24.08
|
Go to the documentation of this file.
29 std::vector<TensorShape>
InferOutputShapes(
const std::vector<TensorShape>& inputShapes)
const override;
void ValidateTensorShapesFromInputs() override
Check if the input tensor shapes will lead to a valid configuration of BatchMatMulLayer.
BatchMatMulLayer * Clone(Graph &graph) const override
Creates a dynamically-allocated copy of this layer.
std::vector< TensorShape > InferOutputShapes(const std::vector< TensorShape > &inputShapes) const override
Infers the output shape from the given input shapes.
virtual std::unique_ptr< IWorkload > CreateWorkload(const IWorkloadFactory &factory) const override
Makes a workload for the BatchMatMul type.
A BatchMatMulDescriptor for the BatchMatMul operator.
Copyright (c) 2021 ARM Limited and Contributors.
BatchMatMulLayer(const BatchMatMulDescriptor ¶m, const char *name)
Constructor to create a BatchMatMulLayer.
~BatchMatMulLayer()=default
Default destructor.