onnx.shape_inference

infer_shapes

onnx.shape_inference.infer_shapes(model: Union[ModelProto, bytes], check_type: bool = False, strict_mode: bool = False, data_prop: bool = False) ModelProto[source]

Apply shape inference to the provided ModelProto.

Inferred shapes are added to the value_info field of the graph.

If the inferred values conflict with values already provided in the graph, that means that the provided values are invalid (or there is a bug in shape inference), and the result is unspecified.

Parameters:
  • model (Union[ModelProto, bytes], bool, bool, bool) –

  • check_type (bool) – Checks the type-equality for input and output

  • strict_mode (bool) – Stricter shape inference, it will throw errors if any; Otherwise, simply stop if any error

  • data_prop (bool) – Enables data propagation for limited operators to perform shape computation

Returns:

(ModelProto) model with inferred shape information

infer_shapes_path

onnx.shape_inference.infer_shapes_path(model_path: str, output_path: str = '', check_type: bool = False, strict_mode: bool = False, data_prop: bool = False) None[source]

Take model path for shape_inference same as infer_shape; it support >2GB models Directly output the inferred model to the output_path; Default is the original model path