convert_to_mixed_precision

paddle.inference. convert_to_mixed_precision ( model_file: str, params_file: str, mixed_model_file: str, mixed_params_file: str, mixed_precision: PrecisionType, backend: PlaceType, keep_io_types: bool = True, black_list: set[str] = {}, **kwargs: Unpack[_WhiteList] ) → None [source]

Convert a fp32 model to mixed precision model.

Parameters

• model_file – fp32 model file, e.g. inference.pdmodel.

• params_file – fp32 params file, e.g. inference.pdiparams.

• mixed_model_file – The storage path of the converted mixed-precision model.

• mixed_params_file – The storage path of the converted mixed-precision params.

• mixed_precision – The precision, e.g. PrecisionType.Half.

• backend – The backend, e.g. PlaceType.GPU.

• keep_io_types – Whether the model input and output dtype remains unchanged. Default is True.

• black_list – Operators that do not convert precision.

• kwargs – Supported keys including ‘white_list’. - white_list: Operators that do convert precision.