23.05
|
Go to the documentation of this file.
12 class ScopedTensorHandle;
21 std::shared_ptr<ConstTensorHandle>
m_Bias;
41 std::vector<TensorShape>
InferOutputShapes(
const std::vector<TensorShape>& inputShapes)
const override;
TransposeConvolution2dLayer(const TransposeConvolution2dDescriptor ¶m, const char *name)
Constructor to create a TransposeConvolution2dLayer.
~TransposeConvolution2dLayer()=default
Default destructor.
std::shared_ptr< ConstTensorHandle > m_Bias
A unique pointer to store bias values.
ImmutableConstantTensors GetConstantTensorsByRef() const override
Retrieve the handles to the constant values stored by the layer.
Copyright (c) 2021 ARM Limited and Contributors.
This layer represents a 2D transpose convolution operation.
std::shared_ptr< ConstTensorHandle > m_Weight
A unique pointer to store weight values.
std::vector< TensorShape > InferOutputShapes(const std::vector< TensorShape > &inputShapes) const override
Infers the output shapes from given input shapes and layer properties.
void ExecuteStrategy(IStrategy &strategy) const override
Apply a visitor to this layer.
A TransposeConvolution2dDescriptor for the TransposeConvolution2dLayer.
TransposeConvolution2dLayer * Clone(Graph &graph) const override
Creates a dynamically-allocated copy of this layer.
std::vector< std::reference_wrapper< const std::shared_ptr< ConstTensorHandle > >> ImmutableConstantTensors
virtual std::unique_ptr< IWorkload > CreateWorkload(const IWorkloadFactory &factory) const override
Makes a workload for the TransposeConvolution2d type.
void ValidateTensorShapesFromInputs() override
Check if the input tensor shape(s) will lead to a valid configuration of TransposeConvolution2dLayer.