mmedit.apis.inferencers.video_interpolation_inferencer

Module Contents

Classes

VideoInterpolationInferencer

inferencer that predicts with video interpolation models.

class mmedit.apis.inferencers.video_interpolation_inferencer.VideoInterpolationInferencer(config: Union[mmedit.utils.ConfigType, str], ckpt: Optional[str], device: Optional[str] = None, extra_parameters: Optional[Dict] = None, seed: int = 2022, **kwargs)

Bases: mmedit.apis.inferencers.base_mmedit_inferencer.BaseMMEditInferencer

inferencer that predicts with video interpolation models.

func_kwargs

extra_parameters

preprocess(video: mmedit.apis.inferencers.base_mmedit_inferencer.InputsType) → Dict

Process the inputs into a model-feedable format.

参数

video (InputsType) – Video to be interpolated by models.

返回

Video to be interpolated by models.

返回类型

video(InputsType)

forward(inputs: mmedit.apis.inferencers.base_mmedit_inferencer.InputsType, result_out_dir: mmedit.apis.inferencers.base_mmedit_inferencer.InputsType = '') → mmedit.apis.inferencers.base_mmedit_inferencer.PredType

Forward the inputs to the model.

参数

• inputs (InputsType) – Input video directory.

• result_out_dir (str) – Output directory of video. Defaults to ‘’.

返回

Result of forwarding

返回类型

PredType

visualize(preds: mmedit.apis.inferencers.base_mmedit_inferencer.PredType, result_out_dir: str = '') → List[numpy.ndarray]

Visualize is not needed in this inferencer.

postprocess(preds: mmedit.apis.inferencers.base_mmedit_inferencer.PredType, imgs: Optional[List[numpy.ndarray]] = None) → Union[mmedit.apis.inferencers.base_mmedit_inferencer.ResType, Tuple[mmedit.apis.inferencers.base_mmedit_inferencer.ResType, numpy.ndarray]]

Postprocess is not needed in this inferencer.