-
Notifications
You must be signed in to change notification settings - Fork 115
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Oral的paper代码写的这么差,头次见 #63
Comments
regression brance侧无法trace到梯度是因为loss字典里有个Key少了个s,对不上,所以源代码压根没用到regression loss item,可以改一下。 |
都这样,没几个人解决issue的,诶。 |
根本看不懂 |
请问具体在哪里? 可以提供一下修改后的版本吗 |
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
如题,请原谅我的直白,好歹是个oral的paper,P2PNet所公开的代码真的一塌糊涂,错误的地方很多,包括频繁新建字典,部分字典keys都是错误的,导致部分判断后其实是个空字典(这也是为什么没法支持ddp的原因,regression branch侧无法trace到梯度),无用的类init也很多,尤其是模型测的,项目也没有人在维护,所提issues没人解决,非常糟糕,第一次见这么敷衍糟糕的ICCV oral paper开源代码.
The text was updated successfully, but these errors were encountered: