跑faster rcnn,我已经修改了配置文件中的类的数量,训练时仍会报和COCO 的80类不匹配 #9813
Unanswered
FengRongYue
asked this question in
Q&A
Replies: 2 comments
-
dataset的config文件中也需要改一下类别名。 |
Beta Was this translation helpful? Give feedback.
0 replies
-
改完model中的类别数 还有mmdet下的coco.py 以及core下的evaluation中的class_name.py中的类别数量 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
报错


我的配置文件
网上的解决办法都是改源码什么的,感觉完全不靠谱啊,我觉得一定是我配置文件写的不对,但是不知道哪里不对。fasterrcnn的配置文件里面我只找到了一个地方该类的数量的。
Beta Was this translation helpful? Give feedback.
All reactions