由网友(眼里开桃花)分享简介：我试图用朱古力来实现施罗夫，Kalenichenko和菲尔宾FaceNet描述三重损失：一个统一嵌入的人脸识别和群集，2015年。I am trying to use caffe to implement triplet loss described in Schroff, Kalenichenko and Phil...

我试图用朱古力来实现施罗夫，Kalenichenko和菲尔宾FaceNet描述三重损失：一个统一嵌入的人脸识别和群集，2015年。

I am trying to use caffe to implement triplet loss described in Schroff, Kalenichenko and Philbin "FaceNet: A Unified Embedding for Face Recognition and Clustering", 2015.

我是新来这个所以如何计算梯度反向传播？

I am new to this so how to calculate the gradient in back propagation?

推荐答案

我假设你定义了损耗层为

I assume you define the loss layer as

layer {
  name: "tripletLoss"
  type: "TripletLoss"
  bottom: "anchor"
  bottom: "positive"
  bottom: "negative"
  ...
}

现在你需要计算梯度WRT每个底S的：

Now you need to compute a gradient w.r.t each of the "bottom"s:

请参阅comment纠正上一届。