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,论文中您在Unconditional Image Generation和Single Image Super-Resolution这两个任务上为netML设置了不同的output embedding(分别为10和32),如何根据自己的任务来选择合适的output embedding呢?比如Image-to-Image translation这样的任务。
The text was updated successfully, but these errors were encountered:
这个问题我们也没有确切的答案,在一定范围内应该都是合理的。我们的一个经验是对于分布复杂的数据用高一些的维度可能更有利,对于分布简单的数据则不需要
Sorry, something went wrong.
好的,感谢。另外,使用MVM进行训练,流行匹配的loss是下降的,度量学习部分的loss呈上升趋势,这是否意味着训练失败了?
训练稳定的话mm_loss的确在下降,ml_loss在一定区间内振荡,如果不是的话训练可能就失败了,不过这是稳定训练的必要条件不是充分条件
No branches or pull requests
作者您好,论文中您在Unconditional Image Generation和Single Image Super-Resolution这两个任务上为netML设置了不同的output embedding(分别为10和32),如何根据自己的任务来选择合适的output embedding呢?比如Image-to-Image translation这样的任务。
The text was updated successfully, but these errors were encountered: