Skip to content

GitLab

"classification/git@developer.sourcefind.cn:OpenDAS/dcnv3.git" did not exist on "fe6cdd2ed0f980afcc832847294f6654f6a328dc"
Commit f03be78f authored by Gustaf Ahdritz's avatar Gustaf Ahdritz
Browse files

Remove a pair of outdated comments

parent 428d90ce
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 4 deletions
openfold/utils/loss.py
View file @ f03be78f
...@@ -120,9 +120,6 @@ def compute_fape( ...@@ -120,9 +120,6 @@ def compute_fape(
return normed_error return normed_error
# DISCREPANCY: From the way this function is written, it's possible that
# DeepMind clamped 90% of individual residue losses, not 90% of all batches.
# We defer to the text, which seems to imply the latter.
def backbone_loss( def backbone_loss(
backbone_affine_tensor: torch.Tensor, backbone_affine_tensor: torch.Tensor,
backbone_affine_mask: torch.Tensor, backbone_affine_mask: torch.Tensor,
...@@ -164,7 +161,6 @@ def backbone_loss( ...@@ -164,7 +161,6 @@ def backbone_loss(
1 - use_clamped_fape 1 - use_clamped_fape
) )
# Take the mean over the layer dimension
fape_loss = torch.mean(fape_loss) fape_loss = torch.mean(fape_loss)
return fape_loss return fape_loss
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment