Use Python to run the engine file of facenet to obtain 512 dimensional face coding data

Please provide complete information as applicable to your setup.

I have a working facenet engine file. Now, I want to write a script in python with the following functions:

  1. Read in a face.
  2. Using the engine model of facenet, the picture is encoded to obtain 512 dimensional data.
    How can I call the engine file directly in Python and perform the above functions?

Hi @837331759 , I think you might be in the wrong sub-category, since you are asking for help on a FaceNet deep learning model. Is this on specific NVIDIA Hardware like a Jetson? Or is it a generic question regarding TensorRT?

Either way I highly recommend looking into those two categories and moving your topic to receive best possible visibility.

I hope that helps!