fq
fq
> 快了吧 @FeiiYin
> @FeiiYin 请问代码开源的进展如何？距离发表也过去很久了，希望公开具体日程计划。 实在不方便开源也不强求，请直接说明即可。没有期限的等待是无意义的 我以为发表了就可以开源的。为啥每次都来个批准，不如一开始就别搞在gayhub上。批准往往也是残缺的开源。比如网易的开源。。没一个完整，有效的。
why there is no answer?
same problem for the latest code..., precious :0 ,recall : 0, hmean :0
> > > same problem for the latest code..., precious :0 ,recall : 0, hmean :0 it seems the dataloader bug? when show in a batch, some image's label is...
> > 导出的 fbx，还是普遍的吗？ > > Can you share how to export fbx files？ may be u can reference vibe, romp, nbs, mocaptofbx,easymocap...project.
> 您好，我下载了您的代码以及在readme.md中所提到的所有模型，并且尝试以evaluate模式运行代码。但是发现还是提示少了"79999_iter.pth"这个模型文件。请问您可以分享给我这个模型文件吗？ https://drive.google.com/file/d/154JgKpzCPW82qINcVieuPH3fZ2e0P812/view
but, i want to use d0-d7, just one 2080Ti, and batch_size >=4 for any backbone, and input shape >=(448,448) or (640, 640) it's seems that, the basic backbone limit the...
> The result video has mouth-only motion when I use pre-trained model. But when I use the model trained by myself, the result has whole-face motion. (vocaset) is there only...
so, you solved this problem?