happynear / happynear/caffe-windows
关于全连接层Forward部分中(114~117行代码)weight的归一化问题
Open
- Dominant language
- C++
- Stars
- 1.3k
- Forks
- 637
- PR merge metrics
- No merged PRs in 30d
Description
https://github.com/happynear/caffe-windows/blob/2e9ade3075d86321342966ed0aa2961031a06daf/src/caffe/layers/inner_product_layer.cpp#L114-L117
@happynear 如题所示，貌似在处理weight归一化时只考虑了非transpose的情况(此时weight的维数为：NxK)，但是weight进行transpose的情况(此时weight的维数为：KxN)好像不能用相同的代码进行处理了。
weight归一化不应该是对每个(共N个，为输出类别数目)长度为K的weight向量进行归一化吗？？？
Contributor guide
Assessment
This issue has not been assessed yet.