Generative Adversarial Networks (GAN) implementations from scratch with PyTorch | Six different GAN Architecture | 7.5 Hours of Video with Code

A Sneak peek of a single video

Black Friday Sale: $12 $17

GANs have been one of the most fascinating developments in Deep Learning and Machine Learning recently.

Also now the technologies around GAN have become so mature, that more and more Industries and Companies are adopting GAN to solve many of the regular problems. (Down below I have mentioned few of them). And hence, the implementation from scratch of various GAN architectures has also become one of the most frequent take-home exercises given by Companies before recruitment for Computer Vision / Deep Learning positions.

This is a code-heavy course with a focus on really understanding and being able to implement the underlying architecture of the most popular GAN frameworks in the industry.

It's a comprehensive seven and half hours (7.5 Hours) of video course on Generative Adversarial Networks (GANs) with each line of code explained while implementing them.

The theories are explained in-depth and in a friendly manner.

What you will get with this Purchase

• All the 7.5 Hours of videos (around 15GB)
• The full Source Code (Python and Jupyter Notebook Files)
• All the future updates to the code.

In this course, I have covered the following Architecture WITH FULL PYTHON CODE IMPLEMENTATIONS AND LINE BY LINE EXPLANATIONS

1. Conditional GAN
2. DCGAN
3. WGAN without Gradient Penalty
4. WGAN WITH Gradient Penalty
5. CycleGAN
6. BiCycleGAN

My courses are the ONLY courses where you will learn how to implement Generative Models machine learning algorithms from scratch

Who is this course for?

• Data scientists willing to take their knowledge and skills to the next level in the area of GANs and Computer Vision
• Research / Postgraduate Students willing to get a comprehensive overview of recent advancement made in the area of GANs
• Deep Learning practitioners willing to apply GANs at work in production environments
• Enthusiasts willing to stay up to date on GANs research and development
• Deep learning beginners willing to master the building blocks of modern GANs
• Anyone who wants to improve their deep learning knowledge

What Can Generative Models do?

Generating novel data samples such as images of non-existent people, animals, objects, etc. Not only images, but other types of media can be generated in this way as well (audio, text).

Image inpainting — restoring missing parts of images.

Image super-resolution — upscaling low-res images to high-res without noticeable upscaling artefacts.

Domain adaptation — making data from one domain resemble the data from the other domain (e.g. making a normal photo look like an oil painting while retaining the originally depicted content).

Denoising — removal of all kinds of noise from the data. For example, removing statistical noise from x-ray images fits medical needs, which will be described in our use cases.

GANs applications are able to solve different tasks:

Generate examples for Image Datasets

Image-to-Image Translation

Text-to-Image Translation

Semantic-Image-to-Photo Translation

Face Frontal View Generation

Generate New Human Poses

Photos to Emojis

Photograph Editing

Face Aging

Photo Blending

Super Resolution

Photo Inpainting

Clothing Translation

Video Prediction

3D Object Generation

By the end you’ll be able to

• Build and train not only the 6 Different GAN Network covered in this Course, but will be able to extend this knowledge to be able to implement various other GAN architecture.

Suggested Prerequisites:

• Python
• The concept of Gradient descent
• Some familiarity with how to build a feedforward and convolutional neural network in PyTorch and TensorFlow

WHAT ORDER SHOULD I TAKE YOUR COURSES IN ?:

Mostly, each of the GAN architecture videos is independently developed. So basically you can follow each of the 6 GANs implementations independently. However, if you are rather new to the concepts of Convolutional Neural Network and the very fundamentals of Deep Neural Network, then I suggest to start with DCGAN (which is the simplest among them all ).

About the Author

Hi, my name is Rohan Paul and I am an Independent Data Scientist (specializing in applied Deep Learning ).

Kaggle Master. Ex Banker. YouTuber.

And previously I have worked as a Full Stack Software Engineer in NodeJS, MongoDB, ReactJS, and Angular Stack in Bangalore (India) Startup scene.

And before coming to the Tech world, I worked in International Banking across India and Australia as a Financial Credit Analyst and Model Builder.

You can find me on Social Media here

**********************************************

🟠 YouTube Channel: https://www.youtube.com/c/rohanpaulai/videos

🐦 TWITTER: https://twitter.com/rohanpaul_ai

👨‍🔧​ Kaggle: https://www.kaggle.com/paulrohan2020

👨🏻‍💼 LINKEDIN: https://www.linkedin.com/in/rohan-paul-b27285129/

👨‍💻 GITHUB: https://github.com/rohan-paul

🤖: My Website and Blog: https://rohan-paul-ai.netlify.app/

🧑‍🦰 Facebook Page: https://www.facebook.com/rohanpaulai/

📸 Instagram: https://www.instagram.com/rohan_paul_2020/

**********************************************