O'Reilly logo

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

PyTorch for Deep Learning and Computer Vision

PyTorch for Deep Learning and Computer Vision

by Sarmad Tanveer, Rayan Slim, Jad Slim, Amer Sharaf
Publisher: Packt Publishing
Release Date: April 2019
ISBN: 9781838822804
View table of contents
Start watching

Video Description

Learn to build highly sophisticated Deep Learning and Computer Vision Applications with PyTorch.

About This Video

  • This course is designed to take students with no programming/mathematics experience to accomplished Deep Learning developers.
  • No experience required.

In Detail

PyTorch has rapidly become one of the most transformative frameworks in the field of Deep Learning. Since its release, PyTorch has completely changed the landscape in the field of deep learning due to its flexibility, and how easy it is to use when building Deep Learning models. Deep Learning jobs command some of the highest salaries in the development world. Learn & Master Deep Learning with PyTorch in this fun and exciting course with top instructor Rayan Slim. With over 44000 students, Rayan is a highly rated and experienced instructor who has followed a "learn by doing" style to create this amazing course. You'll go from beginner to Deep Learning expert and your instructor will complete each task with you step by step on screen. By the end of the course, you will have built state-of-the art Deep Learning and Computer Vision applications with PyTorch. The projects built in this course will impress even the most senior developers and ensure you have hands on skills that you can bring to any project or company.

This course will show you to:

  • Learn how to work with the tensor data structure
  • Implement Machine and Deep Learning applications with PyTorch
  • Build neural networks from scratch
  • Build complex models through the applied theme of advanced imagery and Computer Vision
  • Learn to solve complex problems in Computer Vision by harnessing highly sophisticated pre-trained models
  • Use style transfer to build sophisticated AI applications that are able to seamlessly recompose images in the style of other images.

All the code and supporting files for this course are available at: https://github.com/PacktPublishing/PyTorch-for-Deep-Learning-and-Computer-Vision

Downloading the example code for this course: You can download the example code files for all Packt video courses you have purchased from your account at http://www.PacktPub.com. If you purchased this course elsewhere, you can visit http://www.PacktPub.com/support and register to have the files e-mailed directly to you.

