Sacha
Sacha
Is that really a proper solution? It just does the work on the CPU instead. You can also do boxes.to(torch.device("cpu")) instead of converting to numpy and back.
Does it look different when you disable/enable buffered rendering?
@tedliosu About when you posted this, release v1.10.200 was released with XPU support based on xpu-master branch. Unfortunately as you can tell by the version, it's based on a fairly...
You can use the docker file from here: https://github.com/intel/intel-extension-for-pytorch/commit/e67ce74a5b4a8c428c0bf4a4ebe0737c7f68b086 It's in xpu-master branch and was updated to use XPU
Despite loss not decreasing, does accuracy remain competitive on validation sets? I don't use this repo but I have a similar issue when I use a parallel model where loss...
Also getting the same error here when testing this repository.
Yes, this is how the author intends the distance calculation. There may be better ways of calculating it but this is a typical way. The subtraction is only necessary if...
Works fine here, using C++ too.
@anguoyang pb file? As in tensorflow?
Yes, indeed. This was the smallest one to replace and should give you an idea of what I am looking to do (I'm not working on replacing anything else yet)....