Face Recognition Python Demo AssertionError on landmarks_detector.py

[Duggy]

Hi,

I am trying to run Face Recognition Python Demo with the following code:

face_recognition_demo.py -i NMS1.avi -o "c:\myPath\output.avi" -m_fd models\face-detection-retail-0004\FP16\face-detection-retail-0004.xml -m_lm models\facial-landmarks-35-adas-0002\FP32\facial-landmarks-35-adas-0002.xml -m_reid models\face-reidentification-retail-0095\FP16\face-reidentification-retail-0095.xml

and I am getting the following error:

PATH\face_recognition_demo\python\landmarks_detector.py", line 36, in __init__
assert np.array_equal([1, self.POINTS_NUMBER * 2, 1, 1], output_shape), \
AssertionError: Expected model output shape [1, 10, 1, 1], got [1, 70]

Can anyone shed some light on this?

Thanks

[IntelSupport · Accepted solution]

Hi Duggy,

Thanks for reaching out.

What is the version of the OpenVINO toolkit you are using? The facial-landmarks-35-adas-0002 is a legacy model and is not supported with the face recognition demo anymore. The facial-landmarks-35-adas-0002 is only supported for interactive Face Detection C++ demo from OpenVINO 2019_R1 version.

Therefore, the supported model for Face Recognition Python* Demo is listed in the documentation.

Regards,

Aznie

[IntelSupport]

Hi Duggy,

This thread will no longer be monitored since this issue has been resolved. If you need any additional information from Intel, please submit a new question.

Regards,

Aznie