Timeline for Wasserstein Loss is very sensitive to model architecture
Current License: CC BY-SA 3.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 16, 2020 at 19:48 | answer | added | KFa | timeline score: 1 | |
| Mar 28, 2018 at 15:51 | vote | accept | alpaca | ||
| Mar 27, 2018 at 12:06 | answer | added | shimao | timeline score: 11 | |
| Mar 27, 2018 at 8:30 | comment | added | GR4 | WGAN requires that you also clip the model parameters for the critic, did you do so? Also note that a recent paper has shown a few limitations to this WGAN approach and has improved on it by using a gradient penalty (see this paper: arxiv.org/pdf/1704.00028.pdf ) Using such a WGAN-GP could help you get better results. | |
| Mar 26, 2018 at 21:12 | history | asked | alpaca | CC BY-SA 3.0 |