Sacha
Sacha
Yeah I have given up on this one sorry since the inference time was too high and the deformable conv makes it harder to use. Dropping the deform conv made...
@wmcnally Thanks. That looks quite fast. The videos look very inaccurate (stolen joints) but I guess they are showing the small model. It can be resolved as this is usually...
Would it depend on which combinations were taken? Was there any given .txt file provided with the pairs list for any of the protocols? Could you provide the pair lists...
You just need to choose a suitable batch size for your GPU memory. Example: GTX 660 has only 2GB and can only do batch size of 4. If you have...
Yeah I understand you kept the parameters the same as the paper. Honestly some of them don't make much sense though. I use a similar NMS threshold for other models...
With CUDA, 1920x1080 resolution input without any downscaling (min face size is ~ 14 px), Faceboxes performance can be approximated as: FPS = CUDA CORES / 16 It scales linearly...
Getting the same issue here, with self-built pytorch + torchvision. On CUDA 11.3. Any workarounds?
I only have a single libtorch and torchvision API (nothing from pip or conda on this machine) I have compiled myself from master using same CUDA version. They are all...
I was not using Python at all. Using libtorch + torchvision compiled with same CUDA version. Built torchvision as described by @mattpopovich as I followed the build instructions.
I used that flag when I compiled (as per build instructions) and watched it build the CUDA modules. Then I ended up here with this issue.