24.02.1
|
Go to the documentation of this file.
36 : descriptor(std::move(descriptor))
44 return descriptor.
info;
51 unsigned int output_width = 0;
52 unsigned int output_height = 0;
59 std::tie(output_width, output_height) =
67 weights_descriptor.
shape[3]);
69 return output_descriptor;
constexpr EdgeID EmptyEdgeID
SimpleTensor< float > src
DataLayout
[DataLayout enum definition]
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's output tensor.
TensorID input_id(size_t idx) const
Returns the tensor ID of a given input of the node.
TensorDescriptor & desc()
TensorInfo metadata accessor.
Tensor * output(size_t idx) const
Returns the tensor of a given output of the node.
DeconvolutionLayerNode(const descriptors::DeconvolutionLayerDescriptor &descriptor)
Constructor.
size_t get_dimension_size(const TensorDescriptor &descriptor, const DataLayoutDimension data_layout_dimension)
Get size of a tensor's given dimension depending on its layout.
PadStrideInfo deconvolution_info() const
Deconvolution metadata accessor.
constexpr auto data_layout
NodeType type() const override
Returns node's type.
bool forward_descriptors() override
Forwards descriptor information to outputs if possible.
#define ARM_COMPUTE_ERROR_ON(cond)
If the condition is true then an error message is printed and an exception thrown.
Deconvolution layer descriptor.
DataLayout layout
Data layout.
virtual void visit(INode &n)=0
Visit INode.
TensorShape shape
Tensor shape.
#define ARM_COMPUTE_UNUSED(...)
To avoid unused variables warnings.
QuantizationInfo out_quant_info
Output quantization information.
static TensorDescriptor compute_output_descriptor(const TensorDescriptor &input_descriptor, const TensorDescriptor &weights_descriptor, const PadStrideInfo &info)
Computes deconvolution output descriptor.
size_t get_dimension_idx(DataLayout data_layout, const DataLayoutDimension data_layout_dimension)
Get index of a tensor's given dimension depending on its layout.
Copyright (c) 2017-2024 Arm Limited.
bool empty() const
Indicates whether this QuantizationInfo has valid settings or not.
void accept(INodeVisitor &v) override
Accepts a node visitor.
Tensor * input(size_t idx) const
Returns the tensor of a given input of the node.
PadStrideInfo info
Padding and stride information.
TensorID output_id(size_t idx) const
Returns the tensor ID of a given output of the node.
constexpr TensorID NullTensorID
Constant NodeID specifying an equivalent of null node.
ScaleKernelInfo info(interpolation_policy, default_border_mode, PixelValue(), sampling_policy, false)
TensorShape & set(size_t dimension, size_t value, bool apply_dim_correction=true, bool increase_dim_unit=true)
Accessor to set the value of one of the dimensions.
TensorDescriptor configure_output(size_t idx) const override
Calculates output configuration.