Function batch_dice_loss

semantic_sam/modules/matcher.py:22–37

Compute the DICE loss, similar to generalized IOU for masks Args: inputs: A float tensor of arbitrary shape. The predictions for each example. targets: A float tensor with the same shape as inputs. Stores the binary classification label for e

(inputs: torch.Tensor, targets: torch.Tensor)

def batch_dice_loss(inputs: torch.Tensor, targets: torch.Tensor):
    """
    Compute the DICE loss, similar to generalized IOU for masks
    Args:
        inputs: A float tensor of arbitrary shape.
                The predictions for each example.
        targets: A float tensor with the same shape as inputs. Stores the binary
                 classification label for each element in inputs
                (0 for the negative class and 1 for the positive class).
    """
    inputs = inputs.sigmoid()
    inputs = inputs.flatten(1)
    numerator = 2 * torch.einsum("nc,mc->nm", inputs, targets)
    denominator = inputs.sum(-1)[:, None] + targets.sum(-1)[None, :]
    loss = 1 - (numerator + 1) / (denominator + 1)
    return loss


batch_dice_loss_jit = torch.jit.script(