Marek

Hi, No idea, look at the theano documentation and see there (theano is the library that uses the GPU). Marek

Hi, Are you using the version that I supplied above in dropbox or the version in the repo? If the one in Dropbox, I would suggest trying to enable gpu...

Hi, The performance of the face alignment step (DAN) would definitely be lower than what you would get from a GPU equipped desktop computer. There would definitely be some room...

Hi, Here are my comments to your questions: 1. My settings are set in the .theanorc file in the following way: ``` [global] device=gpu floatX=float32 ``` 2. Ideally you would...

Hi, 1. You need to know the indices of the triangles you removed from the obj mesh and remove the corresponding rows of the _mesh_ variable in zad2.py 2. [Here](https://www.dropbox.com/s/jbxqvm4o0qwv4fb/candide.py?dl=0)...

Hi, You can just replace the `cameraImg` in zad2.py with your own image. One way to do it might be to replace line 38 with: `cameraImg = cv2.imread()` and commenting-out...

Hi, Sorry for taking a while to answer. I suspect your version is very slow because you run the face detection in every frame. If you want it to run...

Hi, No such plans at the moment, but it's an interesting idea. I know that at least one person was looking at a headless version, more details [here](https://github.com/MarekKowalski/FaceSwap/issues/9). Best regards,...

The app should work fine for multiple faces in the video where the face are being swapped. If it does not, it may mean that one face is not detected....

If you want something simple, then you can choose the face you want using some conditions on the locations of the face keypoints. You can, for example, do something like...