4063565295aae8f739b006ac5ab814c12bd8a81e,myloss.py,,dice_coeff,#,30

Before Change

        return grad_input, grad_target

def dice_coeff(input, target):
    return DiceCoeff().forward(input, target)

class DiceLoss(_Loss):
    def forward(self, input, target):
        return 1 - dice_coeff(F.sigmoid(input), target)

After Change

    else:
        s = Variable(torch.FloatTensor(1).zero_())

    for i, c in enumerate(zip(input, target)):
        s = s + DiceCoeff().forward(c[0], c[1])

    return s / (i+1)


class DiceLoss(_Loss):

Instances