HOT
blank

Generative Adversarial Networks (GANs): Complete Guide

Development

Rating4.2
Enroll Now

Generative Adversarial Networks (GANs): Complete Guide, available at $79.99, has an average rating of 4.16, with 112 lectures, based on 229 reviews, and has 3054 subscribers.

You will learn about Understand the basic intuition about GANs Generate images of digits (0 – 9) using DCGAN and WGAN Transform satellite images into maps using Pix2Pix architecture Transform zebras into horses using CycleGAN architecture Transfer styles between images Apply super resolution to improve image quality using ESRGAN architecture Create new faces of people with high quality and definition using StyleGAN Generate images through textual descriptions Restore old photos using GFP-GAN Complete missing parts of images using Boundless architecture Generate deepfakes to swap faces with SimSwap This course is ideal for individuals who are People interested in creating complex applications using GANs or Undergraduate and graduate students who are taking courses on Computer Vision, Artificial Intelligence, Digital Image Processing or Computer Vision or People who want to implement their own projects using Computer Vision techniques or Data Scientists who want to increase their project portfolio It is particularly useful for People interested in creating complex applications using GANs or Undergraduate and graduate students who are taking courses on Computer Vision, Artificial Intelligence, Digital Image Processing or Computer Vision or People who want to implement their own projects using Computer Vision techniques or Data Scientists who want to increase their project portfolio.

Enroll now: Generative Adversarial Networks (GANs): Complete Guide

Summary

Title: Generative Adversarial Networks (GANs): Complete Guide

Price: $79.99

Average Rating: 4.16

Number of Lectures: 112

Number of Published Lectures: 112

Number of Curriculum Items: 112

Number of Published Curriculum Objects: 112

Original Price: $19.99

Quality Status: approved

Status: Live

What You Will Learn

  • Understand the basic intuition about GANs
  • Generate images of digits (0 – 9) using DCGAN and WGAN
  • Transform satellite images into maps using Pix2Pix architecture
  • Transform zebras into horses using CycleGAN architecture
  • Transfer styles between images
  • Apply super resolution to improve image quality using ESRGAN architecture
  • Create new faces of people with high quality and definition using StyleGAN
  • Generate images through textual descriptions
  • Restore old photos using GFP-GAN
  • Complete missing parts of images using Boundless architecture
  • Generate deepfakes to swap faces with SimSwap

Who Should Attend

  • People interested in creating complex applications using GANs
  • Undergraduate and graduate students who are taking courses on Computer Vision, Artificial Intelligence, Digital Image Processing or Computer Vision
  • People who want to implement their own projects using Computer Vision techniques
  • Data Scientists who want to increase their project portfolio

Target Audiences

  • People interested in creating complex applications using GANs
  • Undergraduate and graduate students who are taking courses on Computer Vision, Artificial Intelligence, Digital Image Processing or Computer Vision
  • People who want to implement their own projects using Computer Vision techniques
  • Data Scientists who want to increase their project portfolio

GANs (Generative Adversarial Networks) are considered one of the most modern and fascinating technologies within the field of Deep Learning and Computer Vision. They have gained a lot of attention because they can create fake content. One of the most classic examples is the creation of people who do not exist in the real world to be used to broadcast television programs. This technology is considered a revolution in the field of Artificial Intelligence for producing high quality results, remaining one of the most popular and relevant topics.

In this course you will learn the basic intuition and mainly the practical implementation of the most modern architectures of Generative Adversarial Networks! This course is considered a complete guide because it presents everything from the most basic concepts to the most modern and advanced techniques, so that in the end you will have all the necessary tools to build your own projects! See below some of the projects that you are going to implement step by step:

  • Creating of digits from 0 to 9

  • Transforming satellite images into map images, like Google Maps style

  • Convert drawings into high-quality photos

  • Create zebras using horse images

  • Transfer styles between images using paintings by famous artists such as Van Gogh, Cezanne and Ukiyo-e

  • Increase the resolution of low quality images (super resolution)

  • Generate deepfakes (fake faces) with high quality

  • Create images through textual descriptions

  • Restore old photos

  • Complete missing parts of images

  • Swap the faces of people who are in different environments

To implement the projects, you will learn several different architectures of GANs, such as: DCGAN (Deep Convolutional Generative Adversarial Network), WGAN (Wassertein GAN), WGAN-GP (Wassertein GAN-Gradient Penalty), cGAN (conditional GAN), Pix2Pix (Image-to-Image), CycleGAN (Cycle-Consistent Adversarial Network), SRGAN (Super Resolution GAN), ESRGAN (Enhanced Super Resolution GAN), StyleGAN (Style-Based Generator Architecture for GANs), VQ-GAN (Vector Quantized Generative Adversarial Network), CLIP (Contrastive Language–Image Pre-training), BigGAN, GFP-GAN (Generative Facial Prior GAN), Unlimited GAN (Boundless) and SimSwap (Simple Swap).

During the course, we will use the Python programming language and Google Colab online, so you do not have to worry about installing and configuring libraries on your own machine! More than 100 lectures and 16 hours of videos!

Course Curriculum

Chapter 1: Introduction

Lecture 1: Course content

Lecture 2: Introduction to GANs

Lecture 3: How GANs work

Lecture 4: Course materials

Chapter 2: DCGAN and WGAN

Lecture 1: DCGAN – intuition

Lecture 2: MNIST dataset

Lecture 3: Building the generator

Lecture 4: Building the discriminator

Lecture 5: Loss (error) calculation

Lecture 6: A quick note about the code

Lecture 7: Training

Lecture 8: Visualizing the results

Lecture 9: HOMEWORK and solution

Lecture 10: WGAN – intuition 1

Lecture 11: WGAN – intuition 2

Lecture 12: WGAN-GP – intuition

Lecture 13: Preparing the environment

Lecture 14: Wassertein loss

Lecture 15: Gradient penalty

Lecture 16: Training 1

Lecture 17: Training 2 and visualization

Lecture 18: HOMEWORK and solution

Chapter 3: cGAN – Pix2Pix and CycleGAN

Lecture 1: cGAN – intuition

Lecture 2: Pix2Pix – intuition

Lecture 3: Map dataset

Lecture 4: Preprocessing the images 1

Lecture 5: Preprocessing the images 2

Lecture 6: Loading the data

Lecture 7: Building the generator 1

Lecture 8: Building the generator 2

Lecture 9: Building the generator 3

Lecture 10: Building the discriminator 1

Lecture 11: Building the discriminator 2

Lecture 12: Generating the images

Lecture 13: Training 1

Lecture 14: Training 2 and results

Lecture 15: Pretrained Pix2Pix with PyTorch

Lecture 16: Facades dataset

Lecture 17: Visualizing the results

Lecture 18: Drawing to photo 1

Lecture 19: Drawing to photo 2

Lecture 20: Night to day

Lecture 21: HOMEWORK and solution

Lecture 22: CycleGAN – intuition

Lecture 23: Change in the dataset URL

Lecture 24: Apples and orange dataset

Lecture 25: Preprocessing

Lecture 26: Loading the images

Lecture 27: Generator and discriminator

Lecture 28: Loss function

Lecture 29: Optimizers and checkpoint

Lecture 30: Training 1

Lecture 31: Training 2 and results

Lecture 32: Pretrained CycleGAN with PyTorch

Lecture 33: Horse to zebra

Lecture 34: Style transfer

Lecture 35: Van Gogh, Cezanne and Ukiyo-e styles

Lecture 36: HOMEWORK and solution

Chapter 4: SRGAN and ESRGAN

Lecture 1: SRGAN – intuition

Lecture 2: ESRGAN – intuition

Lecture 3: Pretrained model

Lecture 4: Testing images

Lecture 5: Super resolution

Lecture 6: Evaluating the results – PSNR

Lecture 7: Improving the results

Lecture 8: HOMEWORK and solution

Chapter 5: StyleGAN

Lecture 1: ProGAN – intuition

Lecture 2: StyleGAN – intuition

Lecture 3: Pretrained model

Lecture 4: Generating images 1

Lecture 5: Generating images 2

Lecture 6: Generating images 3

Lecture 7: Interpolation

Lecture 8: Other pretrained models

Lecture 9: HOMEWORK and solution

Chapter 6: VQGAN + CLIP – text to image

Lecture 1: VQGAN + CLIP – intuition

Lecture 2: Warning after lib update

Lecture 3: Pretrained model

Lecture 4: GAN settings

Lecture 5: Visualizing the results

Lecture 6: Results in videos

Lecture 7: HOMEWORK and solution

Chapter 7: Other types of GANs

Lecture 1: BigGAN – intuition

Lecture 2: Pretrained model

Lecture 3: GAN settings

Lecture 4: Generating new images 1

Lecture 5: Generating new images 2

Lecture 6: GFP-GAN to restore old photos

Lecture 7: Pretrained model

Lecture 8: Photo restoration

Lecture 9: Boundless for image extension

Lecture 10: Processing the image

Lecture 11: Visualizing the results

Instructors

Rating Distribution

  • 1 stars: 4 votes
  • 2 stars: 4 votes
  • 3 stars: 14 votes
  • 4 stars: 78 votes
  • 5 stars: 129 votes

Frequently Asked Questions


How long do I have access to the course materials?


You can view and review the lecture materials indefinitely, like an on-demand channel.


Can I take my courses with me wherever I go?


Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!

You may also like

Top 10 Ethical AI Courses to Learn in November 2024

Top 10 Game Development Courses to Learn in November 2024

Top 10 Software Testing Courses to Learn in November 2024