-
Notifications
You must be signed in to change notification settings - Fork 567
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
huge loss #594
Comments
你归一化了吗 |
归一化了,我感觉是数据的问题,换了个数据就没问题了 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
when i run voxelmorph with my dataset using NCC loss,a while after,NCC loss up to thousand or bigger,how can i solved it?
output like this
i: 1 loss: -0.092982 sim: -0.092983 grad: 0.000000
i: 2 loss: -0.095556 sim: -0.095647 grad: 0.000023
i: 3 loss: -0.104686 sim: -0.105146 grad: 0.000115
i: 4 loss: -0.179067 sim: -0.180766 grad: 0.000425
i: 5 loss: -0.242327 sim: -0.245312 grad: 0.000746
i: 6 loss: -0.331464 sim: -0.333647 grad: 0.000546
i: 7 loss: -3.075087 sim: -3.082510 grad: 0.001856
i: 8 loss: -80.884193 sim: -80.894211 grad: 0.002504
i: 9 loss: -2233.514404 sim: -2233.535645 grad: 0.005287
i: 10 loss: -0.641073 sim: -0.645906 grad: 0.001208
i: 11 loss: -330.219147 sim: -330.225281 grad: 0.001531
i: 12 loss: -13.687098 sim: -13.695247 grad: 0.002037
i: 13 loss: -0.485161 sim: -0.491218 grad: 0.001514
i: 14 loss: -19.163136 sim: -19.171404 grad: 0.002067
i: 15 loss: -1.049533 sim: -1.056095 grad: 0.001640
The text was updated successfully, but these errors were encountered: