Hi, i want to minimize my face recognition system from PC to Jetson nano
i use the example code from this link :
import face_recognition
import cv2
import numpy as np
# This is a demo of running face recognition on live video from your webcam. It's a little more complicated than the
# other example, but it includes some basic performance tweaks to make things run a lot faster:
# 1. Process each video frame at 1/4 resolution (though still display it at full resolution)
# 2. Only detect faces in every other frame of video.
# PLEASE NOTE: This example requires OpenCV (the `cv2` library) to be installed only to read from your webcam.
# OpenCV is *not* required to use the face_recognition library. It's only required if you want to run this
# specific demo. If you have trouble installing it, try any of the other demos that don't require it instead.
# Get a reference to webcam #0 (the default one)
video_capture = cv2.VideoCapture(0)
# Load a sample picture and learn how to recognize it.
obama_image = face_recognition.load_image_file("obama.jpg")
obama_face_encoding = face_recognition.face_encodings(obama_image)[0]
show original
the code works fine on PC. but when i move the code to Jetson nano, it can’t recognize known faces.
and i just following the guidline in this link https://medium.com/@ageitgey/build-a-hardware-based-face-recognition-system-for-150-with-the-nvidia-jetson-nano-and-python-a25cb8c891fd . to solve the dlib bug on jetson nano
when i recompile the dlib, the system still can’t recognize known faces
does anyone have experience to solve this kind of problem? thanks in advance !
the value of face encodings returned 128-dimension value and sometimes returned ‘nan’ value. and i’m using rasberry pi camera.
array when returned value:
[array([-2.71021342e+18, 5.32363354e+18, -2.49195294e+18, 8.96801266e+18... ]
array when returned nan value:
[array([nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,...]
Hi,
It looks like you are still having the same issue of topic_1049660 :https://devtalk.nvidia.com/default/topic/1049660/jetson-nano/issues-with-dlib-library/2
A possible cause is that there are multiple dlib versopm in your environment and the python doesn’t use the compiled one.
Thanks.