Table of Contents

  1. Chapter 1 : Introduction
    1. Introduction 00:01:41
  2. Chapter 2 : Getting Started
    1. Finding the codes (Github) 00:00:33
    2. A Look at the Projects 00:02:20
  3. Chapter 3 : Intro to Tensors – PyTorch
    1. Intro 00:00:18
    2. 1 Dimensional Tensors 00:08:44
    3. Vector Operations 00:05:23
    4. 2 Dimensional Tensors 00:05:30
    5. Slicing 3D Tensors 00:03:03
    6. Matrix Multiplication 00:03:21
    7. Gradient with PyTorch 00:04:23
    8. Outro 00:00:14
  4. Chapter 4 : Linear Regression – PyTorch
    1. Intro 00:00:44
    2. Making Predictions 00:06:15
    3. Linear Class 00:04:30
    4. Custom Modules 00:08:09
    5. Creating Dataset 00:10:35
    6. Loss Function 00:03:33
    7. Gradient Descent 00:04:41
    8. Mean Squared Error 00:03:16
    9. Training - Code Implementation 00:11:36
    10. Outro 00:00:31
  5. Chapter 5 : Perceptrons – PyTorch
    1. Intro 00:00:31
    2. What is Deep Learning 00:01:19
    3. Creating Dataset 00:09:35
    4. Perceptron Model 00:11:56
    5. Model Setup 00:11:23
    6. Model Training 00:10:38
    7. Model Testing 00:05:23
    8. Outro 00:00:23
  6. Chapter 6 : Deep Neural Networks – PyTorch
    1. Intro 00:00:28
    2. Non-Linear Boundaries 00:02:57
    3. Architecture 00:09:07
    4. Feedforward Process 00:07:46
    5. Error Function 00:04:10
    6. Backpropagation 00:05:03
    7. Code Implementation 00:08:49
    8. Testing Model 00:15:22
    9. Outro 00:00:22
  7. Chapter 7 : Image Recognition – PyTorch
    1. Intro 00:00:36
    2. MNIST Dataset 00:05:50
    3. Training and Test Datasets 00:12:39
    4. Image Transforms 00:16:26
    5. Neural Network Implementation 00:30:44
    6. Neural Network Validation 00:12:21
    7. Final Tests 00:13:26
    8. A note on adjusting batch size 00:01:29
    9. Outro 00:00:22
  8. Chapter 8 : Convolutional Neural Networks – PyTorch
    1. Convolutions and MNIST 00:06:06
    2. Convolutional Layer 00:18:12
    3. Convolutions II 00:08:07
    4. Pooling 00:14:11
    5. Fully Connected Network 00:06:23
    6. Neural Network Implementation with PyTorch 00:12:46
    7. Model Training with PyTorch 00:17:18
  9. Chapter 9 : CIFAR 10 Classification – PyTorch
    1. The CIFAR 10 Dataset 00:01:44
    2. Testing LeNet 00:09:52
    3. Hyperparameter Tuning 00:07:52
    4. Data Augmentation 00:12:26
  10. Chapter 10 : Transfer Learning – PyTorch
    1. Pre-trained Sophisticated Models 00:14:41
    2. AlexNet and VGG16 00:27:35
  11. Chapter 11 : Style Transfer – PyTorch
    1. VGG 19 00:09:45
    2. Image Transforms 00:17:27
    3. Feature Extraction 00:12:09
    4. The Gram Matrix 00:12:01
    5. Optimization 00:25:12
    6. Style Transfer with Video 00:09:49
  12. Chapter 12 : Appendix A - Python Crash Course
    1. Overview 00:01:11
    2. Anaconda Installation (Mac) 00:02:37
    3. Anaconda Installation Windows 00:02:49
    4. Jupyter Notebooks 00:01:39
    5. Arithmetic Operators 00:04:11
    6. Variables 00:05:05
    7. Numeric Data Types 00:04:10
    8. String 00:05:42
    9. Booleans 00:04:10
    10. Methods 00:03:04
    11. Lists 00:05:32
    12. Slicing 00:08:16
    13. Membership Operator 00:02:51
    14. Mutability 00:04:09
    15. Mutability II 00:04:45
    16. Common Functions & Methods 00:07:32
    17. Tuples 00:03:21
    18. Sets 00:02:58
    19. Dictionaries 00:05:16
    20. Compound Data Structures 00:02:50
    21. Part 1 – Outro 00:00:15
    22. Part 2 - Control Flow 00:00:47
    23. If, else 00:04:47
    24. elseif 00:06:53
    25. Complex Comparisons 00:05:11
    26. For Loops 00:07:18
    27. For Loops II 00:03:07
    28. While Loops 00:03:07
    29. Break 00:03:24
    30. Part 2 – Outro 00:00:17
    31. Part 3 – Functions 00:00:52
    32. Functions 00:05:25
    33. Scope 00:01:45
    34. Doc Strings 00:02:45
    35. Lambda and Higher Order Functions 00:06:08
    36. Part 3 – Outro 00:00:24
  13. Chapter 13 : Appendix B - NumPy Crash Course
    1. Overview 00:00:49
    2. Arrays vs Lists 00:12:03
    3. Multidimensional Arrays 00:11:46
    4. One Dimensional Slicing 00:03:33
    5. Reshaping 00:03:35
    6. Multidimensional Slicing 00:07:21
    7. Manipulating Array Shapes 00:08:17
    8. Matrix Multiplication 00:04:19
    9. Stacking 00:13:51
    10. Outro 00:00:09
  14. Chapter 14 : Appendix C - Softmax Explanation
    1. Softmax 00:11:46
    2. Cross Entropy 00:08:02