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
您好,我可能对量化这方面的工作还不是很了解,我对您的这个工作有一个简单的疑问。请问为什么您展示的量化后的模型会超过原始全精度模型的指标呢?期待您的回复。
The text was updated successfully, but these errors were encountered:
量化模型的训练load了pretrained全精度模型,之后再次训练300回合。可以粗略地认为量化模型训练了600回合(2x),所以有可能会超过全精度的效果。
Sorry, something went wrong.
这个解释未免太过牵强了
这种现象很常见。除了作者所讲述的原因,quantization也起到了regularization的作用。原网络可能overfitting了,所以quantization之后的accuracy会上升一些。
No branches or pull requests
您好,我可能对量化这方面的工作还不是很了解,我对您的这个工作有一个简单的疑问。请问为什么您展示的量化后的模型会超过原始全精度模型的指标呢?期待您的回复。
The text was updated successfully, but these errors were encountered: