pyabsa.tasks.AspectPolarityClassification.trainer.apc_trainer¶

Classes¶

APCTrainer

Trainer entry point for Aspect Polarity Classification (APC).

Module Contents¶

class pyabsa.tasks.AspectPolarityClassification.trainer.apc_trainer.APCTrainer(config: pyabsa.tasks.AspectPolarityClassification.configuration.apc_configuration.APCConfigManager = None, dataset=None, from_checkpoint: str = None, checkpoint_save_mode: int = ModelSaveOption.SAVE_MODEL_STATE_DICT, auto_device: bool | str = DeviceTypeOption.AUTO, path_to_save=None, load_aug=False)¶

Bases: pyabsa.framework.trainer_class.trainer_template.Trainer

Trainer entry point for Aspect Polarity Classification (APC).

This wrapper connects configuration, datasets and the APC training instructor. After initialization, it triggers the standard training pipeline and exposes load_trained_model() (in the base trainer) to obtain a ready-to-use SentimentClassifier for inference.

training_instructor¶

inference_model_class¶