Skip to content

Assert RAFT input resolution is 128 x 128 or higher #7339

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

Merged
NicolasHug merged 9 commits into from
May 11, 2023
Merged

Assert RAFT input resolution is 128 x 128 or higher #7339

Changes from 3 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
d8b4d0e
Check that input resolution is 128 x 128 or higher
ChristophReich1996 Feb 25, 2023
8e2358f
Fix error message
ChristophReich1996 Feb 27, 2023
9d42a8f
formatting
NicolasHug Feb 27, 2023
930fcf7
Check resolution at the feature level w/ corr_block parameters
ChristophReich1996 Feb 27, 2023
ba2d0c2
Merge branch 'main' into main
NicolasHug May 10, 2023
ca2134d
Move min res check to build_pyramid and simplify
ChristophReich1996 May 10, 2023
3f353ec
Update logic
NicolasHug May 11, 2023
1cbcada
lint
NicolasHug May 11, 2023
949c0b0
Merge branch 'main' into main
NicolasHug May 11, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions torchvision/models/optical_flow/raft.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -475,6 +475,10 @@ def forward(self, image1, image2, num_flow_updates: int = 12):
raise ValueError(f"input images should have the same shape, instead got ({h}, {w}) != {image2.shape[-2:]}")
if not (h % 8 == 0) and (w % 8 == 0):
raise ValueError(f"input image H and W should be divisible by 8, instead got {h} (h) and {w} (w)")
if h < 128 or w < 128:
raise ValueError(
f"input image H and W should be equal to or larger than 128, instead got {h} (h) and {w} (w)"
)

fmaps = self.feature_encoder(torch.cat([image1, image2], dim=0))
fmap1, fmap2 = torch.chunk(fmaps, chunks=2, dim=0)
Expand Down