Generative Adversarial Networks (GANs): Complete Guide

Focused View

Jones Granatyr,IA Expert Academy,Gabriel Alves

9:54:03

82 View

1. Introduction

1. Course content.mp4

15:09

2. Introduction to GANs.mp4

18:21

3. How GANs work.mp4

13:37

4. Course materials.html

2. DCGAN and WGAN

1.1 Source code - Google Colab.html

1. DCGAN - intuition.mp4

08:13

2. MNIST dataset.mp4

17:05

3. Building the generator.mp4

19:53

4. Building the discriminator.mp4

12:03

5. Loss (error) calculation.mp4

10:27

6. Training.mp4

12:32

7. Visualizing the results.mp4

11:07

8. HOMEWORK and solution.html

9.1 Source code - Google Colab.html

9. WGAN - intuition 1.mp4

16:53

10. WGAN - intuition 2.mp4

12:29

11. WGAN-GP - intuition.mp4

06:16

12. Preparing the environment.mp4

05:52

13. Wassertein loss.mp4

09:15

14. Gradient penalty.mp4

16:01

15. Training 1.mp4

12:34

16. Training 2 and visualization.mp4

13:05

17. HOMEWORK and solution.html

3. cGAN - Pix2Pix and CycleGAN

1. cGAN - intuition.mp4

13:32

2.1 Source code - Google Colab.html

2. Pix2Pix - intuition.mp4

13:54

3. Map dataset.mp4

09:13

4. Preprocessing the images 1.mp4

08:59

5. Preprocessing the images 2.mp4

16:56

6. Loading the data.mp4

09:03

7. Building the generator 1.mp4

19:36

8. Building the generator 2.mp4

21:39

9. Building the generator 3.mp4

08:37

10. Building the discriminator 1.mp4

16:00

11. Building the discriminator 2.mp4

06:15

12. Generating the images.mp4

06:35

13. Training 1.mp4

13:49

14. Training 2 and results.mp4

22:23

15.1 Source code - Google Colab.html

15. Pretrained Pix2Pix with PyTorch.mp4

11:58

16. Facades dataset.mp4

04:54

17. Visualizing the results.mp4

08:39

18. Drawing to photo 1.mp4

05:14

19. Drawing to photo 2.mp4

11:37

20. Night to day.mp4

03:23

21. HOMEWORK and solution.html

4. Additional content 1 Artificial neural networks

1. Biological fundamentals.mp4

05:42

2. Single layer perceptron.mp4

19:23

3. Multilayer perceptron sum and activation functions.mp4

14:20

4. Multilayer perceptron error calculation.mp4

05:19

5. Gradient descent.mp4

09:49

6. Delta parameter.mp4

08:09

7. Updating weights with backpropagation.mp4

14:03

8. Bias, error, stochastic gradient descent, and more parameters.mp4

17:56

5. Additional content 2 Convolution neural networks

1. Introduction to convolutional neural networks.mp4

07:18

2. Convolutional operator.mp4

10:04

3. Pooling.mp4

05:28

4. Flattening.mp4

06:31

5. Dense neural network.mp4

05:10

6. Final remarks

1. Final remarks.mp4

01:43

Description

Deep Learning and Computer Vision to implement projects using one of the most revolutionary technologies in the world!

What You'll 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 is this for?

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

What You Need to Know?

Programming logic

Basic Python programming

Knowledge about neural networks is desirable, but not mandatory

More details

Description
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 Languageâ€“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!
Who this course is for:
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

User Reviews

Rating

average 0

Total votes0

Focused display

Olá! Meu nome é Jones Granatyr e já trabalho em torno de 10 anos com Inteligência Artificial (IA), inclusive fiz o meu mestrado e doutorado nessa área. Atualmente sou professor, pesquisador e fundador do portal IA Expert, um site com conteúdo específico sobre Inteligência Artificial. Desde que iniciei na Udemy criei vários cursos sobre diversos assuntos de IA, como por exemplo: Deep Learning, Machine Learning, Data Science, Redes Neurais Artificiais, Algoritmos Genéticos, Detecção e Reconhecimento Facial, Algoritmos de Busca, Mineração de Textos, Buscas em Textos, Mineração de Regras de Associação, Sistemas Especialistas e Sistemas de Recomendação. Os cursos são abordados em diversas linguagens de programação (Python, R e Java) e com várias ferramentas/tecnologias (tensorflow, keras, pandas, sklearn, opencv, dlib, weka, nltk, por exemplo). Meu principal objetivo é desmistificar a área de IA e ajudar profissionais de TI a entenderem como essa tecnologia pode ser utilizada na prática e que possam visualizar novas oportunidades de negócios.

IA Expert Academy

Instructor's Courses

A plataforma IA Expert tem o objetivo de trazer cursos teóricos e práticos de fácil entendimento sobre sobre Inteligência Artificial e Ciência de Dados, para que profissionais de todas as áreas consigam entender e aplicar os benefícios que a IA pode trazer para seus negócios, bem como apresentar todas as oportunidades que essa área pode trazer para profissionais de tecnologia da informação. Também trazemos notícias atualizadas semanais sobre a área em nosso portal.

Gabriel Alves

Instructor's Courses

Olá, eu me chamo Gabriel Alves e sou formado em Ciência da Computação pela Universidade do Contestado (UnC) de Porto União. Também possuo Curso Técnico em Informática pelo Colégio Técnico de União da Vitória (COLTEC), concluído em 2014. Trabalho como desenvolvedor web há 7 anos, mas já lido com programação há mais de 9 anos. Em meus projetos faço o uso de várias linguagens, especialmente Python, a qual tenho preferência para utilizar no desenvolvimento das minhas pesquisas relacionadas a Inteligência Artificial e Aprendizagem de Máquina. Sou desde sempre apaixonado pela computação e por temas que envolvem ciência e tecnologia.

Udemy

View courses Udemy

Students take courses primarily to improve job-related skills.Some courses generate credit toward technical certification. Udemy has made a special effort to attract corporate trainers seeking to create coursework for employees of their company.