Google Colab is not using GPU

• face_recognition version:'1.2.3'
• Python version: python3
• Operating System:

face_recognition library not using google colab gpu

I am following this tutorial
https://www.pyimagesearch.com/2018/06/18/face-recognition-with-opencv-python-and-deep-learning/

I have installed library in google colab like this:
!apt-get install libjpeg-dev libpng-dev libtiff-dev
!apt-get install libavcodec-dev libavformat-dev libswscale-dev libv4l-dev
!apt-get install libxvidcore-dev libx264-dev
!apt-get install libgtk-3-dev
!apt-get install libatlas-base-dev
!apt-get install gfortran
!apt-get install python3-dev

!apt-get -qq install -y libsm6 libxext6 && pip install -q -U opencv-python
import cv2
print(cv2.version)

Install dlib library

!apt update
!apt install -y cmake
!pip install dlib

import dlib
import dlib.cuda as cuda
print(cuda.get_num_devices())
dlib.DLIB_USE_CUDA=1
dlib.USE_AVX_INSTRUCTIONS=1

Install face_recognition library

!pip install face_recognition
import face_recognition
face_recognition.version

!pip install imutils

# After installing all the library & importing dataset, then i run following command
!python encode_faces.py --dataset dataset --encodings encodings.pickle

The issue names no repository file or test; the only entry point mentioned is encode_faces.py, run after installing dlib and face_recognition in Google Colab. Start by reproducing the installation and checking dlib.cuda.get_num_devices() before running that command. Done means establishing whether the reported GPU behavior is reproducible and identifying the project-level change or documentation needed.