onnx_ir.schemas

See Writing transformation passes for using schema and opset requirements in transformation pipelines.

The onnx_ir.schemas module provides classes for representing operator signatures and their parameters. These classes are useful for introspecting operator definitions and validating operator usage.

OpSignature

The OpSignature class represents the schema for an ONNX operator, including its inputs, outputs, and attributes.

class onnx_ir.schemas.OpSignature(domain, name, overload, params, outputs, since_version=1)

Schema for an operator.

Parameters:

• domain (str)

• name (str)

• overload (str)

• params (Sequence[Parameter | AttributeParameter])

• outputs (Sequence[Parameter])

• since_version (int)

domain

Domain of the operator. E.g. “”.

Type:

str

name

Name of the operator. E.g. “Add”.

Type:

str

overload

Overload name of the operator.

Type:

str

params

Input parameters. When the op is an ONNX function definition, the order is according to the function signature. This mean we can interleave ONNX inputs and ONNX attributes in the list.

Type:

collections.abc.Sequence[onnx_ir.schemas.Parameter | onnx_ir.schemas.AttributeParameter]

outputs

Output parameters.

Type:

collections.abc.Sequence[onnx_ir.schemas.Parameter]

since_version

The version of the operator set. E.g. 1.

Type:

int

property attributes: Sequence[AttributeParameter]

The attribute parameters.

classmethod from_op_schema(op_schema)

Produce an OpSignature from an ONNX OpSchema.

Parameters:

op_schema (OpSchema)

Return type:

OpSignature

get(name, default=None)

Return a parameter by name, or default when missing.

Parameters:

• name (str)

• default (Parameter | AttributeParameter | None)

Return type:

Parameter | AttributeParameter | None

property inputs: Sequence[Parameter]

The input parameters.

Parameter

The Parameter class represents a formal input parameter of an operator.

class onnx_ir.schemas.Parameter(name, type_constraint, required, variadic, homogeneous=True, min_arity=1, default=_EMPTY_DEFAULT)

A formal parameter of an operator.

Parameters:

• name (str)

• type_constraint (TypeConstraintParam)

• required (bool)

• variadic (bool)

• homogeneous (bool)

• min_arity (int)

• default (Any)

has_default()

Return True if the parameter has a default value.

Return type:

bool

is_attribute()

Return False because this is an input/output parameter.

Return type:

bool

is_param()

This parameter is an ONNX input or output parameter, as opposed to an ONNX attribute parameter.

Return type:

bool

AttributeParameter

The AttributeParameter class represents an attribute parameter in the operator signature.

class onnx_ir.schemas.AttributeParameter(name, type, required, default=None)

A parameter in the function signature that represents an ONNX attribute.

Parameters:

• name (str)

• type (AttributeType)

• required (bool)

• default (Attr | None)

has_default()

Return True if the attribute parameter has a default value.

Return type:

bool

is_attribute()

This parameter is an ONNX attribute parameter, as opposed to an ONNX input or output parameter.

Return type:

bool

is_param()

Return False because this parameter models an attribute.

Return type:

bool

TypeConstraintParam

The TypeConstraintParam class represents type constraints for parameters, specifying which types are allowed.

class onnx_ir.schemas.TypeConstraintParam(name, allowed_types, description='')

Type constraint for a parameter.

Parameters:

• name (str)

• allowed_types (frozenset[TypeProtocol])

• description (str)

name

Name of the parameter. E.g. “TFloat”

Type:

str

allowed_types

Allowed types for the parameter.

Type:

frozenset[onnx_ir.TypeProtocol]

description

Human-readable description of the type constraint.

Type:

str