34 std::vector<TensorShape>
InferOutputShapes(
const std::vector<TensorShape>& inputShapes)
const override;
void Accept(ILayerVisitor &visitor) const override
Apply a visitor to this layer.
bool IsInverse(const Layer &other) const
Indicates if the other layer received is inverse of this one.
virtual std::unique_ptr< IWorkload > CreateWorkload(const IWorkloadFactory &factory) const override
Makes a workload for the Permute type.
PermuteDescriptor m_Param
The parameters for the layer (not including tensor-valued weights etc.).
bool IsEqual(const Layer &other) const
Indicates if the other layer received is equal to this one.
PermuteLayer(const PermuteDescriptor ¶m, const char *name)
Constructor to create a PermuteLayer.
Copyright (c) 2020 ARM Limited.
~PermuteLayer()=default
Default destructor.
This layer represents a permutation operation.
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.
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.
void ValidateTensorShapesFromInputs() override
Check if the input tensor shape(s) will lead to a valid configuration of PermuteLayer.
PermuteLayer * Clone(Graph &graph) const override
Creates a dynamically-allocated copy of this layer.
bool IsEqual(const PermutationVector &other) const
const PermutationVector & GetPermutation() const
LayerType GetType() const
bool IsInverse(const PermutationVector &other) const
A PermuteDescriptor for the PermuteLayer.