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.

Sign up for GitHub

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

Jump to bottom

也出现了loss突然变nan的问题 #32

Open

wangguanhua opened this issue May 1, 2020 · 2 comments

wangguanhua commented May 1, 2020

您好，我这边也出现了loss变nan的问题，我网上搜了一下，发现有一种解决方法方法是添加hook函数（连接如下：https://discuss.pytorch.org/t/ctcloss-performance-of-pytorch-1-0-0/27524），我按照上述方法，定义backward_hook，并在倒数第二行添加crnn.register_backward_hook(backward_hook)代码，您看这样的解决方法在逻辑上是否可行？

InferMaster commented Jun 19, 2021

哪里定义的backward_hook呢，我训练出现损失一百多

WwLuo-1024 commented Feb 22, 2022

哪里定义的backward_hook呢，我训练出现损失一百多

想询问下这个问题你有解决吗？我这边也是损失一直下不去

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment