AdrienPlayerium

ax = pc.get_axes() to ax = pc.axes

@Dentrax install tensorflow_gpu

you need to give integers to reach indices of gray_border. use a int(float f) to make sure you get it right.

@Mrinal18 In this code sample, he got a numpy array which contains pixel information, to pick the region of interest you got to pick a part of this matrix, that's...

@wonny2001 probably because "faces" was not in the scope of your call.

@yazidabdulsalam Looks like you do not have opencv library installed in your environment. >pip install opencv-python? or cv2

@Mrinal18 You need to open the video stream with videopath instead of 0 (webcam) cv2.VideoCapture(videoPath)

Training on GPU is way faster... @sakshamjindal07 sorry mate :/ I can't share mine you get get one model here https://github.com/JostineHo/mememoji She did a nice job, not sure how good...

@AlainPilon Your model is probably not loaded ~Or you are a real happy guy hehe

@paulkirkland Maybe without training a different network, you can take that output, as a noisy detection, and use mean shift, or kalman filtering to reduce the noise.