Deep Learning with PyTorch

Build useful and effective deep learning models with the PyTorch Deep Learning framework

4.05 (57 reviews)
Udemy
platform
English
language
Data Science
category
303
students
4.5 hours
content
May 2018
last update
$44.99
regular price

What you will learn

Understand PyTorch and Deep Learning concepts

Build your neural network using Deep Learning techniques in PyTorch.

Perform basic operations on your dataset using tensors and variables

Build artificial neural networks in Python with GPU acceleration

See how CNN works in PyTorch with a simple computer vision example

Train your RNN model from scratch for text generation

Use Auto Encoders in PyTorch to remove noise from images

Perform reinforcement learning to solve OpenAI's Cartpole task

Extend your knowledge of Deep Learning by using PyTorch to solve your own machine learning problems

Description

This video course will get you up-and-running with one of the most cutting-edge deep learning libraries: PyTorch. Written in Python, PyTorch is grabbing the attention of all data science professionals due to its ease of use over other libraries and its use of dynamic computation graphs.

In this course, you will learn how to accomplish useful tasks using Convolutional Neural Networks to process spatial data such as images and using Recurrent Neural Networks to process sequential data such as texts. You will explore how you can make use of unlabeled data using Auto Encoders. You will also be training a neural network to learn how to balance a pole all by itself, using Reinforcement Learning. Throughout this journey, you will implement various mechanisms of the PyTorch framework to do these tasks.

By the end of the video course, you will have developed a good understanding of, and feeling for, the algorithms and techniques used. You'll have a good knowledge of how PyTorch works and how you can use it in to solve your daily machine learning problems.

This course uses Python 3.6, and PyTorch 0.3, while not the latest version available, it provides relevant and informative content for legacy users of Python, and PyTorch.

About the Author

Anand Saha is a software professional with 15 years' experience in developing enterprise products and services. Back in 2007, he worked with machine learning to predict call patterns at TATA Communications. At Symantec and Veritas, he worked on various features of an enterprise backup product used by Fortune 500 companies. Along the way he nurtured his interests in Deep Learning by attending Coursera and Udacity MOOCs.

He is passionate about Deep Learning and its applications; so much so that he quit Veritas at the beginning of 2017 to focus full time on Deep Learning practices. Anand built pipelines to detect and count endangered species from aerial images, trained a robotic arm to pick and place objects, and implemented NIPS papers. His interests lie in computer vision and model optimization.

Content

Getting Started With PyTorch

The Course Overview
Introduction to PyTorch
Installing PyTorch on Linux and Windows
Installing CUDA
Introduction to Tensors and Variables
Working with PyTorch and NumPy
Working with PyTorch and GPU
Handling Datasets in PyTorch
Deep Learning Using PyTorch

Training Your First Neural Network

Building a Simple Neural Network
Loss Functions in PyTorch
Optimizers in PyTorch
Training the Neural Network
Saving and Loading a Trained Neural Network
Training the Neural Network on a GPU

Computer Vision – CNN for Digits Recognition

Computer Vision Motivation
Convolutional Neural Networks
The Convolution Operation
Concepts - Strides, Padding, and Pooling
Loading and Using MNIST Dataset
Building the Model
Training and Testing

Sequence Models – RNN for Text Generation

Sequence Models Motivation
Word Embedding
Recurrent Neural Networks
Building a Text Generation Model in PyTorch
Training and Testing

Autoencoder - Denoising Images

Autoencoders Motivation
How Autoencoders Work
Types of Autoencoders
Building Denoising Autoencoder Using PyTorch
Training and Testing

Reinforcement Learning – Balance Cartpole Using DQN

Reinforcement Learning Motivation
Reinforcement Learning Concepts
DQN, Experience Replay
The OpenAI Gym Environment
Building the Cartpole Agent Using DQN
Training and Testing

Screenshots

Deep Learning with PyTorch - Screenshot_01Deep Learning with PyTorch - Screenshot_02Deep Learning with PyTorch - Screenshot_03Deep Learning with PyTorch - Screenshot_04

Reviews

Yaron
June 2, 2021
This is very good course, it pass over most of the deep learning different kind of neural networks. This pass is very detailed and comprehensive, but to my opinion, you have to be a little bit familiar with the subject in order to understand. I recommend on this course .
Isaac
February 13, 2020
Quite good so far, but I am not happy with two things: 1. Not enough on text-based classifiers 2. Not enough on GPU acceleration speedups in performance, the communication overheads were huge for the GPU code mentioned in the talks
John
April 15, 2019
Courses on technology quickly get outdated and this was certainly the case for this course I was finding that the code for all of the exercises didn't run (except for Section 6 which ran just fine). Either the videos need to be updated or the course should have significant addenda to help people who are running the latest versions of Anaconda, PyTorch, CUDA, etc.
Liana
December 9, 2018
I understand how CNN works now. I would strongly recommend anybody who is interested in CNN to take this course first. Follow the explanations folks, this course is money very well spent!
Mitul
December 5, 2018
A Good course for anyone who wishes to quickly get familiar with PyTorch for Deep Learning applications. Concise and well-organized course. Thanks a lot Anand Saha for such an excellent course.
Phil
October 14, 2018
Dude, do not glimpse over setup. If you set something up, tell us. I got distracted while trying to get the Iris data into my collabs- You did not show how you got it and your code did not work. I went through a similar thing with torch.utils.data. I got these to work but it took away attention from learning.
Atharva
June 20, 2018
The instructor should give clear explanations of what is he teaching. Data preprocessing is not done not don but rather skipped. The instructor should explain each line of code, as is required by beginners. Mistake enrolling here.

Charts

Price

Deep Learning with PyTorch - Price chart

Rating

Deep Learning with PyTorch - Ratings chart

Enrollment distribution

Deep Learning with PyTorch - Distribution chart

Related Topics

1691994
udemy ID
5/14/2018
course created date
11/23/2020
course indexed date
Bot
course submited by