Skip to content
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

代码错误 #63

Open
GuilmK opened this issue Mar 2, 2020 · 3 comments
Open

代码错误 #63

GuilmK opened this issue Mar 2, 2020 · 3 comments

Comments

@GuilmK
Copy link

GuilmK commented Mar 2, 2020

感谢作者提供的优秀代码,在训练过程中我遇到一旦出现Loss小于0.4,运行一次测试集上的测试后,代码就会阻塞,无法继续训练。在对问题进行追踪后,我发现是DataLoader的写法有问题,导致在ubuntu上的多线程阻塞。解决方法:

  1. config.py 将workers数量改为0,该方法会让数据读取变慢
  2. train.py中的train_epoch里
    for i, (images, labels, training_mask) in enumerate(train_loader):
    改成
    for i, mydatas in enumerate(train_loader):
    (images, labels, training_mask) = mydatas
    即可解决
@WenmuZhou
Copy link
Owner

可以提个pr

@1156150793
Copy link

为什么我用作者提供的weight。 AP为0,精确度也好低

@interestingzhuo
Copy link

为什么第二种方法还是会卡住?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants