minygd

Results 5 comments of minygd

> For triplet loss, In his code, you can see that he first random select K samples as anchors, K is the batch size, and then for each id in...

Hello, but I still can't figure out in Pytorch 1.5.0 CUDA10.2.

@shijianjian Hi, I can build DCN and `test` D3DNet with Pytorch 1.0.0, you may try to use a lower version of Pytorch.

Me too. The solution is deadly needed!

I have fixed this. Just make sure uninstall every pkgs/pip downloads/conda downloads of OpenEXR. And then use `pip --no-cache-dir install OpenEXR` instead to avoid downloading the former pkgs.