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,请问一下FPGM剪枝时将卷积层的部分滤波器权重和梯度都设为0,因此不会进行梯度更新进而更新这些置0的滤波器,而在模型训练时,每次剪枝都是相同的滤波器,这些滤波器的权重和梯度都不在更新,只有没有置0的滤波器在更新。而硬剪枝是直接剪掉这些滤波器获得一个小网络,之后对这个小网络进行微调,这两者有什么不同?
The text was updated successfully, but these errors were encountered:
https://github.com/he-y/filter-pruning-geometric-median/issues/9#issuecomment-504809258可以再解释一下吗
Sorry, something went wrong.
No branches or pull requests
作者您好,请问一下FPGM剪枝时将卷积层的部分滤波器权重和梯度都设为0,因此不会进行梯度更新进而更新这些置0的滤波器,而在模型训练时,每次剪枝都是相同的滤波器,这些滤波器的权重和梯度都不在更新,只有没有置0的滤波器在更新。而硬剪枝是直接剪掉这些滤波器获得一个小网络,之后对这个小网络进行微调,这两者有什么不同?
The text was updated successfully, but these errors were encountered: