Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Simbert将不能正常使用,除非你安装keras后端:tensorflow .... type object 'AutoRegressiveDecoder' has no attribute 'wraps' #25

Open
le8888e opened this issue May 31, 2022 · 3 comments

Comments

@le8888e
Copy link

le8888e commented May 31, 2022

您好,我运行from nlpcda import Simbert报错:
Simbert将不能正常使用,除非你安装keras后端:tensorflow .... type object 'AutoRegressiveDecoder' has no attribute 'wraps'

环境按requirements.txt和README的要求装好了,具体是:
keras==2.3.1
bert4keras==0.7.7
tensorflow-gpu==1.13.1
requests==2.24.0
numpy==1.18.5
jieba==0.42.1

请问有什么解决方法?谢谢!

@dyx-max
Copy link

dyx-max commented Jun 9, 2022

同问
readme里的环境根本不能用

@xu-song
Copy link

xu-song commented Dec 16, 2022

1

@Danvae
Copy link

Danvae commented Sep 5, 2023

依赖包安装版本:
keras==2.3.1
bert4keras==0.7.7
tensorflow==1.13.1
经过调试,发现可以将 tools.simbert.generator.py里面的 @AutoRegressiveDecoder.wraps('probas') 改成 @AutoRegressiveDecoder.set_rtype('probas'),可以成功运行。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants