class ngraph::pass::low_precision::MarkupQuantizationGranularity

Overview

MarkupPerTensorQuantization transformation marks operations as required per-tensor quantization according to the provided restrictions. More…

#include <markup_quantization_granularity.hpp>

class MarkupQuantizationGranularity: public ov::pass::ModelPass
{
public:
    // classes

    class PerTensorQuantization;

    // construction

    MarkupQuantizationGranularity(const std::vector<QuantizationGranularityRestriction>& restrictions = {});

    // methods

    OPENVINO_RTTI("MarkupPerTensorQuantization", "0");
    bool run_on_model(const std::shared_ptr<ngraph::Function>& m);
};

Inherited Members

public:
    // typedefs

    typedef DiscreteTypeInfo type_info_t;

    // methods

    bool get_property(const PassPropertyMask& prop_mask) const;
    void set_name(const std::string& name);
    std::string get_name() const;
    void set_callback(const param_callback& callback);
    virtual void set_pass_config(const std::shared_ptr<PassConfig>& pass_config);
    std::shared_ptr<PassConfig> get_pass_config();
    bool m_transformation_callback(const std::shared_ptr<const Node>& node);
    bool transformation_callback(const std::shared_ptr<const Node>& node);
    virtual const type_info_t& get_type_info() const = 0;
    OPENVINO_RTTI("ov::pass::ModelPass");
    virtual bool run_on_function(std::shared_ptr<ov::Model> m);
    virtual bool run_on_model(const std::shared_ptr<ov::Model>& m);

Detailed Documentation

MarkupPerTensorQuantization transformation marks operations as required per-tensor quantization according to the provided restrictions.

For more details about the transformation, refer to MarkupPerTensorQuantization page in the Inference Engine Developer Guide.