24.02
|
Go to the documentation of this file.
12 class ScopedTensorHandle;
38 std::vector<TensorShape>
InferOutputShapes(
const std::vector<TensorShape>& inputShapes)
const override;
~DepthwiseConvolution2dLayer()=default
Default destructor.
This layer represents a depthwise convolution 2d operation.
virtual std::unique_ptr< IWorkload > CreateWorkload(const IWorkloadFactory &factory) const override
Makes a workload for the DepthwiseConvolution2d type.
std::vector< std::reference_wrapper< const std::shared_ptr< ConstTensorHandle > >> ImmutableConstantTensors
DepthwiseConvolution2dLayer * Clone(Graph &graph) const override
Creates a dynamically-allocated copy of this layer.
void ValidateTensorShapesFromInputs() override
Check if the input tensor shape(s) will lead to a valid configuration of DepthwiseConvolution2dLayer.
std::function< void(const std::string &name, const std::string &value)> ParameterStringifyFunction
ImmutableConstantTensors GetConstantTensorsByRef() const override
Retrieve the handles to the constant values connected to the layer.
void ReleaseConstantData() override
This layer does not have any data stored, weights and bias are now stored in constant layers.
void ExecuteStrategy(IStrategy &strategy) const override
Apply a visitor to this layer.
std::vector< TensorShape > InferOutputShapes(const std::vector< TensorShape > &inputShapes) const override
By default returns inputShapes if the number of inputs are equal to number of outputs,...
Copyright (c) 2021 ARM Limited and Contributors.
A DepthwiseConvolution2dDescriptor for the DepthwiseConvolution2dLayer.
void SerializeLayerParameters(ParameterStringifyFunction &fn) const override
Helper to serialize the layer parameters to string.
DepthwiseConvolution2dLayer(const DepthwiseConvolution2dDescriptor ¶m, const char *name)
Constructor to create a DepthwiseConvolution2dLayer.