版权声明:本文为博主原创文章,转载请注明出处. https://blog.csdn.net/weixin_35653315/article/details/72715367
还是在SSD中发现的:
layer {
name: "conv4_3_norm"
type: "Normalize"
bottom: "conv4_3"
top: "conv4_3_norm"
norm_param {
across_spatial: false
scale_filler {
type: "constant"
value: 20.0
}
channel_shared: false
}
}
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
有两个问题:
1. Normalize
层做了什么?
2. 为什么只对conv4_3
进行normalize 操作?
Normalize Layer
Normalize 操作很简单:给定一个向量xx维向量上操作。
为什么只对conv4_3
进行norm操作?
https://github.com/weiliu89/caffe/issues/241
That was discovered in my other paper (ParseNet) that conv4_3 has different scale from other layers. That is why I add L2 normalization for conv4_3 only.