如何在训练阶段获得PyCaffe上的Top-k准确率？

Question

我想知道是否有一种方法可以在进行训练阶段时获得PyCaffe上的top-k错误。

我知道.prototxt文件有top_k参数，但是有什么方法可以在PyCaffe上使用它吗？

layer {
  name: "accuracy"
  type: "Accuracy"
  bottom: "..."
  bottom: "label"
  top: "accuracy"
  accuracy_param {
    top_k: 5
  }
  include {
    phase: TEST
  }
}

Answer 1

对于任何想知道的人，我只是发现你需要用不同的top-k数字放置多个精确层。这是一个前3名准确率的例子。

layer {
    name: "accuracy1"
    type: "Accuracy"
    bottom: "score"
    bottom: "label"
    top: "accuracy1"
    include {
      phase: TEST
    }
  }
  layer {
    name: "accuracy2"
    type: "Accuracy"
    bottom: "score"
    bottom: "label"
    top: "accuracy2"
    accuracy_param {
        top_k: 2
    }
    include {
      phase: TEST
    }
  }
  layer {
    name: "accuracy3"
    type: "Accuracy"
    bottom: "score"
    bottom: "label"
    top: "accuracy3"
    accuracy_param {
        top_k: 3
    }
    include {
      phase: TEST
    }
  }