Darren759
Darren759
请问你训练的是v1还是v3,有出现双眼皮变单眼皮的现象吗
v3训练配置文件没有公开,主要差异应该在stylegan2的网络结构上,参数量更大,训练数据质量更高
Same problem,did you solve it?
> Same problem,did you solve it? Same problem,did you solve it?
> main分支支持了 请问如何调用
you can try: CUDA_VISIBLE_DEVICES=8,9,10,11 python -m torch.distributed.launch train.py
Did you solved it? I have the same problem!
"Did you solve this problem?"