Closed Jawkx closed 3 years ago
@Jawkx please have a look at the the function defination of the function detect_marks in the face_landmarks.py. You need to pass the original image along with [x0, y0, X1, y0] which represents the face box coordinates you would have found from face detector. it should work then.
Issue solved, thanks
Hi, I tried your code and I copied your save_model.pb file. I use my own face detection algorithm and plan to use your face landmark system. The detect_marks() is not working and it shows the error
got shape [1, 128, 128, 3], but wanted [1]
. Do you know what should I do to fix this ?Thank you very much