-
Notifications
You must be signed in to change notification settings - Fork 2
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
如何引用在半监督语义分割 #2
Comments
Thank you for your interest in our work. Ideally, you only need to replace:
with something like:
However, there are several important considerations when using segmentation losses in general. For more details, please refer to the FAQs. For the loss weight, please refer to here as well as the configs. |
非常感谢您的回复,我尝试把该函数JDTLoss导入到我的代码中,并按照您的建议修改了原有的交叉熵损失,但效果下降明显,我猜测我的操作有问题。README中的意思是只需要把JDTLoss导入到我的代码中就可以了吗?其他的文件是否需要导入?希望您解答,非常感谢! (另外我在半监督语义分割的训练中使用的是两个GPU。) |
你原来是只有交叉熵损失没有其他的损失对吧?你每个GPU上能装几张照片? 半监督经常会把几个loss叠在一起,一般是这样:
你只需要把JDTLoss导入,变成下面这样:
如果效果没有提升的话,我建议最需要调的参数应该是epochs,建议看一下FAQs。 |
epochs已改为原有的一半,没有其他损失,单个GPU batchsize是2。 非常感谢您的解答,我会继续尝试。 |
作者您好,感谢您提供的优秀工作,我希望将该损失使用在我所做的半监督语义分割中,我的论文中目前所使用的交叉熵损失,请问我按照README中直接引用JDTLoss(from losses.jdt_loss import JDTLoss)即可吗?是否有其他需要注意的情况?
另外在论文中您提到和交叉熵最好的组合是0.75,0.25,请问这一部分在代码的哪里体现?期待您的回答,谢谢!
The text was updated successfully, but these errors were encountered: