Fuxu Liu
Fuxu Liu
@cavalleria thanks for your reply. Looking forward to the results of your experiments.
@cavalleria thanks for your reply. Looking forward to the results of your experiments.
@cavalleria I checked the result from model_zoo. It seems the data aug get lower accuracy?
Like this, For example: `pnet.cuda() rnet.cuda() onet.cuda() offsets = output[0].cpu().data.numpy() probs = output[1].cpu().data.numpy()` finish the rest like that
@zuoqing1988 左博您好，我想问下，你在训MobileFaceNet-res4-8-16-4-dim512的时候version_output选择‘GNAP’和’E‘，精度差别大吗?
@Ontheway361 ok, it is really nice, thank you.
@qjadud1994 Good job.
@sciencefans yep, thanks for your reply.
@sciencefans I got it, thank you.
same questions. I was reading the source code and found that sidechain's output is simply extended by backbone coords, but there is no real prediction. But in the paper, the...