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!感谢您的这份工作。 您的resnet.py里,默认rectified_conv=False,在resnest.py创建resnest时也使用默认设置。 我想用resnest101或者resnest269作为主干网络,并使用预训练模型。 请问rectified_conv如果设置为True是否可能会对结果造成不利的影响? 谢谢!
resnet.py
rectified_conv=False
resnest.py
resnest
resnest101
resnest269
rectified_conv
True
The text was updated successfully, but these errors were encountered:
你好,关于 RFConv 可以看这里 https://github.com/zhanghang1989/RFConv
比标准的 conv 会好一些,但是需要重新训练模型
Sorry, something went wrong.
No branches or pull requests
您好!感谢您的这份工作。
您的
resnet.py
里,默认rectified_conv=False
,在resnest.py
创建resnest
时也使用默认设置。我想用
resnest101
或者resnest269
作为主干网络,并使用预训练模型。请问
rectified_conv
如果设置为True
是否可能会对结果造成不利的影响?谢谢!
The text was updated successfully, but these errors were encountered: