Skip to content

Wessam611 focal loss kwargs (#1) #2

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

Open
wessam611 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Wessam611 focal loss kwargs (#1) #2

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
7 changes: 4 additions & 3 deletions cbloss/loss.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,20 +46,21 @@ class FocalLoss(nn.Module):
Focal loss value.
"""

def __init__(self, num_classes, alpha=1, gamma=2, reduction="mean"):
def __init__(self, num_classes, alpha=1, gamma=2, reduction="mean", **kwargs):
super(FocalLoss, self).__init__()
self.num_classes = num_classes
self.alpha = alpha
self.gamma = gamma
self.reduction = reduction
self.kwargs = kwargs

def forward(self, outputs, targets):
if self.num_classes == 2:
# binary classification problem
ce_loss = F.binary_cross_entropy_with_logits(outputs, targets.float(), reduction="none")
ce_loss = F.binary_cross_entropy_with_logits(outputs, targets.float(), reduction="none", **self.kwargs)
elif self.num_classes > 2:
# multi-class classification problem
ce_loss = F.cross_entropy(outputs, targets, reduction="none")
ce_loss = F.cross_entropy(outputs, targets, reduction="none", **self.kwargs)
else:
raise ValueError(f"Invalid input value : {self.num_classes}. It should be equal or greater than 2.")

Expand Down