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.

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

Pytorch17 complex fft #11

Open
wants to merge 4 commits into
base: master
Choose a base branch
from

Conversation

vdutell
Copy link

@vdutell vdutell commented May 5, 2022

No description provided.

@@ -156,23 +160,17 @@ def _build_levels(self, lodft, log_rad, angle, Xrcos, Yrcos, height):
for b in range(self.nbands):

anglemask = pointOp(angle, Ycosn, self.Xcosn + np.pi*b/self.nbands)
anglemask = anglemask[None,:,:,None] # for broadcasting
anglemask = anglemask[None,:,:] # for broadcasting
anglemask = torch.from_numpy(anglemask).float().to(self.device)

# Bandpass filtering
banddft = lodft * anglemask * himask
Copy link

@ChairManMeow-SY ChairManMeow-SY May 30, 2022

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should line 167 be:

banddft=(-1j)**order*lodft *anglemask * himask ?

As the code here

@ChairManMeow-SY
Copy link

I'm so confusing for line 91:
height, width = im_batch.shape[2], im_batch.shape[1]

As the input is in the shape [N, C, H, W], the squeezed im_batch should be in [N, H, W].....

Thus
height = im_batch.shape[1]
and
width = im_batch.shape[2] ?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants