我想知道在进行训练时是否有办法在PyCaffe上获得top-k错误。
我知道.prototxt文件有top_k参数,但是我可以在PyCaffe上使用它吗?
layer {
name: "accuracy"
type: "Accuracy"
bottom: "..."
bottom: "label"
top: "accuracy"
accuracy_param {
top_k: 5
}
include {
phase: TEST
}
}
答案 0 :(得分:0)
对于想知道我只是发现您需要放置具有不同top-k值的多个精度层的人。这是前三位准确性的示例。
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
}
}