PyTorch Deep Learning in 7 Days
3.9 (9 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
42 students enrolled

PyTorch Deep Learning in 7 Days

Boost your career in one week with the cutting-edge field of Deep Learning with PyTorch
3.9 (9 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
42 students enrolled
Created by Packt Publishing
Last updated 4/2019
English
English [Auto-generated]
Current price: $86.99 Original price: $124.99 Discount: 30% off
5 hours left at this price!
30-Day Money-Back Guarantee
This course includes
  • 2 hours on-demand video
  • 1 downloadable resource
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
Training 5 or more people?

Get your team access to 4,000+ top Udemy courses anytime, anywhere.

Try Udemy for Business
What you'll learn
  • Get comfortable with most commonly used PyTorch concepts, modules and API including Tensor operations, data representations, and manipulation
  • Work with Deep Learning models and architectures including layers, activations, loss functions, gradients, chain rule, forward and backward passes, and optimizers
  • Apply Deep Learning architectures to solve Machine Learning problems for Structured Datasets, Computer Vision, and Natural Language Processing
  • Utilize the concept of Transfer Learning by using pre-trained Deep Learning models to your own problems
  • Implement state of the art in Natural Language Processing to solve real-world problems such as sentiment analysis
  • Implement a simple Generative Adversarial Network to generate fancy images after training on a large image dataset
Requirements
  • Basic knowledge of machine learning concepts and Python programming is required.
Description

PyTorch is Facebook’s latest Python-based framework for Deep Learning. It has the ability to create dynamic Neural Networks on CPUs and GPUs, both with a significantly less code compared to other competing frameworks. PyTorch has a unique interface that makes it as easy to learn as NumPy.

This 7-day course is for those who are in a hurry to get started with PyTorch. You will be introduced to the most commonly used Deep Learning models, techniques, and algorithms through PyTorch code. This course is an attempt to break the myth that Deep Learning is complicated and show you that with the right choice of tools combined with a simple and intuitive explanation of core concepts, Deep Learning is as accessible as any other application development technologies out there. It’s a journey from diving deep into the fundamentals to getting acquainted with the advance concepts such as Transfer Learning, Natural Language Processing and implementation of Generative Adversarial Networks.

By the end of the course, you will be able to build Deep Learning applications with PyTorch.

About the Author

Will Ballard is the chief technology officer at GLG, responsible for engineering and IT. He was also responsible for the design and operation of large data centers that helped run site services for customers including Gannett, Hearst Magazines, NFL, NPR, The Washington Post, and Whole Foods. He has also held leadership roles in software development at NetSolve (now Cisco), NetSpend, and Works (now Bank of America).

Who this course is for:
  • This course is for software development professionals and machine learning enthusiasts, who have heard the hype of Deep Learning and want to learn it to stay relevant in their field.
Course content
Expand all 40 lectures 02:09:18
+ Getting started with PyTorch
7 lectures 23:50

This video will give you an overview about the course.

Preview 02:33

The aim of this video is to dive into a quick introduction to PyTorch.

   •  Get a basic understanding of PyTorch

   •  Know what we can do with Pytorch

   •  Learn how PyTorch compares to Tensorflow and MxNet

Quick Intro to PyTorch
03:02

The aim of this video is to learn the Installation and Jupyter Notebook setup for PyTorch.

   •  Cover PyTorch and Jupyter in VS Code

   •  Take a look at PyTorch Dockerfile

   •  Investigate PyTorch GPU support on Docker

Installation and Jupyter Notebook Setup
03:13

The aim of this video is to learn about the basic tensor operations.

   •  Create Tensors and data types

   •  Create Tensor math

   •  Work with NumPy

Tensors and Basic Tensor Operations
03:44

The aim of this video is to learn about the advanced tensor operations.

   •  Take a look at using the GPU

   •  Discuss Gradients

   •  Perform numerical algebra with PyTorch

Advanced Tensor Operations
06:48

We’ll take a look at loading and saving data with this video.

   •  Work with dataset and dataloader

   •  Take a look at the built in torchvision datasets

Loading and Saving Data
03:50

This video is your homework for day one.

   •  Take a look at the Question and try solving it on your own before the next lecture

Assignment
00:40
+ Building a Neural Network
6 lectures 17:46

The aim of this video is to get introduced to neural networks.

   •  Explore Machine Learning

   •  Get a brief understanding of neural networks and deep learning

   •  Quick visualization of the concepts learnt

Preview 03:29

The aim of this video is to learn to create a neural network with PyTorch Sequential.

   •  Learn the concept of Inputs

   •  Learn the concept of Outputs

   •  Link inputs and outputs with sequential layers

Creating a Neural Network with PyTorch Sequential
02:27

The aim of this video is to learn about activations, loss functions, and gradients.

   •  Add activations to our model

   •  Hook up a loss function

   •  Compute gradients, and know why to use them

Activations, Loss Functions, and Gradients
03:29

The aim of this video is to learn and implement the concepts of forward and backward passes.

   •  Take forward passes to the model

   •  Backward propagate with the computing gradients in the model

   •  Update the model weights

Forward and Backward Passes
03:05

In this video, build a network with nn.module.

   •  Get in-depth understanding of inputs and outputs

   •  Building an object-oriented model

   •  Learn loop using an optimizer

Building a Network with nn.Module
04:45

This video is your homework for day two.

   •  Take a look at the Question and try solving it on your own before the next lecture

Assignment
00:31
+ Regression and Classification
6 lectures 21:04

The aim of this video is to load structured data for classification.

