onnx.numpy_helper

array

onnx.numpy_helper.to_array(tensor: onnx.onnx_ml_pb2.TensorProto, base_dir: str = '') numpy.ndarray[source]

Converts a tensor def object to a numpy array.

Inputs:

tensor: a TensorProto object. base_dir: if external tensor exists, base_dir can help to find the path to it

Returns

the converted array.

Return type

arr

onnx.numpy_helper.from_array(arr: numpy.ndarray, name: Optional[str] = None) onnx.onnx_ml_pb2.TensorProto[source]

Converts a numpy array to a tensor def.

Inputs:

arr: a numpy array. name: (optional) the name of the tensor.

Returns

the converted tensor def.

Return type

tensor_def

sequence

onnx.numpy_helper.to_list(sequence: onnx.onnx_data_pb2.SequenceProto) List[Any][source]

Converts a sequence def to a Python list.

Inputs:

sequence: a SequenceProto object.

Returns

the converted list.

Return type

lst

onnx.numpy_helper.from_list(lst: List[Any], name: Optional[str] = None, dtype: Optional[int] = None) onnx.onnx_data_pb2.SequenceProto[source]

Converts a list into a sequence def.

Inputs:

lst: a Python list name: (optional) the name of the sequence. dtype: (optional) type of element in the input list, used for specifying

sequence values when converting an empty list.

Returns

the converted sequence def.

Return type

sequence

dictionary

onnx.numpy_helper.to_dict(map: onnx.onnx_data_pb2.MapProto) numpy.ndarray[source]

Converts a map def to a Python dictionary.

Inputs:

map: a MapProto object.

Returns

the converted dictionary.

Return type

dict

onnx.numpy_helper.from_dict(dict: Dict[Any, Any], name: Optional[str] = None) onnx.onnx_data_pb2.MapProto[source]

Converts a Python dictionary into a map def.

Inputs:

dict: Python dictionary name: (optional) the name of the map.

Returns

the converted map def.

Return type

map

optional

onnx.numpy_helper.to_optional(optional: onnx.onnx_data_pb2.OptionalProto) Optional[Any][source]

Converts an optional def to a Python optional.

Inputs:

optional: an OptionalProto object.

Returns

the converted optional.

Return type

opt

onnx.numpy_helper.from_optional(opt: Optional[Any], name: Optional[str] = None, dtype: Optional[int] = None) onnx.onnx_data_pb2.OptionalProto[source]

Converts an optional value into a Optional def.

Inputs:

opt: a Python optional name: (optional) the name of the optional. dtype: (optional) type of element in the input, used for specifying

optional values when converting empty none. dtype must be a valid OptionalProto.DataType value

Returns

the converted optional def.

Return type

optional

tools

onnx.numpy_helper.convert_endian(tensor: onnx.onnx_ml_pb2.TensorProto) None[source]

call to convert endianess of raw data in tensor. @params TensorProto: TensorProto to be converted.

onnx.numpy_helper.combine_pairs_to_complex(fa: Sequence[int]) Sequence[numpy.complex64][source]