Line by line explanation of yolox source code of anchor free series network (7) -- obj in head_ loss、Cls_ Loss and reg_ Calculation and reverse transmission of loss I

Whole YOLOX The learning of the source code must be in the following order to be connected as a whole ：Backbone->FPN->Head->-> Data read into the source code -> Data enhancement source code ->loss Calculation source code ->simOTA Source code ->demo.py Script ->train.py Script . And this series of blog posts also follow this order to analyze the code line by line . Note that line by line , Include python grammar ,tensor Role and application of dimension and line by line code . In fact, there is no mystery about the network structure , It's a stack of modules , There is no reason why you can modify any module . After reading this series, I can do anything about any network structure at will , It's not just limited to one caller .

This article is about YOLOX in Head Of loss Calculation and back transmission , yes YOLOX The core part . There are few pictures in this section , There is enough code . First, position the code to yolox\models\yolo_head.py in Orange frame , Let's start here ：