Found bugs including GPU out of memory

[18608003987]

Very nice contribution from you! thanks and I find
[1] need to swith from LA to L mode in line#35 of proxyPredictor.py
img = Image.open(img_path).convert('L')
[2] can not run under Tensorflow 2.0 currently
[3] can run proxy estimation base on two priors: --FAC 1 and --emotion 1, but can not get displacementMap, normalMap successfully when I run facialDetails.py , will encounter the issue below,
File "G:\Facial_Details_Synthesis\released_v0.1\DFDN\models\networks.py", line 317, in forward
return torch.cat([self.model(x), x], 1)
RuntimeError: CUDA out of memory. Tried to allocate 800.00 MiB (GPU 0; 6.00 GiB total capacity; 3.65 GiB already allocated; 798.37 MiB free; 4.00 KiB cached)
What's the minimal GPU VRAM for it ?

[apchenstu]

Hi, you can simply reduce the batchSize for out of memory issue. Thanks.