Haoru Zhao

I used the datasets of 512*512, the pose feature vector and the noise vector are 512 dimensional. Is this the problem?

The problem has been solved. I missed the val_loader in my training. Thank you very much~

I have met the same problem. Have you solved it?

请问如何裁剪 SplitNet网络，获取BVMR的训练模型？

This error pops up when I use the pre-trained CelebA-HQ-p256 model. Have you found any solution for it?