class ov::pass::ConvertBatchToSpace

Overview

ConvertBatchToSpace transformation decomposes BatchToSpace layer to Reshape->Transpose->Reshape->Crop. More…

#include <convert_batch_to_space.hpp>

class ConvertBatchToSpace: public ov::pass::MatcherPass
{
public:
    // construction

    ConvertBatchToSpace();

    // methods

    "ConvertBatchToSpace""0" OPENVINO_RTTI(, );
};

Inherited Members

public:
    // typedefs

    typedef DiscreteTypeInfo type_info_t;

    // methods

    boolconst PassPropertyMask& get_property() const;
    voidconst std::string& set_name();
    std::string get_name() const;
    voidconst param_callback& set_callback();
    virtual voidconst std::shared_ptr<PassConfig>& set_pass_config();
    std::shared_ptr<PassConfig> get_pass_config();
    boolconst std::shared_ptr<const Node>& transformation_callback();
    virtual const type_info_t& get_type_info() const = 0;
    "ov::pass::MatcherPass" OPENVINO_RTTI();
    MatcherPass&const MatcherPass& operator = ();
    boolstd::shared_ptr<ov::Node> apply();

    template <, >
    std::shared_ptr<T>Args&&... register_new_node();

    template <>
    std::shared_ptr<T>const std::shared_ptr<T>& register_new_node();

    std::shared_ptr<ov::Node>const std::shared_ptr<ov::Node>& register_new_node_();
    const std::vector<std::shared_ptr<ov::Node>>& get_new_nodes();
    void clear_new_nodes();
    std::shared_ptr<pattern::Matcher> get_matcher();

Detailed Documentation

ConvertBatchToSpace transformation decomposes BatchToSpace layer to Reshape->Transpose->Reshape->Crop.

Parameters:

convert_by_elements

reduces the maximum number of dimensions that arise during the transformation if enabled. Default value: true. false - BatchToSpace decomposes to Reshape->Transpose->Reshape->Crop. During transformation, the number of tensor dimensions can be increased by length of block_shape input of BatchToSpace layer. true - BatchToSpace decomposes to N x (Reshape->Transpose->Reshape)->Crop, where N = length of block_shape input of BatchToSpace layer. During transformation, the number of tensor dimensions can be increased by 1.