MMDeepSpeedEngineWrapper¶ class mmengine._strategy.deepspeed.MMDeepSpeedEngineWrapper(*, model, inputs_to_half=None)[source]¶ Parameters: model (deepspeed.DeepSpeedEngine) – inputs_to_half (List[int | str] | None) – test_step(data)[source]¶ Gets the predictions of module during testing process. Parameters: data (dict or tuple or list) – Data sampled from dataset. Returns: The predictions of given data. Return type: list val_step(data)[source]¶ Gets the prediction of module during validation process. Parameters: data (dict or tuple or list) – Data sampled from dataset. Returns: The predictions of given data. Return type: list