24.08
|
Go to the documentation of this file.
35 std::vector<TensorShape>
InferOutputShapes(
const std::vector<TensorShape>& inputShapes)
const override;
~Pooling2dLayer()=default
Default destructor.
void ValidateTensorShapesFromInputs() override
Check if the input tensor shape(s) will lead to a valid configuration of Pooling2dLayer.
void ExecuteStrategy(IStrategy &strategy) const override
Apply a visitor to this layer.
Pooling2dLayer(const Pooling2dDescriptor ¶m, const char *name)
Constructor to create a Pooling2dLayer.
Pooling2dLayer * Clone(Graph &graph) const override
Creates a dynamically-allocated copy of this layer.
This layer represents a pooling 2d operation.
Copyright (c) 2021 ARM Limited and Contributors.
virtual std::unique_ptr< IWorkload > CreateWorkload(const IWorkloadFactory &factory) const override
Makes a workload for the Pooling2d type.
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,...
A Pooling2dDescriptor for the Pooling2dLayer.