PyTorch for Deep Learning Bootcamp: Zero to Mastery

Name: PyTorch for Deep Learning Bootcamp: Zero to Mastery
Rating: 4.3 (232 reviews)

Learn How to Use PyTorch (Facebook Library) for Deep Learning with Practical Examples

Created byNavid Shirzadi, PhD, P.Eng.

Last updated 12/2024

English

What you'll learn

Understand the basic concepts about neural network and how it works
Use PyTorch for Linear Regression using Multilayer Perceptron (MLP)
Use PyTorch for image classification using Deep Artificial Neural Network (ANN)
Learn how to work with different data types such as tensors and arrays
Use PyTorch for image classification using Convolutional Neural Network (CNN)
Use PyTorch for time series prediction using Recurrent Neural Network (RNN)

Course content

10 sections • 41 lectures • 9h 20m total length

Course Content9:54
Why Google Colab?1:19
Introduction to Colab Environment9:10
Open Google Colab in your browser, create a new notebook, and rename it; run cells with the run button or shortcuts, and save or export as ipynb, py, or pdf.

Introduction4:57
Convolutional Layer (Image Filter)16:08
Pooling Layer7:09
Flattening2:34
Conclusion3:15
PyTorch Image Classification Using CNN – Part118:33
Build a CNN image classification workflow in PyTorch by loading the CIFAR-10 dataset, applying transforms, normalizing to -1 to 1, and setting up train and test loaders for batch processing.
PyTorch Image Classification Using CNN – Part230:45
PyTorch Image Classification Using CNN – Part313:49
PyTorch Image Classification Using CNN – Part413:58

Introduction to CPU & GPU7:35
Compare CPUs and GPUs, noting sequential processing on CPUs and parallel processing on GPUs with thousands of cores. Learn about NVIDIA CUDA and Colab for PyTorch training.
Watch if You Don't Use Colab!8:18
Install CUDA and enable PyTorch GPU support without Google Colab. Follow the start locally steps for Windows, Linux, or Mac, install CUDA toolkit, update environment variables, then verify with nvidia-smi.
How to Use GPU?19:57
Important Note!0:31
How to Save & Load a Model Using PyTorch18:39

Introduction to Recurrent Neural Network6:01
What is LSTM and How it Works?12:53
PyTorch for Time Series Forecasting Using LSTM-Part127:11
Create an LSTM-based time series forecast in Python with PyTorch on a New York dataset. Normalize with MinMaxScaler, visualize the data, and build 24-hour input windows for train and test.
PyTorch for Time Series Forecasting Using LSTM-Part221:03
PyTorch for Time Series Forecasting Using LSTM-Part313:09
Train a PyTorch LSTM for time series forecasting, resetting hidden and cell states each epoch. Extract batches from X_train and Y_train, compute loss, and backpropagate to update the model.
PyTorch for Time Series Forecasting Using LSTM-Part416:38
Master time series forecasting with PyTorch by testing an LSTM on 24-hour ahead predictions, using a 24-hour window, inverse transforming results, plotting actual vs predicted, and computing mean absolute error.

Requirements

Understanding basic Python topics (Function, for loop, etc.)
Knowing the basics of OOP is recommended

Description

Deep learning has become one of the most popular machine learning techniques in recent years, and PyTorch has emerged as a powerful and flexible tool for building deep learning models. In this course, you will learn the fundamentals of deep learning and how to implement neural networks using PyTorch.

Through a combination of lectures, hands-on coding sessions, and projects, you will gain a deep understanding of the theory behind deep learning techniques such as deep Artificial Neural Networks (ANNs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs). You will also learn how to train and evaluate these models using PyTorch, and how to optimize them using techniques such as stochastic gradient descent and backpropagation. During the course, I will also show you how you can use GPU instead of CPU and increase the performance of the deep learning calculation.

In this course, I will teach you everything you need to start deep learning with PyTorch such as:

NumPy Crash Course
Pandas Crash Course
Neural Network Theory and Intuition
How to Work with Torchvision datasets
Convolutional Neural Network (CNN)
Long-Short Term Memory (LSTM)
and much more

Since this course is designed for all levels (from beginner to advanced), we start with basic concepts and preliminary intuitions.

By the end of this course, you will have a strong foundation in deep learning with PyTorch and be able to apply these techniques to various real-world problems, such as image classification, time series analysis, and even creating your own deep learning applications.

Who this course is for:

beginner to advance python developers, data analysts, engineers and overall data science enthusiast want to learn about deep learning with PyTorch

PyTorch for Deep Learning Bootcamp: Zero to Mastery

What you'll learn

Explore related topics

Course content

Course Introduction & Overview3 lectures • 20min

Useful Packages2 lectures • 37min

PyTorch Tensor Basics2 lectures • 24min

Neural Network Basic Concepts4 lectures • 30min

PyTorch for Multilayer Perceptron (MLP)4 lectures • 1hr 25min

PyTorch for Deep Artificial Neural Network (ANN)5 lectures • 1hr 41min

PyTorch for Convolutional Neural Network (CNN)9 lectures • 1hr 51min

Using GPU Instead of CPU5 lectures • 55min

PyTorch for Recurrent Neural Network6 lectures • 1hr 37min

Bonus!1 lecture • 1min

Requirements

Description

Who this course is for: