DataType¶

class onnx_ir.DataType(value)¶

Enum for the data types of ONNX tensors, defined in onnx.TensorProto.

classmethod from_numpy(dtype: dtype) → DataType[source]¶

Returns the ONNX data type for the numpy dtype.

Raises:: TypeError – If the data type is not supported by ONNX.

classmethod from_short_name(short_name: str) → DataType[source]¶

Returns the ONNX data type for the short name.

Raises:: TypeError – If the short name is not available for the data type.

property itemsize: float¶: Returns the size of the data type in bytes.

numpy() → dtype[source]¶

Returns the numpy dtype for the ONNX data type.

Raises:: TypeError – If the data type is not supported by numpy.

short_name() → str[source]¶

Returns the short name of the data type.

The short name is a string that is used to represent the data type in a more compact form. For example, the short name for DataType.FLOAT is “f32”. To get the corresponding data type back, call from_short_name on a string.

Naming reference: https://github.com/pytorch/pytorch/blob/4bead7b85ea4160243c74109e0ce9bb80686d016/torch/utils/_dtype_abbrs.py

Raises:: TypeError – If the short name is not available for the data type.

is_floating_point() → bool[source]¶: Returns True if the data type is a floating point type.

UNDEFINED = 0¶

FLOAT = 1¶

UINT8 = 2¶

INT8 = 3¶

UINT16 = 4¶

INT16 = 5¶

INT32 = 6¶

INT64 = 7¶

STRING = 8¶

BOOL = 9¶

FLOAT16 = 10¶

DOUBLE = 11¶

UINT32 = 12¶

UINT64 = 13¶

COMPLEX64 = 14¶

COMPLEX128 = 15¶

BFLOAT16 = 16¶

FLOAT8E4M3FN = 17¶

FLOAT8E4M3FNUZ = 18¶

FLOAT8E5M2 = 19¶

FLOAT8E5M2FNUZ = 20¶

UINT4 = 21¶

INT4 = 22¶

FLOAT4E2M1 = 23¶