Serge-weihao

> > > Did u test the inference speed of DFAnet? The result of my test by mxnet is over 40ms for one image(size:1024*1024), which is far away from the...

@charlesCXK hha = getHHA(camera_matrix, D, RD) what are the RDs for Cityscapes?

@huberthomas do you know how to get the camera intrinsics from nyuv2 and sunrgbd datasets?

> > > have you compared the moiu between your cc.py and the original code on cityscapes ??? > becauese i have test your cc.py,and ..... I have checked the...

> can the miou reach 80％------------------ 原始邮件 ------------------ I load the same checkpoint using our pure PyTorch implementation and the official cc_attention, the mIoU results are almost the same, because...

The same CKPT of 30000/60000, using official inplace-abn Testing with 1) official CUDA cc_attention  2) My CC.py 

> the original code is not like yours,i don't understand his code ,for example , _ext. is for what, i can't understand They use CPP extension with CUDA, so you...

What op sys are you using, Linux or Win?

This repo uses [Synchronized-BatchNorm-PyTorch](https://github.com/vacancy/Synchronized-BatchNorm-PyTorch) as cross gpus BatchNorm, it costs more gpu memory. I have tested it for batchsize of 4, the result is about 67, so I think the...

inplace-abn can save some GPU memory for training, but the official CUDA inplace-abn may not support Windows well. If this repo is helpful for you, you can star it.