Once we train the network, we can make each embedding vectors with each given one-hot encoding vevtor.
'Papers > Machine learning' 카테고리의 다른 글
| Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields (0) | 2019.07.17 |
|---|---|
| cosign similarity (0) | 2019.07.11 |
| Diffrence between MIPS and DMIPS (0) | 2019.06.24 |
| CornerNet: Detecting Objects as Paired Keypoints (0) | 2019.06.22 |
| Generative adversary network (0) | 2019.06.21 |