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

Derivative bugs #4

Closed

weepiess opened this issue May 21, 2021 · 1 comment

weepiess commented May 21, 2021

Hi,

for l in range(L):
      I = torch.t(torch.reshape(X[l], (3, -1)))
      II = torch.pow(I, 2)
      if self.intensity_scale:
        Iy = torch.unsqueeze(torch.sqrt(II[:, 0] + II[:, 1] + II[:, 2]), dim=1)
      else:
        Iy = 1

I found a bug here:

torch.sqrt(II[:, 0] + II[:, 1] + II[:, 2]), dim=1)

sqrt is not derivable at point 0
Therefore, it is better to change to this:

torch.sqrt(II[:, 0] + II[:, 1] + II[:, 2]+ EPS), dim=1)

Owner

mahmoudnafifi commented May 26, 2021

Thanks for catching this. Fixed.

mahmoudnafifi closed this as completed

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