losses.py 文件源码

def calc_gradient_penalty(self, netD, real_data, fake_data):
        alpha = torch.rand(1, 1)
        alpha = alpha.expand(real_data.size())
        alpha = alpha.cuda()

        interpolates = alpha * real_data + ((1 - alpha) * fake_data)

        interpolates = interpolates.cuda()
        interpolates = Variable(interpolates, requires_grad=True)

        disc_interpolates = netD.forward(interpolates)

        gradients = autograd.grad(outputs=disc_interpolates, inputs=interpolates,
                                  grad_outputs=torch.ones(disc_interpolates.size()).cuda(),
                                  create_graph=True, retain_graph=True, only_inputs=True)[0]

        gradient_penalty = ((gradients.norm(2, dim=1) - 1) ** 2).mean() * self.LAMBDA
        return gradient_penalty