Description

Learn to build highly sophisticated deep learning and Computer Vision applications with PyTorch

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 of the deep learning domain with its flexibility and has made building deep learning models easier. The development world offers some of the highest paying jobs in deep learning. In this exciting course, instructor Rayan Slim will help you learn and master deep learning with PyTorch. Having taught over 44,000 students, Rayan is a highly rated and experienced instructor who has followed a learning-by-doing style to create this course. You'll go from a beginner to deep learning expert with your instructor completing each step of the task with you. By the end of this 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 organization.
All the code and supporting files for this course are available at https://github.com/PacktPublishing/PyTorch-for-Deep-Learning-and-Computer-Vision

What You Will Learn

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
Solve complex problems in Computer Vision by harnessing highly sophisticated pre-trained models
Use style transfer to build sophisticated AI applications

Audience

This course is for you if you're interested in deep learning and Computer Vision. Anyone (no matter the skill level) who wants to transition into the field of artificial intelligence and entrepreneurs with an interest in working on some of the most cutting-edge technologies will find this course useful.

Approach

This course will take you right from the basics to building state-of-the-art deep learning and Computer Vision applications with PyTorch.

Key Features

This course is designed to help you become an accomplished deep learning developer even with no experience in programming or mathematics

Github Repo

https://github.com/packtpublishing/pytorch-for-deep-learning-and-computer-vision

Course Outline

1. Introduction

In this section, we are introduced to build state-of-the art Deep Learning and Computer Vision applications with PyTorch.

1. Introduction

Introduction: Introduction

2. Getting Started

In this section, we look into where can access the code files and projects.

1. Finding the codes (Github)

Getting Started: Finding the codes (Github)

2. (Free Preview): A Look at the Projects

Getting Started: A Look at the Projects

3. Intro to Tensors - PyTorch

In this section, we learn how to work with the tensor data structure.

1. Intro

Intro to Tensors - PyTorch: Intro

2. (Free Preview): 1 Dimensional Tensors

Intro to Tensors - PyTorch: 1 Dimensional Tensors

3. Vector Operations

Intro to Tensors - PyTorch: Vector Operations

4. 2 Dimensional Tensors

Intro to Tensors - PyTorch: 2 Dimensional Tensors

5. Slicing 3D Tensors

Intro to Tensors - PyTorch: Slicing 3D Tensors

6. Matrix Multiplication

Intro to Tensors - PyTorch: Matrix Multiplication

7. Gradient with PyTorch

Intro to Tensors - PyTorch: Gradient with PyTorch

8. Outro

Intro to Tensors - PyTorch: Outro

4. Linear Regression - PyTorch

This section is for you to get familiar with Machine Learning algorithm and trailing in linear model to properly fit a set of data points.

1. Intro

Linear Regression - PyTorch: Intro

2. Making Predictions

Linear Regression - PyTorch: Making Predictions

3. Linear Class

Linear Regression - PyTorch: Linear Class

4. Custom Modules

Linear Regression - PyTorch: Custom Modules

5. Creating Dataset

Linear Regression - PyTorch: Creating Dataset

6. Loss Function

Linear Regression - PyTorch: Loss Function

7. Gradient Descent

Linear Regression - PyTorch: Gradient Descent

8. Mean Squared Error

Linear Regression - PyTorch: Mean Squared Error

9. Training - Code Implementation

Linear Regression - PyTorch: Training - Code Implementation

10. Outro

Linear Regression - PyTorch: Outro

5. Perceptrons - PyTorch

We will make use of this section to cover any concepts of Perceptron's in great depth.

1. Intro

Perceptrons - PyTorch: Intro

2. What is Deep Learning

Perceptrons - PyTorch: What is Deep Learning

3. Creating Dataset

Perceptrons - PyTorch: Creating Dataset

4. Perceptron Model

Perceptrons - PyTorch: Perceptron Model

5. Model Setup

Perceptrons - PyTorch: Model Setup

6. Model Training

Perceptrons - PyTorch: Model Training

7. Model Testing

Perceptrons - PyTorch: Model Testing

8. Outro

Perceptrons - PyTorch: Outro

6. Deep Neural Networks - PyTorch

In this section, we learn to build deep Neural Networks from scratch.

