Wrong calculation of LSGAN

There exists an apparent error in the implementation of LSGAN below.

https://github.com/akanimax/BBMSG-GAN/blob/da82aa2e8507d17801bd2134a4ae754335d716f5/sourcecode/MSG_GAN/Losses.py#L145

Right implementation:

```python
class LSGAN(GANLoss):

def __init__(self, dis):
super().__init__(dis)

def dis_loss(self, real_samps, fake_samps):
real_scores = th.mean((self.dis(real_samps) - 1) ** 2)
fake_scores = th.mean(self.dis(fake_samps) ** 2)
return 0.5 * (real_scores + fake_scores)

def gen_loss(self, _, fake_samps):
return 0.5 * th.mean((self.dis(fake_samps) - 1) ** 2)

```

reference equation 8 of [Least Squares Generative Adversarial Networks].