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,最近我想试试部署adder到mobilenet v2网络里,但是遇到了点问题,请问可以帮我解答吗。
我用这里的源码(训练参数对齐)跑resnet,精度和report里差不多。但是当我把mobilenet v2的pointwise层(depthwise要改为群卷积,准备等pointwise没问题再改)替换成adder-conv2d后,精度会有2%的下降。
我没有替换开头和末尾两层。请问精度下降2%会是什么原因呢? 会不会是残差的问题,需要每一层都有残差吗(mobilenet v2若是stride=2或维度变化,就没有残差了)?
The text was updated successfully, but these errors were encountered:
你好,小网络由于本身冗余度就比较低,替换为adder后精度会下降比较多。
Sorry, something went wrong.
感觉可以所有的卷积(包括1x1的)都换成adder,不要一会addernet一会一般卷积,因为addernet是计算1范式距离,但是1x1的卷积算的是余弦距离,混用可能导致不好的结果
No branches or pull requests
您好,最近我想试试部署adder到mobilenet v2网络里,但是遇到了点问题,请问可以帮我解答吗。
我用这里的源码(训练参数对齐)跑resnet,精度和report里差不多。但是当我把mobilenet v2的pointwise层(depthwise要改为群卷积,准备等pointwise没问题再改)替换成adder-conv2d后,精度会有2%的下降。
我没有替换开头和末尾两层。请问精度下降2%会是什么原因呢?
会不会是残差的问题,需要每一层都有残差吗(mobilenet v2若是stride=2或维度变化,就没有残差了)?
The text was updated successfully, but these errors were encountered: