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
作者您好,我在阅读model.py文件的forward()函数时,发现对象Model在实现论文中 ReLU(W ∑r +b) 公式时,使用的是以下顺序的代码:
act1 = self.activation(drop1) # ReLU l = self.Linear(act1) # Linear 这样的顺序,按照我的理解,应该是对 ∑r 进行了一次ReLU,再进行 W · ReLU( ∑r ) + b 的操作,与论文实际所描述的公式不符,但却得到了论文中实验结果所展示的准确率,而我调换这两行代码的顺序之后,准确率降到了80%左右,对此感到很疑惑,能否请您指点一下我的思考是不是存在什么漏洞,确实没想明白这个环节,感谢!
The text was updated successfully, but these errors were encountered:
No branches or pull requests
act1 = self.activation(drop1) # ReLU
l = self.Linear(act1) # Linear
这样的顺序,按照我的理解,应该是对 ∑r 进行了一次ReLU,再进行 W · ReLU( ∑r ) + b 的操作,与论文实际所描述的公式不符,但却得到了论文中实验结果所展示的准确率,而我调换这两行代码的顺序之后,准确率降到了80%左右,对此感到很疑惑,能否请您指点一下我的思考是不是存在什么漏洞,确实没想明白这个环节,感谢!
The text was updated successfully, but these errors were encountered: