ type()

NodeType type ( ) const
overridevirtual

Returns node's type.

Returns
Node's type

Implements INode.

Definition at line 100 of file DeconvolutionLayerNode.cpp.

References arm_compute::graph::DeconvolutionLayer.


The documentation for this class was generated from the following files: