Hacker News new | past | comments | ask | show | jobs | submit login

It is not quite relative but regularised by another GAN...



It's from same GAN though, C(x_r) and C(x_f) come from the same neural network. It's how realistic real data is compared to fake data (and vice-versa) as determined by C (discriminator without activation function).




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: