shape_predictor_68_face_landmarks.dat deserialization error

[jameswhite0811]

I'm getting a runtime error that says RuntimeError: An error occurred while trying to read the first object from the file 'datFiles/shape_predictor_68_face_landmarks.dat'. ERROR: Error deserializing object of type unsigned long while deserializing object of type std::string. I've researched for quite some time now, and a few people have said they solved it, but didn't post their solutions. Here is my code for reference: `import cv2
import dlib
import numpy as np

Load the test image

image = cv2.imread('testPics/group.jpg')

Convert to grayscale

gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

Load the face cascade for detection

face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')

Load the pre-trained face recognition model

face_rec_model = dlib.face_recognition_model_v1("datFiles/shape_predictor_68_face_landmarks.dat")`

[arrufat]

I think you want to perform landmarks detection, then follow this example
http://dlib.net/face_landmark_detection.py.html