QiulinW
QiulinW
I got the same problem as you...
> Hi! Thanks for your compliments. > Training with only CelebA-HQ is quite a dangerous choice. > The dataset bias can be affected to total loss. > In your loss...
> Could you please tell me how long does it take to finish the training? For celebHQ dataset only, it takes 2-3 hours for an epoch.
> > Hi! You did very fast training! > > > > 1. Yes, I used full-set dataset. I don't know about IJB-C dataset. The distribution of dataset can influence...
Yes, but you need to turn off the --relative option, use absolute mode instead.
Hi, The ldmk loss is a re-projection loss. Therefore, for a given set of landmarks on the 2D images, there are countless solutions of 3DMM parameters (shape, exp, pose). This...
Hi, I added some videos to ./assets, have fun!
> resultSAFA.mp4 > @Qiulin-W For face swapping, it is something like "copy and paste" in our framework, which relies on a face segmentor and we deform the source face so...
> > > > I see! Have you tried to train with SoftRas on the full training set? Does it still not work well? > > > > > >...
> By the way, I have test the AIC-ICC Validset from BriVL-API1.0, but the retrieval result is too low (Recall@1 < 1%). I use your released code for 'retrieval '...