Deep Learning for
Computer Vision
INTRODUCTION TO
DEEP LEARNING
Prof. G.S. Jison Hsu 徐繼聖
• Artificial Vision Laboratory
• National Taiwan University of
Science and Technology
Deep Learning for Computer Vision
What Is Google Colab?
Google Colab is a free cloud service and now it supports free GPU!
You can:
1. Improve your Python programming language coding skills.
2. Develop deep learning applications using popular libraries
such as Keras, TensorFlow, PyTorch, and OpenCV.
Deep Learning for Computer Vision 2
Getting Google Colab Ready to Use
1. Sign in your Google account 2. Open your Google drive
Deep Learning for Computer Vision 3
Create a New Notebook
1. New > More > Colaboratory 2. Create a new notebook
Deep Learning for Computer Vision 4
Setting Free GPU
1. Edit > Notebook settings 2. Hardware > GPU > SAVE
Deep Learning for Computer Vision 5
Exercise
• If you want to run the exercise, you can follow the steps.
1. Log in and upload the ipynb file
Deep Learning for Computer Vision 6
Exercise
1. Log in and upload the ipynb file
Deep Learning for Computer Vision 7
Exercise
1. Log in and upload the ipynb file
Deep Learning for Computer Vision 8
Exercise
2. Open the ipynb file with Google Colaboratory
Deep Learning for Computer Vision 9
Exercise
3.1 Setting Free GPU 3.2 Hardware > GPU > SAVE
Edit > Notebook settings
Deep Learning for Computer Vision 10
Exercise
4.1 Run the code 4.2 Files : the path of your files
Run the code
Deep Learning for Computer Vision 11
How to save file?
5.1 File > Download > Download .ipynb/Download .py
Deep Learning for Computer Vision 12
Exercise
• Download “Bounding_Box.zip” from Moodle.
• Use google colab to run the code.
• Relevant information:
http://d2l.ai/chapter_computer-vision/bounding-box.html
Deep Learning for Computer Vision 13