32 std::vector<TensorShape>
InferOutputShapes(
const std::vector<TensorShape>& inputShapes)
const override;
bool IsEqual(const Layer &other) const
Indicates if the other layer received is equal to this one.
TransposeDescriptor m_Param
The parameters for the layer (not including tensor-valued weights etc.).
void Accept(ILayerVisitor &visitor) const override
Apply a visitor to this layer.
TransposeLayer * Clone(Graph &graph) const override
Creates a dynamically-allocated copy of this layer.
~TransposeLayer()=default
Default destructor.
Copyright (c) 2020 ARM Limited.
virtual std::unique_ptr< IWorkload > CreateWorkload(const IWorkloadFactory &factory) const override
Makes a workload for the Transpose type.
void ValidateTensorShapesFromInputs() override
Check if the input tensor shape(s) will lead to a valid configuration of TransposeLayer.
TransposeLayer(const TransposeDescriptor ¶m, const char *name)
Constructor to create a TransposeLayer.
bool IsInverse(const Layer &other) const
Indicates if the other layer received is inverse of this one.
This layer represents a transpose operation.
bool IsEqual(const PermutationVector &other) const
std::vector< TensorShape > InferOutputShapes(const std::vector< TensorShape > &inputShapes) const override
Infers the output shapes from given input shapes and the permutation vector.
LayerType GetType() const
A TransposeDescriptor for the TransposeLayer.
bool IsInverse(const PermutationVector &other) const
const PermutationVector & GetPermutation() const
PermutationVector m_DimMappings
Indicates how to translate tensor elements from a given source into the target destination, when source and target potentially have different memory layouts e.g.