We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
readme中说 那些pretrained 文件放在 base-uncased. 需要在base.py 中改掉 config 里的路径base-chinese
给的cnews,如果默认 gbk则不能读入,需要 在open(raw_data_path,'r')中加入,encoding='utf-8' 。这个应该是本地默认编码问题,不大
运行train步骤,load预训练权重会提示 在 bert_for_multi_class.py", line 11 init_weights() takes 1 positional argument but 2 were given 找了一会,应该是 把self.apply(self.init_weights) 改为 self.apply(self._init_weights) 不过这样也还是没有用到预训练权重bin文件,默认还是用的未训练的权重 把self.apply(self.init_weights) 注释掉,也可以略过加载预训练权重部分,不会报错
暂时发现如上这些
The text was updated successfully, but these errors were encountered:
No branches or pull requests
readme中说 那些pretrained 文件放在 base-uncased.
需要在base.py 中改掉 config 里的路径base-chinese
给的cnews,如果默认 gbk则不能读入,需要 在open(raw_data_path,'r')中加入,encoding='utf-8' 。这个应该是本地默认编码问题,不大
运行train步骤,load预训练权重会提示
在 bert_for_multi_class.py", line 11
init_weights() takes 1 positional argument but 2 were given
找了一会,应该是 把self.apply(self.init_weights) 改为 self.apply(self._init_weights)
不过这样也还是没有用到预训练权重bin文件,默认还是用的未训练的权重
把self.apply(self.init_weights) 注释掉,也可以略过加载预训练权重部分,不会报错
暂时发现如上这些
The text was updated successfully, but these errors were encountered: