Why d_loss = 0.5 * np.add(d_loss_real, d_loss_fake) ?

I wonder why it's d_loss = 0.5 * np.add(d_loss_real, d_loss_fake) and not d_loss = np.add(d_loss_real, d_loss_fake)?

https://github.com/eriklindernoren/Keras-GAN/blob/master/gan/gan.py#L123