class ov::op::v0::FakeQuantize

Overview

Class performing element-wise linear quantization. More…

#include <fake_quantize.hpp>

class FakeQuantize: public ov::op::Op
{
public:
    // fields

     BWDCMP_RTTI_DECLARATION;

    // construction

    FakeQuantize();

    FakeQuantize(
        const Output<Node>& data,
        const Output<Node>& input_low,
        const Output<Node>& input_high,
        const Output<Node>& output_low,
        const Output<Node>& output_high,
        std::size_t levels,
        const AutoBroadcastSpec& auto_broadcast = AutoBroadcastSpec(AutoBroadcastType::NUMPY)
        );

    // methods

    OPENVINO_OP("FakeQuantize", "opset1");
    virtual bool visit_attributes(AttributeVisitor& visitor);
    virtual void validate_and_infer_types();
    virtual std::shared_ptr<Node> clone_with_new_inputs(const OutputVector& new_args) const;
    std::size_t get_levels() const;
    void set_levels(std::size_t levels);
    const AutoBroadcastSpec& get_auto_broadcast() const;
    void set_auto_broadcast(const AutoBroadcastSpec& auto_broadcast);

    virtual OPENVINO_SUPPRESS_DEPRECATED_START bool evaluate(
        const HostTensorVector& output_values,
        const HostTensorVector& input_values
        ) const;

    virtual OPENVINO_SUPPRESS_DEPRECATED_END bool has_evaluate() const;

    virtual bool constant_fold(
        OutputVector& output_values,
        const OutputVector& inputs_values
        );
};

Inherited Members

public:
    // typedefs

    typedef DiscreteTypeInfo type_info_t;
    typedef std::map<std::string, Any> RTMap;

    // methods

    virtual void validate_and_infer_types();
    void constructor_validate_and_infer_types();
    virtual bool visit_attributes(AttributeVisitor&);
    virtual const ov::op::AutoBroadcastSpec& get_autob() const;
    virtual bool has_evaluate() const;

    virtual bool evaluate(
        const ov::HostTensorVector& output_values,
        const ov::HostTensorVector& input_values
        ) const;

    virtual bool evaluate(
        const ov::HostTensorVector& output_values,
        const ov::HostTensorVector& input_values,
        const EvaluationContext& evaluationContext
        ) const;

    virtual bool evaluate_lower(const ov::HostTensorVector& output_values) const;
    virtual bool evaluate_upper(const ov::HostTensorVector& output_values) const;

    virtual bool evaluate(
        ov::TensorVector& output_values,
        const ov::TensorVector& input_values
        ) const;

    virtual bool evaluate(
        ov::TensorVector& output_values,
        const ov::TensorVector& input_values,
        const ov::EvaluationContext& evaluationContext
        ) const;

    virtual bool evaluate_lower(ov::TensorVector& output_values) const;
    virtual bool evaluate_upper(ov::TensorVector& output_values) const;
    virtual bool evaluate_label(TensorLabelVector& output_labels) const;

    virtual bool constant_fold(
        OutputVector& output_values,
        const OutputVector& inputs_values
        );

    virtual OutputVector decompose_op() const;
    virtual const type_info_t& get_type_info() const = 0;
    const char \* get_type_name() const;
    void set_arguments(const NodeVector& arguments);
    void set_arguments(const OutputVector& arguments);
    void set_argument(size_t position, const Output<Node>& argument);

    void set_output_type(
        size_t i,
        const element::Type& element_type,
        const PartialShape& pshape
        );

