Adrian Bulat

The cost will depend on the size of your images, since the detection part will dominate the timing. A few suggestions: Try one of the 3 available face detector (see...

You should be able to change this by passing the device explicitly: e.g.: ```device = 'cuda:1'``` when constructing the model. Alternatively, if you are running this as a separate script...

Hi @Yozey , Yes, I was in the process of converting/retraining the smaller models but most of them are not fully retrained. I will resume this at some point during...

Hi @nightmaredimple , The entire process is dominated by dlib face detector. In CPU mode dlib uses basically a V-J face detector while in cuda mode a cnn-based detector.The 2D/2.5D...

Hi @nightmaredimple, that makes sense, the first pass is taking longer due to all initialisation and copying stuff from cpu to cuda. The 20-30 was achieved usign a Titan X...

Hi @moncio This interfacing is handled by pytorch, as such this shouldn't be an issue. Just make sure that you install an appropriate pytorch version ( see https://pytorch.org/get-started/locally/)

Can you please try updating the face alignment lib to the latest version? (1.3.3)

According to the error trace this seems to be an issue with your nvidia/cuda installation: ```failed to open libnvrtc-builtins.so.``` Please make sure this is installed and added to your path.

@moncio I am unable to reproduce the issue at the moment on my system. Could you check please if after fixing the missing library the error still occurs?

Could you please try running the test suite, available in test folder? Also, does the code provided here: https://github.com/1adrianb/face-alignment/blob/master/examples/demo.ipynb work? Finally, does sdf instead of blazeface work?