本文介绍了Caffe的第二个“最高"排名“准确性"层的的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!
问题描述
查看 层,我看到该层有第二个输出/顶部"的选项.
第二个输出产生什么?
Looking at the code of "Accuracy"
layer, I see there is an option for a second output/"top" for this layer.
What does this second output produce?
推荐答案
查看 accuracy_layer.hpp
,其中定义了该层的输出数量,有以下注释:
Looking at accuracy_layer.hpp
, where the number of outputs for the layer are defined, there's this comment:
// If there are two top blobs, then the second blob will contain
// accuracies per class.
因此,"Accuracy"
层的第二个"top"
仅报告每个类的准确性.
So, the second "top"
of the "Accuracy"
layer simply reports per-class accuracies.
只是作为层精度的附带说明,所报告的精度通过有效"预测的数量进行了标准化(与对损耗层使用normalization: VALID
相同).
Just as a side note for layer Accuracy, the reported Accuracy is normalized by the number of "valid" predictions (same as using normalization: VALID
for loss layers).
这篇关于Caffe的第二个“最高"排名“准确性"层的的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持!