13 class ScopedTensorHandle;
38 std::vector<TensorShape>
InferOutputShapes(
const std::vector<TensorShape>& inputShapes)
const override;
virtual std::unique_ptr< IWorkload > CreateWorkload(const IWorkloadFactory &factory) const override
Makes a workload for the Convolution3d type.
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, otherwise infers the output shapes from given input shapes and layer properties.
Copyright (c) 2021 ARM Limited and Contributors.
void SerializeLayerParameters(ParameterStringifyFunction &fn) const override
Helper to serialize the layer parameters to string.
Convolution3dLayer * Clone(Graph &graph) const override
Creates a dynamically-allocated copy of this layer.
A Convolution3dDescriptor for the Convolution3dLayer.
Convolution3dLayer(const Convolution3dDescriptor ¶m, const char *name)
Constructor to create a Convolution3dLayer.
void ValidateTensorShapesFromInputs() override
Check if the input tensor shape(s) will lead to a valid configuration of Convolution3dLayer.
This layer represents a convolution 3d operation.
std::function< void(const std::string &name, const std::string &value)> ParameterStringifyFunction
~Convolution3dLayer()=default
Default destructor.