Skip to content

Fix typo in CRF layer argument name #2327

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
wyli merged 2 commits into from
Jun 7, 2021
Merged

Fix typo in CRF layer argument name #2327

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0c1ad15
fix typo in crf args name
masadcv Jun 7, 2021
e2e2dca
Merge branch 'dev' into quick-crf-args-fix
wyli Jun 7, 2021
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
12 changes: 6 additions & 6 deletions monai/networks/blocks/crf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ def __init__(
bilateral_color_sigma: float = 0.5,
gaussian_spatial_sigma: float = 5.0,
update_factor: float = 3.0,
compatability_matrix: Optional[torch.Tensor] = None,
compatibility_matrix: Optional[torch.Tensor] = None,
):
"""
Args:
Expand All @@ -54,7 +54,7 @@ def __init__(
bilateral_color_sigma: standard deviation in color space for the bilateral term.
gaussian_spatial_sigma: standard deviation in spatial coordinates for the gaussian term.
update_factor: determines the magnitude of each update.
compatability_matrix: a matrix describing class compatability, should be NxN where N is the numer of classes.
compatibility_matrix: a matrix describing class compatibility, should be NxN where N is the numer of classes.
"""
super(CRF, self).__init__()
self.iterations = iterations
Expand All @@ -64,7 +64,7 @@ def __init__(
self.bilateral_color_sigma = bilateral_color_sigma
self.gaussian_spatial_sigma = gaussian_spatial_sigma
self.update_factor = update_factor
self.compatability_matrix = compatability_matrix
self.compatibility_matrix = compatibility_matrix

def forward(self, input_tensor: torch.Tensor, reference_tensor: torch.Tensor):
"""
Expand Down Expand Up @@ -98,10 +98,10 @@ def forward(self, input_tensor: torch.Tensor, reference_tensor: torch.Tensor):
# combining filter outputs
combined_output = self.bilateral_weight * bliateral_output + self.gaussian_weight * gaussian_output

# optionally running a compatability transform
if self.compatability_matrix is not None:
# optionally running a compatibility transform
if self.compatibility_matrix is not None:
flat = combined_output.flatten(start_dim=2).permute(0, 2, 1)
flat = torch.matmul(flat, self.compatability_matrix)
flat = torch.matmul(flat, self.compatibility_matrix)
combined_output = flat.permute(0, 2, 1).reshape(combined_output.shape)

# update and normalize
Expand Down