1. Intro

Deep Neural Networks - PyTorch: Intro

2. Non-Linear Boundaries

Deep Neural Networks - PyTorch: Non-Linear Boundaries

3. Architecture

Deep Neural Networks - PyTorch: Architecture

4. Feedforward Process

Deep Neural Networks - PyTorch: Feedforward Process

5. Error Function

Deep Neural Networks - PyTorch: Error Function

6. Backpropagation

Deep Neural Networks - PyTorch: Backpropagation

7. Code Implementation

Deep Neural Networks - PyTorch: Code Implementation

8. Testing Model

Deep Neural Networks - PyTorch: Testing Model

9. Outro

Deep Neural Networks - PyTorch: Outro

7. Image Recognition - PyTorch

In this section, we are going to explore image datasets, talk about how we are going to use deep neural networks to have a model fit image data, we also extent our discussion to validation sets to validate neural nets.

1. Intro

Image Recognition - PyTorch: Intro

2. MNIST Dataset

Image Recognition - PyTorch: MNIST Dataset

3. Training and Test Datasets

Image Recognition - PyTorch: Training and Test Datasets

4. Image Transforms

Image Recognition - PyTorch: Image Transforms

5. Neural Network Implementation

Image Recognition - PyTorch: Neural Network Implementation

6. Neural Network Validation

Image Recognition - PyTorch: Neural Network Validation

7. Final Tests

Image Recognition - PyTorch: Final Tests

8. A note on adjusting batch size

Image Recognition - PyTorch: A note on adjusting batch size

9. Outro

Image Recognition - PyTorch: Outro

8. Convolutional Neural Networks - PyTorch

In this section, this type of neural network will change the way how we classify neural networks which classifies data with known grid like topology.

1. Convolutions and MNIST

Convolutional Neural Networks - PyTorch: Convolutions and MNIST

2. Convolutional Layer

Convolutional Neural Networks - PyTorch: Convolutional Layer

3. Convolutions II

Convolutional Neural Networks - PyTorch: Convolutions II

4. Pooling

Convolutional Neural Networks - PyTorch: Pooling

5. Fully Connected Network

Convolutional Neural Networks - PyTorch: Fully Connected Network

6. Neural Network Implementation with PyTorch

Convolutional Neural Networks - PyTorch: Neural Network Implementation with PyTorch

7. Model Training with PyTorch

Convolutional Neural Networks - PyTorch: Model Training with PyTorch

9. CIFAR 10 Classification - PyTorch

In this section, we look into CIFAR dataset and learn more about data augmentation.

1. The CIFAR 10 Dataset

CIFAR 10 Classification - PyTorch: The CIFAR 10 Dataset

2. Testing LeNet

CIFAR 10 Classification - PyTorch: Testing LeNet

3. Hyperparameter Tuning

CIFAR 10 Classification - PyTorch: Hyperparameter Tuning

4. Data Augmentation

CIFAR 10 Classification - PyTorch: Data Augmentation

10. Transfer Learning - PyTorch

In this section, we look into AlexNet and VGG16.

1. Pre-trained Sophisticated Models

Transfer Learning - PyTorch: Pre-trained Sophisticated Models

2. AlexNet and VGG16

Transfer Learning - PyTorch: AlexNet and VGG16

11. Style Transfer - PyTorch

In this section, use style transfer to build sophisticated AI applications.

1. VGG 19

Style Transfer - PyTorch: VGG 19

2. Image Transforms

Style Transfer - PyTorch: Image Transforms

3. Feature Extraction

Style Transfer - PyTorch: Feature Extraction

4. The Gram Matrix

Style Transfer - PyTorch: The Gram Matrix

5. Optimization

Style Transfer - PyTorch: Optimization

6. Style Transfer with Video

Style Transfer - PyTorch: Style Transfer with Video

12. Appendix A - Python Crash Course

This is bonus optional section for Python crash course.