   •  Load a CSV dataset

   •  Train and test the data

Preview 04:20

The aim of this video is to learn about pre-processing data.

   •  Handle categorical values

   •  Transform a Dataset

Preprocessing Data
03:35

The aim of this video is to learn about classification, accuracy, and the confusion matrix.

   •  Build a simple classification network

   •  Run training loops

   •  Use test data with a confusion matrix

Classification, Accuracy, and the Confusion Matrix
04:44

The aim of this video is to load structured data for regression.

   •  Discuss regression versus classification

   •  Encode numbers, categories, and dates

Loading Structured Data for Regression
04:41

The aim of this video is to create neural networks for regression.

   •  Build a simple regression network

   •  Setup the training loops

   •  Take a look at the reporting error

Neural Networks for Regression
03:27

This video is your homework for day three.

   •  Take a look at the Question and try solving it on your own before the next lecture

Assignment
00:17
+ Implementing Convolutional Neural Networks
6 lectures 17:57

With this video, get to study the convolutional networks for image analysis.

   •  Learn what makes a convolutional network

   •  Know why to use convolutional networks

   •  Explore why are convolutional networks effective on images

Preview 03:26

The aim of this video is to get an in-depth understanding of the convolutional concepts.

   •  Learn about Filters and Strides

   •  Study the concept of Pooling and Padding

Convolutional Concepts: Filters, Strides, Padding, and Pooling
03:56

The aim of this video is to implement a convolutional network.

   •  Use torchvision to get image datasets

   •  Look at stacking convolutional layers

   •  Train and evaluate a pre-convolutional network

Implementing a Convolutional Network
03:19

The aim of this video is to visualize a convolutional network layers.

   •  Visualize tensors with matplotlib.pyplot

   •  Augment a network to see intermediate results

   •  Visualize individual image filters

Visualizing Convolutional Network Layers
03:41

The aim of this video is to implementing an end-to-end deep convolutional network.

   •  Base our architecture of the AlexNet

   •  Connect convolutional and fully-connected classifiers

   •  Use CUDA with PyTorch

Implementing an End-To-End Deep Convolutional Network
03:16

This video is your homework for day four.

   •  Take a look at the Question and try solving it on your own before the next lecture

Assignment
00:19
+ Implementing Transfer Learning
5 lectures 17:00

This video aims to explain about transfer learning and prebuilt models.

   •  Learn about transfer learning

   •  Know the use transfer learning

   •  Explore transfer learning gotchas

Transfer Learning and Prebuilt Models
03:03

This video aims to explain about deep learning with VGG.

   •  Explore VGG models in PyTorch

   •  Learn about the input and output layers

   •  Study the different layer patterns

Deep Learning with VGG
03:00

This video aims to explain about transfer learning with VGG.

   •  Load a pre-trained model and use an alternate dataset

   •  Adjust the output layers

   •  Train and validate your network

Transfer Learning with VGG
04:10

This video aims to explain about transfer learning with ResNet.

   •  Compare ResNet to VGG and load a pre-trained model

   •  Use an alternate dataset of MNIST digits and adjust the output layers

   •  Train and validate the network

Transfer Learning with ResNet
06:27

This video is your homework for day five.

   •  Take a look at the Question and try solving it on your own before the next lecture

Assignment
00:20
+ LSTM and Embedding for Natural Language Models
5 lectures 14:20

This video aims to explain about recurrent networks, RNN, and LSTM, GRU.

   •  Take a look at Recurrent networks

   •  Explore LSTM networks

   •  Learn about GRU networks

Recurrent Networks, RNN, and LSTM, GRU
04:01

This video aims to explain about text modeling with bag-of-words approach.

   •  Parse words from text with spaCy

   •  Dive into word ordinal numbers

   •  Explore the sequence of words bag-of-word encodings

Text Modeling with Bag-of-Words
01:33

This video aims to explain about sentiment analysis with bag-of-words technique.

   •  Review the data

   •  Build a PyTorch dataset with one hot encoding

   •  Perform sentiment analysis – predict the rating with regression

Sentiment Analysis with Bag-of-Words
03:29

This video aims to explain about sentiment analysis with word embeddings.

   •  Learn about language models and word embeddings with spaCy

   •  Encode sequences with word embeddings

   •  Perform sentiment analysis

Sentiment Analysis with Word Embeddings
04:59

This video is your homework for day six.

   •  Take a look at the Question and try solving it on your own before the next lecture

Assignment
00:18
+ Deep Convolutional Generative Adversarial Networks
5 lectures 17:21

This video aims to explain about GANs and DCGANs.

   •  Learn about classification, regression, and generation

   •  Learn what a GAN is and what is a DCGAN?

   •  Explore how to train GANs

Introduction to GANs and DCGANs
04:21

This video aims to explain how to implement DCGAN model with PyTorch.

   •  Study about Generator models

   •  Learn about Discriminator models

   •  Implementing DCGAN Model with PyTorch

Implementing DCGAN Model with PyTorch
03:09

This video aims to explain how to train and evaluate DCGAN on an image dataset.

   •  Load up training data

   •  Take a look at Generation vectors and Adversarial training

   •  Visualize generated images

Training and Evaluating DCGAN on an Image Dataset
05:28

This video aims to explain how to improve performance.

   •  Custom initialization

   •  Perform data normalization

   •  Work on improving performance

Improving Performance
02:42

This video is your homework for day seven.

   •  Take a look at the Question and try to solve it on your own

Assignment
01:41