每个类在python/caffe中用于语义分割实现的IoU [英] IoU for semantic segmentation implementation in python/caffe per class

问题描述

每个像素精度(与边界框不同)实现的每个类的IoU(并集交点)是否有任何建议.我正在使用caffe并设法获得平均IoU，但我很难为每个类的精度进行IoU.如果有人可以指出任何语言的良好实现，我将不胜感激

Is there any recommendable per class IoU(intersection over union) per pixel accuracy(different from bounding box) implementation.I am using caffe and managed to get the mean IoU but i am having difficulty in doing IoU for per class accuracy.I would appreciate a lot if someone could point out a good implementation in any language

推荐答案

到目前为止，这是我迄今为止看到的唯一的具有多个像素标签的紧密语义分段

so far this the only close semantic segmentation with multiple pixel label i ve seen so far here

这篇关于每个类在python/caffe中用于语义分割实现的IoU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IT屋！