Closed ycjing closed 5 years ago
Hi, Yes, we will try to release it next week.
пт, 21 сен 2018 г., 14:52 Yongcheng Jing notifications@github.com:
Hi. Thanks for the nice code. The results are really impressive. It could be great if you could release the pre-trained model for calculating style transfer deception rate and follow-up works could thus have a quantitative comparison with your algorithm. Thanks!
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/CompVis/adaptive-style-transfer/issues/5, or mute the thread https://github.com/notifications/unsubscribe-auth/ABnM9Va78Ijut9oeotrNxlMUXqoC8N3dks5udNLlgaJpZM4Wz_4W .
I need the same model, but for style grouping mainly. @asanakoy, it'd be great help to have it sooner. If not possible, do you know any other publicly available model that did the same?
Thanks.
The instructions how to calculate deception score are now in evaluation folder.
Run evaluation/download_evaluation_data.py to download a pretrained model for deception rate computation or get it by the link https://yadi.sk/d/A2CBqSGuJ0M_XA.
I'm sorry for the delay.
Hi. Thanks for the nice code. The results are really impressive. It would be great if you could release the pre-trained model for calculating style transfer deception rate and follow-up works could thus have a quantitative comparison with your algorithm. Thanks!