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
作者你好,我看到你的代码里面有self.lambda_bilinear = [1e-4, 0.0],用于reg_loss之中,这些系数的作用是什么?在EHCF单行为的代码中,这两个系数甚至为0,那么reg_loss不是永远为0吗?对于训练又起着什么样的作用?
The text was updated successfully, but these errors were encountered:
Hi,您好,这个系数是控制l2 regression的正则化系数,防止模型过拟合的。 代码里面加上self.lambda_bilinear是为了让代码的可扩展性更强。其实在我们的模型里面它并不是一个影响大的参数,默认设置为0就可以了。因为我们的模型里面主要通过调节dropout来防止过拟合。
Sorry, something went wrong.
谢谢解答
No branches or pull requests
作者你好,我看到你的代码里面有self.lambda_bilinear = [1e-4, 0.0],用于reg_loss之中,这些系数的作用是什么?在EHCF单行为的代码中,这两个系数甚至为0,那么reg_loss不是永远为0吗?对于训练又起着什么样的作用?
The text was updated successfully, but these errors were encountered: