Description

In this course, you will be learning one of the widely used deep learning frameworks, that is, PyTorch, and learn the basics of convolutional neural networks in PyTorch. We will also cover the basics of Python and understand how to implement different Python libraries.

Note: The course is primarily focused on teaching PyTorch and deep learning for computer vision, but it also includes a few sections on the fundamentals of Python (Sections 8-12). These optional learning sections are designed for individuals who may be new to Python or who want to refresh their knowledge of Python basics. In this course, we will take a step-by-step method by first grasping PyTorch's fundamentals. Then, using a guide to getting free GPU for learning, you will learn how to code in GPU. You will then learn about PyTorch's AutoGrad feature and how to use it. Later, you will learn how to use PyTorch to create deep learning models and understand the fundamentals of convolutional neural networks (CNN). You will also learn how to use CNN with a real-world dataset. Additionally, the course will emphasize the fundamentals and lay the groundwork for an understanding of Python. We will also talk about the three significant Python libraries known as NumPy, Pandas, and Matplotlib. In this part of the course, we will also build a mini project where we will be building a hangman game in Python. By the end of this course, we will be able to perform Computer Vision tasks with deep learning. All the resources for this course are available at: https://github.com/PacktPublishing/Deep-Learning---Computer-Vision-for-Beginners-Using-PyTorch

What You Will Learn

Learn how to work with PyTorch
Build intuition on convolution operation on images
Implement gradient descent using AutoGrad
Learn about LeNet architecture
Create a mini-Python project game
Understand how to use NumPy, Pandas, and Matplotlib libraries

Audience

Software developers, machine learning practitioners, data scientists, and anybody else interested in understanding PyTorch and deep learning should take this course. While a basic knowledge of Python would be beneficial, it is not a prerequisite as we will be covering the necessary fundamentals during the course.

Approach

This is a step-by-step learning course where we will start with the basics and move toward real-world implementation. You will also learn the basics of Python programming and build a mini project to test our learning in the real world.

Key Features

Learn how to perform Computer Vision tasks with deep learning * Learn to implement LeNet architecture on CIFAR10 dataset, which has 60,000 images * Build your programming foundation with Python

Github Repo

https://github.com/PacktPublishing/Deep-Learning---Computer-Vision-for-Beginners-Using-PyTorch

About the Author

Manifold AI Learning

Manifold AI Learning is an online academy with the goal to empower students with the knowledge and skills that can be directly applied to solving real-world problems in data science, machine learning, and artificial intelligence. With a curated curriculum and a hands-on guide, you will always be an industry-ready professional.

Course Outline

1. Welcome Aboard

Welcome to the course! This is a quick introductory section.

1. Course Introduction

In this video, we will have a quick course introduction.

2. Why Is PyTorch Powerful?

In this video, we will look at a quick demo and understand why PyTorch is powerful.

2. Introduction to PyTorch and Tensors

In this section, we will get introduced to PyTorch and Tensors.

1. What Is PyTorch

In this video, we will get a brief introduction to PyTorch.

3. Diving into PyTorch

In this section, we will dive into PyTorch and get in action.

1. Installing PyTorch

In this video, you will learn how to install PyTorch using Google Colab ipynb.

2. Create Tensors in PyTorch

In this video, you will learn how to create Tensors in PyTorch.

3. Tensor Slicing and Reshape

In this video, you will learn how to reshape and slice a Tensor.

4. Mathematical Operations on Tensors

In this video, let's see how we can perform mathematical operations on Tensors.

5. NumPy in PyTorch

In this video, you will learn how to convert a NumPy array in PyTorch.

6. What Is CUDA

In this video, we will first understand what CUDA is and then see it in action.

7. PyTorch on GPU

In this video, we will test the competition speed with GPU.

4. AutoGrad in PyTorch

In this section, we will have a look at AutoGrad in PyTorch.

1. AutoGrad in PyTorch

In this video, you will learn what is AutoGrad in PyTorch.

2. AutoGrad in a Loop

In this video, you will learn to implement the AutoGrad function in a loop.

5. Creating Deep Neural Networks in PyTorch

In this section, we will be working on creating a deep neural network in PyTorch.

1. Building the First Neural Network

In this video, you will learn how to build your first neural network.

2. Writing a Deep Neural Network

In this video, you will learn how to write a deep neural network.

3. Writing a Custom NN Module

In this video, you will learn how to write a custom NN (Neural Network) module.

6. CNN in PyTorch

In this section, you will learn how to implement a convolutional neural network in PyTorch.

1. Data Loading - CIFAR10

In this video, you will learn how to load our CIFAR10 dataset in PyTorch.

2. Data Visualization

In this video, you will learn how to visualize your data to understand it better.

