xhhlll

The problem that training requires 2000 epochs to converge

1

In my own training set, it only takes 50 epochs to train yolact on mmdetection to achieve mAP=85, but it takes 2000 epochs to get the same accuracy in the...

为什么在mmdetection上训练yolact ,epoch在100左右就收敛，而原作者代码需要2000个epoch（note:并不是2000个迭代）

运行setup.py出现Error compiling objects for extension

1

作者您好！ 我运行python setup.py develop时候出现,运行环境cuda11.0 python3.6 pytorch1.7.1 .请问怎么解决呢？ running develop running egg_info creating focalloss.egg-info writing focalloss.egg-info/PKG-INFO writing dependency_links to focalloss.egg-info/dependency_links.txt writing top-level names to focalloss.egg-info/top_level.txt writing manifest file 'focalloss.egg-info/SOURCES.txt' reading manifest...