自定义模型 训练 保存 再倒入使用报错

[xrzlizheng]

File ".\getvec.py", line 86, in pro_model =Double_BiLSTM_Model.load_model('double_model') File "d:\anaconda3\lib\site-packages\kashgari\tasks\abs_task_model.py", line 101, in load_model model = load_data_object(model_config) File "d:\anaconda3\lib\site-packages\kashgari\utils\serialize.py", line 25, in load_data_object obj: Any = pydoc.locate(module_name)(**data['config'], **kwargs) # type: ignore TypeError: 'NoneType' object is not callable

[BrikerMan]

2.0.2 版本应该修复了该问题，可以测试一下～

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[AnitaSherry]

仍然报错

[pineapple-427]

我也遇到了类似的问题，我的解决方法是将自定义的模型放到kashgari.tasks.classification 中，重新导入模型解决了此问题。不知有没有别的load_model()方法.

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.