-
Notifications
You must be signed in to change notification settings - Fork 201
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
why loss is nan #126
Comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi,
I have input data between 0 and 1, and at the first several epoches, the loss is normal, but then it turned to nan. I cannot find the errors,can you help me?
in base_dataset.py
transform_list += [transforms.ToTensor(), # normalized to [0, 1] transforms.Normalize((0, 0, 0), (1, 1, 1))]
in util.py line 18
image_numpy = np.transpose(image_numpy, (1, 2, 0)) * 255.0
The text was updated successfully, but these errors were encountered: