Sean

def identify_axis(shape): # Three dimensional if len(shape) == 5 : return [2,3,4] # Two dimensional elif len(shape) == 4 : return [2,3] # Exception - Unknown else : raise ValueError('Metric:...

@tomanick Does AsymmetricUnifiedFocalLoss works fine on multi-class? I tried, but got some unexpected errors.

# Calculate losses separately for each class, only enhancing foreground class back_dice = (1-dice_class[:,0]) fore_dice = (1-dice_class[:,1]) * torch.pow(1-dice_class[:,1], -self.gamma) This is not suitable for multi-class, right?