We need three loss functions as below.
1. Discriminator
input : noise
Loss : | output - 0(false) |
Topology : generator + discriminator
2. Discriminator
input : real data
Loss : | output - 1(true) |
Topology : discriminator
3. Generator
input : noise
Loss : | output - 1(true) |
Topology : generator + discriminator
'Papers > Machine learning' 카테고리의 다른 글
| Diffrence between MIPS and DMIPS (0) | 2019.06.24 |
|---|---|
| CornerNet: Detecting Objects as Paired Keypoints (0) | 2019.06.22 |
| Tracking based on siamese network (0) | 2019.06.10 |
| Tracking without bells and whistles (0) | 2019.06.07 |
| zero skip (0) | 2019.06.04 |