    void set_output_size(size_t output_size);
    void invalidate_values();
    virtual void revalidate_and_infer_types();
    virtual std::string description() const;
    const std::string& get_name() const;
    void set_friendly_name(const std::string& name);
    const std::string& get_friendly_name() const;
    virtual bool is_dynamic() const;
    size_t get_instance_id() const;
    virtual std::ostream& write_description(std::ostream& os, uint32_t depth = 0) const;
    const std::vector<std::shared_ptr<Node>>& get_control_dependencies() const;
    const std::vector<Node \*>& get_control_dependents() const;
    void add_control_dependency(std::shared_ptr<Node> node);
    void remove_control_dependency(std::shared_ptr<Node> node);
    void clear_control_dependencies();
    void clear_control_dependents();
    void add_node_control_dependencies(std::shared_ptr<Node> source_node);
    void add_node_control_dependents(std::shared_ptr<Node> source_node);
    void transfer_control_dependents(std::shared_ptr<Node> replacement);
    size_t get_output_size() const;
    const element::Type& get_output_element_type(size_t i) const;
    const element::Type& get_element_type() const;
    const Shape& get_output_shape(size_t i) const;
    const PartialShape& get_output_partial_shape(size_t i) const;
    Output<const Node> get_default_output() const;
    Output<Node> get_default_output();
    virtual size_t get_default_output_index() const;
    size_t no_default_index() const;
    const Shape& get_shape() const;
    descriptor::Tensor& get_output_tensor(size_t i) const;
    descriptor::Tensor& get_input_tensor(size_t i) const;
    const std::string& get_output_tensor_name(size_t i) const;
    std::set<Input<Node>> get_output_target_inputs(size_t i) const;
    size_t get_input_size() const;
    const element::Type& get_input_element_type(size_t i) const;
    const Shape& get_input_shape(size_t i) const;
    const PartialShape& get_input_partial_shape(size_t i) const;
    const std::string& get_input_tensor_name(size_t i) const;
    Node \* get_input_node_ptr(size_t index) const;
    std::shared_ptr<Node> get_input_node_shared_ptr(size_t index) const;
    Output<Node> get_input_source_output(size_t i) const;
    virtual std::shared_ptr<Node> clone_with_new_inputs(const OutputVector& inputs) const = 0;
    std::shared_ptr<Node> copy_with_new_inputs(const OutputVector& new_args) const;

    std::shared_ptr<Node> copy_with_new_inputs(
        const OutputVector& inputs,
        const std::vector<std::shared_ptr<Node>>& control_dependencies
        ) const;

    bool has_same_type(std::shared_ptr<const Node> node) const;
    RTMap& get_rt_info();
    const RTMap& get_rt_info() const;
    NodeVector get_users(bool check_is_used = false) const;
    virtual size_t get_version() const;
    virtual std::shared_ptr<Node> get_default_value() const;
    bool operator < (const Node& other) const;
    std::vector<Input<Node>> inputs();
    std::vector<Input<const Node>> inputs() const;
    std::vector<Output<Node>> input_values() const;
    std::vector<Output<Node>> outputs();
    std::vector<Output<const Node>> outputs() const;
    Input<Node> input(size_t input_index);
    Input<const Node> input(size_t input_index) const;
    Output<Node> input_value(size_t input_index) const;
    Output<Node> output(size_t output_index);
    Output<const Node> output(size_t output_index) const;
    OPENVINO_SUPPRESS_DEPRECATED_START void set_op_annotations(std::shared_ptr<ngraph::op::util::OpAnnotations> op_annotations);
    std::shared_ptr<ngraph::op::util::OpAnnotations> get_op_annotations() const;

    virtual OPENVINO_SUPPRESS_DEPRECATED_END bool match_value(
        ov::pass::pattern::Matcher \* matcher,
        const Output<Node>& pattern_value,
        const Output<Node>& graph_value
        );

    virtual bool match_node(
        ov::pass::pattern::Matcher \* matcher,
        const Output<Node>& graph_value
        );

    static _OPENVINO_HIDDEN_METHODconst ::ov::Node::type_info_t& get_type_info_static();
    virtual const ::ov::Node::type_info_t& get_type_info() const;

Detailed Documentation

Class performing element-wise linear quantization.

Input floating point values are quantized into a discrete set of floating point values.

Construction

FakeQuantize(
    const Output<Node>& data,
    const Output<Node>& input_low,
    const Output<Node>& input_high,
    const Output<Node>& output_low,
    const Output<Node>& output_high,
    std::size_t levels,
    const AutoBroadcastSpec& auto_broadcast = AutoBroadcastSpec(AutoBroadcastType::NUMPY)
    )

Constructs a FakeQuantize operation node.

Parameters:

data

The input data tensor.

input_low

The minimum limit for input values.

input_high

The maximum limit for input values.

output_low

The minimum quantized value.

output_high

The maximum quantized value.

levels

The number of quantization levels.

auto_broadcast

AutoBroadcast mode to be used for broadcasting limit values

Methods

virtual void validate_and_infer_types()

Verifies that attributes and inputs are consistent and computes output shapes and element types. Must be implemented by concrete child classes so that it can be run any number of times.

Throws if the node is invalid.

virtual OPENVINO_SUPPRESS_DEPRECATED_START bool evaluate(
    const HostTensorVector& output_values,
    const HostTensorVector& input_values
    ) const

Evaluates the op on input_values putting results in output_values.

Deprecated Use evaluate with ov::Tensor instead

Parameters:

output_values

Tensors for the outputs to compute. One for each result

input_values

Tensors for the inputs. One for each inputs.

Returns:

true if successful

virtual OPENVINO_SUPPRESS_DEPRECATED_END bool has_evaluate() const

Allows to get information about availability of evaluate method for the current operation.