最近正在阅读Mask rcnn一个变种的源码,遇到了一个问题,就是在计算deltas
,也就是bbox的偏移量的时候,总是会用到参数RPN_BBOX_STD_DEV
或者BBOX_STD_DEV
进行或乘或除的计算,一直不知道这个的作用是什么,搜索了一下貌似没有看到很好的中文解释,在github的issue上看到了很好的解释,索性搬过来
这个是github地址:https://github.com/matterport/Mask_RCNN/issues/270
问题描述
This is really great project - love the level of comments, the working notebooks, and the simple shapes dataset…all makes it exceptionally easy to read.
One thing that is not clear - In the RPN proposal layer the deltas are multiplied by BBOX_STD_DEV. There was a previous issue asking about this #85. The answer given refers to fastrcnn paper section on normalising the regression targets for the loss function.
However this is applied after the RPN loss function; and before the bbox spec is normalised to 0-1 range. Also two of the delta numbers are log(delta). I can possibly envisage that