L.JIE

Results 10 comments of L.JIE

改一下这个值:previous_loss

@Shiyu555 @Nancyh-e HERE: https://github.com/cleardusk/3DDFA/blob/master/benchmark_aflw.py

> > @Shiyu555 @Nancyh-e > > HERE: https://github.com/cleardusk/3DDFA/blob/master/benchmark_aflw.py > > hi,I am sorry to bother you again,do you get a similar NME result( according to the link method you have...

同样的问题,请问你的解决了吗?

> > 那可以分享下您训练用到的参数吗?例如net_blocks,emb_size,lr,wd ,lr_steps等 > > 详情参考:[deepinsight/insightface#214](https://github.com/deepinsight/insightface/issues/214) 链接中的代码是emb_size是128, 但是您分享的是256

@zeakey Thanks very much. I will have a try.

I test my `nvdiffrast` package by the script ' python ./samples/torch/cube.py --resolution 32', all is ok `No output directory specified, not saving log or images Mesh has 12 triangles and...