flytekitplugins.onnxpytorch.PyTorch2ONNXConfig#

class flytekitplugins.onnxpytorch.PyTorch2ONNXConfig(args, export_params=True, verbose=False, training=<TrainingMode.EVAL: 0>, opset_version=9, input_names=<factory>, output_names=<factory>, operator_export_type=None, do_constant_folding=False, dynamic_axes=<factory>, keep_initializers_as_inputs=None, custom_opsets=<factory>, export_modules_as_functions=False)#

PyTorch2ONNXConfig is the config used during the pytorch to ONNX conversion.

Parameters:
  • args (Tuple | Tensor) – The input to the model.

  • export_params (bool) – Whether to export all the parameters.

  • verbose (bool) – Whether to print description of the ONNX model.

  • training (TrainingMode) – Whether to export the model in training mode or inference mode.

  • opset_version (int) – The ONNX version to export the model to.

  • input_names (List[str]) – Names to assign to the input nodes of the graph.

  • output_names (List[str]) – Names to assign to the output nodes of the graph.

  • operator_export_type (OperatorExportTypes | None) – How to export the ops.

  • do_constant_folding (bool) – Whether to apply constant folding for optimization.

  • dynamic_axes (Dict[str, Dict[int, str]] | Dict[str, List[int]]) – Specify axes of tensors as dynamic.

  • keep_initializers_as_inputs (bool | None) – Whether to add the initializers as inputs to the graph.

  • custom_opsets (Dict[str, int]) – A dictionary of opset domain name and version.

  • export_modules_as_functions (bool | set[Type]) – Whether to export modules as functions.

Methods

classmethod from_dict(kvs, *, infer_missing=False)#
Parameters:

kvs (dict | list | str | int | float | bool | None)

Return type:

A

classmethod from_json(s, *, parse_float=None, parse_int=None, parse_constant=None, infer_missing=False, **kw)#
Parameters:

s (str | bytes | bytearray)

Return type:

A

classmethod schema(*, infer_missing=False, only=None, exclude=(), many=False, context=None, load_only=(), dump_only=(), partial=False, unknown=None)#
Parameters:
Return type:

SchemaF[A]

to_dict(encode_json=False)#
Return type:

Dict[str, dict | list | str | int | float | bool | None]

to_json(*, skipkeys=False, ensure_ascii=True, check_circular=True, allow_nan=True, indent=None, separators=None, default=None, sort_keys=False, **kw)#
Parameters:
Return type:

str

Attributes

dataclass_json_config = None
do_constant_folding: bool = False
export_modules_as_functions: bool | set[Type] = False
export_params: bool = True
keep_initializers_as_inputs: bool | None = None
operator_export_type: OperatorExportTypes | None = None
opset_version: int = 9
training: TrainingMode = <TrainingMode.EVAL: 0>
verbose: bool = False
args: Tuple | Tensor
input_names: List[str]
output_names: List[str]
dynamic_axes: Dict[str, Dict[int, str]] | Dict[str, List[int]]
custom_opsets: Dict[str, int]