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.

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

Train the expert discriminator to report errors #68

Closed
shengzewen opened this issue Aug 17, 2023 · 4 comments
Closed

Train the expert discriminator to report errors #68

shengzewen opened this issue Aug 17, 2023 · 4 comments

Comments

@shengzewen
Copy link

Run color_syncnet_train.py on the server, and in the middle of running, an error occurs:
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
RuntimeError: cuDNN error: CUDNN_STATUS_MAPPING_ERROR
What is the reason?
@shengzewen
Copy link
Author

我更改了PReLU为ReLU后，虽然color_syncnet_train.py能训练起来，但是损失值一直在0.7左右降不下去，这是为什么

@fordeep3d
Copy link

我更改了PReLU为ReLU后，虽然color_syncnet_train.py能训练起来，但是损失值一直在0.7左右降不下去，这是为什么

我也是降不下去，模型结构有问题吗

@shengzewen
Copy link
Author

很有可能是因为数据预处理出问题了，你可以看看 #21 。我按照作者的要求处理后，损失值下降了

@fordeep3d
Copy link

很有可能是因为数据预处理出问题了，你可以看看 #21 。我按照作者的要求处理后，损失值下降了

非常感谢

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@shengzewen @fordeep3d