Question

我想使用Python软件包----“ dlib”来检测图片中的人脸，当我使用“ detector = dlib.get_frontal_face_detector（）”作为检测器时，没有错误，我可以获得人脸图片。但是当我使用“ detector = dlib.cnn_face_detection_model_v1”作为检测器时，会出现一些错误。在两种情况下，预测变量都是“ shape_predictor_68_face_landmarks.dat”。

我使用DEBUG查找导致错误的代码，并且在运行代码“ shape = dictoror（frame，d）”时发现错误：

Traceback (most recent call last):
File "/home/cxd/pycharm-community-2019.1/helpers/pydev/pydevd.py", line 1741, in <module>
    main()
File "/home/cxd/pycharm-community-2019.1/helpers/pydev/pydevd.py", line 1735, in main
    globals = debugger.run(setup['file'], None, None, is_module)
File "/home/cxd/pycharm-community-2019.1/helpers/pydev/pydevd.py", line 1135, in run
    pydev_imports.execfile(file, globals, locals)  # execute the script
File "/home/cxd/PycharmProjects/ROI/videos.py", line 47, in get_frames_mouth
    shape = predictor(frame, d)
TypeError: __call__(): incompatible function arguments. The following argument types are supported:
1. (self: dlib.shape_predictor, image: array, box: dlib.rectangle) -> dlib.full_object_detection

Invoked with: <dlib.shape_predictor object at 0x7f17f3684ce0>, array([[[124, 106, 145],
    [124, 106, 145],
    [124, 106, 145],
    ...,
    [134, 116, 145],
    [134, 116, 145],
    [134, 116, 145]],

   [[124, 106, 145],
    [124, 106, 145],
    [124, 106, 145],
    ...,
    [134, 116, 145],
    [134, 116, 145],
    [134, 116, 145]],

   [[124, 106, 145],
    [124, 106, 145],
    [124, 106, 145],
    ...,
    [134, 115, 147],
    [134, 115, 147],
    [134, 115, 147]],

   ...,

   [[ 37,   0,   1],
    [ 37,   0,   1],
    [ 36,   0,   0],
    ...,
    [ 56,   0,  17],
    [ 55,   0,  17],
    [ 55,   0,  17]],

   [[ 37,   0,   0],
    [ 36,   0,   0],
    [ 36,   0,   0],
    ...,
    [ 55,   0,  16],
    [ 54,   0,  16],
    [ 54,   0,  16]],

   [[ 37,   0,   0],
    [ 36,   0,   0],
    [ 36,   0,   0],
    ...,
    [ 55,   0,  16],
    [ 54,   0,  16],
    [ 54,   0,  16]]], dtype=uint8), <dlib.mmod_rectangle object at 0x7f18250c7308>

Process finished with exit code 1

代码是：

detector = dlib.cnn_face_detection_model_v1("mmod_human_face_detector.dat")
predictor = dlib.shape_predictor("shape_predictor_68_face_landmarks.dat")
dets = detector(frame, 1)  #frame is np.array
shape = None
for k, d in enumerate(dets):  
    shape = predictor(frame, d)

我认为两种检测器的结果相同，有人可以帮助我解决这个问题吗？

我将“ cnn_face_detection_model_v1”用作检测器时如何解决此错误？

0 个答案: