LeiZhu

> I've test DECA pretrained model in NoW dataset, result is median:1.15, mean:1.44mm,std:1.24mm... but in DECA paper they report median:1.09, mean:1.38mm,std:1.18mm @littlePrince126 朋友，方便加个微信讨论吗？ hello 你好 最近也在跑这个代码 方便加个微信讨论吗？或者邮箱？

i got the same problem there is a bug in torch while you are using nn.conv2d and set it's padding mode as circular https://github.com/reshow/PRNet-PyTorch/blob/9b0a5dc6fec77c5edd45c66e46b5b050d400b352/torchmodule.py#L97 different version of torch will get...

it seems it doesn't support AFLW