3. CNN Recap

In this video, we will have a quick recap on the convolution operation.

4. First CNN

In this video, we will work on building our first convolution layer.

5. CNN Deep Layers

In this video, you will learn how to perform a series of convolution operations to the required output.

7. LeNet Architecture in PyTorch

In this section, you will learn how to implement the LeNet architecture in PyTorch.

1. LeNet Overview

In this video, let's first understand what LeNet architecture is.

2. LeNet Model in PyTorch

In this video, you will learn how to implement the LeNet model in PyTorch.

3. Preparation and Evaluation

In this video, you will learn how to train our LeNet model.

8. Optional Learning- Python Basics

In this section, you will be learning the basics of Python.

1. Why Learn Any Programming Language

In this video, we will first understand why we should learn any programming language.

2. Why Choose Python

In this video, we will understand the benefits of Python.

3. Installing Jupyter Notebook

In this video, you will learn how to install Jupyter Notebook.

4. Jupyter Notebook - Tips and Tricks

In this video, you will learn some useful tips and tricks of working in Jupyter Notebook.

5. What We Will Cover in This Section

In this video, we will understand the learning objective of the Python basics section.

6. Variables in Python

In this video, you will learn about variables in Python.

7. Print Function

In this video, you will learn about the Print function.

8. Numerical Data Types and Arithmetic Operations in Python

In this video, you will learn about numerical data types and arithmetic operations in Python.

9. String Data Type

In this video, you will learn about the string data type.

10. Boolean Data Type

In this video, we will understand the Boolean data type.

11. Type Conversion and Type Casting

In this video, we will understand how to convert one data type to another data type.

12. Adding Comments in Python Programming Language

In this video, you will learn how to add comments to our programs.

13. Data Structures in Python

In this video, we will understand the data structures in Python.

14. Tuples and Sets in Python

In this video, you will learn about tuples and sets in Python.

15. Python Dictionaries

In this video, you will learn about Python dictionaries.

16. Conditional Statements in Python - if

In this video, you will learn about the "If" conditional statement and how to implement it.

17. Conditional Statements in Python - While

In this video, you will learn about the "While" conditional statement and how to implement it.

18. Inbuilt Functions in Python - range and input

In this video, you will learn two important inbuilt functions in Python, which are range and input functions.

19. For Loops

In this video, you will learn about for loops.

20. Functions in Python

In this video, you will learn about functions in Python.

21. Classes in Python

In this video, you will learn about classes in Python.

9. Optional Learning - Mini Project with Python Basics

In this section, we will be working on a mini project where we will implement our learning from the Python basics section.

1. Mini Project - Hangman

In this video, we will get introduced to our mini project, which is called the Hangman.

2. Writing a Class

In this video, we will start writing the program for our classes and objects.

3. Mini Project - Continued

In this video, we will continue writing the program for our hangman game.

4. Logic Building

In this video, we will work on building the logic.

5. Logic for Single-Letter input

In this video, we will continue building the logic for single-letter input.

6. Final Testing

In this video, we will run our project and check whether our program runs as required.

10. Optional Learning - Python for Data Science with NumPy

IN this section, we will understand how to work with the NumPy library.

1. NumPy

In this video, we will first understand how to create arrays using NumPy library.

2. Resize and Reshape Arrays

In this video, you will learn how to resize and reshape an array.

3. Slicing

In this video, we will understand how to perform slicing on NumPy arrays.

4. Broadcasting

In this video, we will understand the concept of broadcasting.

5. Mathematical Operations and Functions in NumPy

In this video, we will understand the different mathematical operations and functions that we can perform on NumPy arrays.

11. Optional Learning - Python for Data Science with Pandas

In this section, you will learn about Pandas.

1. Pandas Library

In this video, you will learn about the Pandas library.

2. Pandas Dataframe

In this video, you will learn about Pandas Dataframe.

3. Pandas Dataframe - Load from External File

In this video, you will learn how to load the data to our dataframe from an external file.

4. Working with Null Values

In this video, you will learn how to work with null values.

5. Slicing Pandas Dataframe

In this video, we will understand how we can return the required elements from our dataframe using the concept of slicing.

6. Imputation

In this video, we will understand how to perform imputation on our dataframe.

12. Optional Learning - Python for Data Science with Matplotlib

In this section, we will talk about Matplotlib.

1. Matplotlib Introduction

In this video, we will get introduced to Matplotlib.

2. Format the Plot

In this video, you will learn how to format our Matplotlib plot.

3. Plot Formatting and Scatter Plot

In this video, we will cover plot formatting and scatter plot.

4. Histplot

In this video, you will learn how to create a Histplot.

Course Images

Deep Learning - Computer Vision for Beginners Using PyTorch

By Packt

Booking options

Highlights