xiaosi

关于全身模型训练实现（destylize.py 后续流程）

3

大佬，我微调得到一个全身的模型，在接下来执行训练流程，我发现几个问题： 1. PsP encoder，这个模型参数如何获取，因为没有全身人像的编码器，只有人脸的编码器？（destylize.py） 2. 对于[model_ir_se50.pth](https://drive.google.com/file/d/1KW7bjndL3QG3sxBbZxreGHigcCCpsDgn/view?usp=sharing) 这个 模型如何使用呢，因为他不在适用于全身模型 

你好，我想只输出3D位置显示，该如何处理输出结果？

6

1. 请问大佬，如何绑定真实世界坐标系  https://github.com/Arthur151/ROMP/issues/372#issuecomment-1345247684，看了这个回复，还是不太懂，如何实现 2. 当我镜头里只有两个人时候会出现缩放现象（人物比例不一，就像镜头拉近了一样），这个如何消除。无论几个人我只想保持原始比例不变。 

Can I install windows

about train texture translator datasets

3

 I think my data structure is wrong

Need change this code ,set os.environ['CUDA_VISIBLE_DEVICES'] = '0' 

How to Convert Low-Res Videos to High-Res Videos

1

How to test my own videos, do I need to train first? I only have a low res video

https://github.com/dvschultz/stylegan2-ada-pytorch/issues/43 

Camera positioning in an all-green room

1

Can I use this project in the green shed because I found that there are white walls without texture testing，（Hand-held dataset with textureless wall）？ like this room for Camera positioning...

how to run offline?

about convert model? only g_ema? why ? other parameters?

2

I want to use the stylegan2-ada-pytorch model as a stylegan-pytorch([rosinality](https://github.com/rosinality)) pre-training model. I find that the model is loaded with missing parameters. What should I do?