cswwp
cswwp
> I had read your paper about “monodepth2”. I also had read your code about “monodepth2”. I wondered about how to train on custom dataset. I have obtained the pose...
it show '_predictor = new caffe2::Predictor(_initNet, _predictNet)' crash in debug mode,
@ ghost I encountered into the same issue, use shufflenet pb that had tested on pc with caffe python, and it show '_predictor = new caffe2::Predictor(_initNet, _predictNet)' crash in debug...
> The main difference is which distributed training library you use. The 1st one uses NVIDIA Apex library. The 2nd one uses `torch.nn.DistributedDataParallel`. The 1st one gives better perf and...
You can just consider each grid as an "anchor" whose aspect ratio is 1 and area is downsample size. About label assignment, use get_assignments
树莓派3安装tensorflow求经验
> @spring-sea 但是我看代码里边 关键点是否可见这一列给丢掉了，没有用，是这样吗？
Hi, @yaringal. I also meet this problem, and i want to know what's your understanding, thank you