1. Overview

Appendix A - Python Crash Course: Overview

2. Anaconda Installation (Mac)

Appendix A - Python Crash Course: Anaconda Installation (Mac)

3. Anaconda Installation Windows

Appendix A - Python Crash Course: Anaconda Installation Windows

4. Jupyter Notebooks

Appendix A - Python Crash Course: Jupyter Notebooks

5. Arithmetic Operators

Appendix A - Python Crash Course: Arithmetic Operators

6. Variables

Appendix A - Python Crash Course: Variables

7. Numeric Data Types

Appendix A - Python Crash Course: Numeric Data Types

8. String

Appendix A - Python Crash Course: String

9. Booleans

Appendix A - Python Crash Course: Booleans

10. Methods

Appendix A - Python Crash Course: Methods

11. Lists

Appendix A - Python Crash Course: Lists

12. Slicing

Appendix A - Python Crash Course: Slicing

13. Membership Operator

Appendix A - Python Crash Course: Membership Operator

14. Mutability

Appendix A - Python Crash Course: Mutability

15. Mutability II

Appendix A - Python Crash Course: Mutability II

16. Common Functions & Methods

Appendix A - Python Crash Course: Common Functions & Methods

17. Tuples

Appendix A - Python Crash Course: Tuples

18. Sets

Appendix A - Python Crash Course: Sets

19. Dictionaries

Appendix A - Python Crash Course: Dictionaries

20. Compound Data Structures

Appendix A - Python Crash Course: Compound Data Structures

21. Part 1 - Outro

Appendix A - Python Crash Course: Part 1 - Outro

22. Part 2 - Control Flow

Appendix A - Python Crash Course: Part 2 - Control Flow

23. If, else

Appendix A - Python Crash Course: If, else

24. elseif

Appendix A - Python Crash Course: elseif

25. Complex Comparisons

Appendix A - Python Crash Course: Complex Comparisons

26. For Loops

Appendix A - Python Crash Course: For Loops

27. For Loops II

Appendix A - Python Crash Course: For Loops II

28. While Loops

Appendix A - Python Crash Course: While Loops

29. Break

Appendix A - Python Crash Course: Break

30. Part 2 - Outro

Appendix A - Python Crash Course: Part 2 - Outro

31. Part 3 - Functions

Appendix A - Python Crash Course: Part 3 - Functions

32. Functions

Appendix A - Python Crash Course: Functions

33. Scope

Appendix A - Python Crash Course: Scope

34. Doc Strings

Appendix A - Python Crash Course: Doc Strings

35. Lambda and Higher Order Functions

Appendix A - Python Crash Course: Lambda and Higher Order Functions

36. Part 3 - Outro

Appendix A - Python Crash Course: Part 3 - Outro

13. Appendix B - NumPy Crash Course

This is bonus section on NumPy crash course.

1. Overview

Appendix B - NumPy Crash Course: Overview

2. Arrays vs Lists

Appendix B - NumPy Crash Course: Arrays vs Lists

3. Multidimensional Arrays

Appendix B - NumPy Crash Course: Multidimensional Arrays

4. One Dimensional Slicing

Appendix B - NumPy Crash Course: One Dimensional Slicing

5. Reshaping

Appendix B - NumPy Crash Course: Reshaping

6. Multidimensional Slicing

Appendix B - NumPy Crash Course: Multidimensional Slicing

7. Manipulating Array Shapes

Appendix B - NumPy Crash Course: Manipulating Array Shapes

8. Matrix Multiplication

Appendix B - NumPy Crash Course: Matrix Multiplication

9. Stacking

Appendix B - NumPy Crash Course: Stacking

10. Outro

Appendix B - NumPy Crash Course: Outro

14. Appendix C - Softmax Explanation

In this section, the author provides explanation on Softmax and cross entropy.

1. Softmax

Appendix C - Softmax Explanation: Softmax

2. Cross Entropy

Appendix C - Softmax Explanation: Cross Entropy

Course Images

PyTorch for Deep Learning and Computer Vision

By Packt

Booking options

Highlights

Description

Course Content

About The Provider

Tags

Reviews