Generative AI, from GANs to CLIP, with Python and Pytorch

Generative AI, from GANs to CLIP, with Python and Pytorch, available at $109.99, has an average rating of 4.51, with 104 lectures, based on 7882 reviews, and has 39021 subscribers.

You will learn about How to code generative A.I architectures from scratch using Python and Pytorch How generative architectures work, in great depth, from GANs to multimodal A.I, understanding every little detail in the process In addition to the coding, every section begins with an in-depth review of the key concepts related to these architectures Examples: We will code a generative network that produces human faces, and also combine two advanced networks to transform text prompts into amazing images. Examples: We will learn to edit the clothes of a person in a picture by combining a segmentation architecture with the Stable Diffusion generative model Special Bonus Section: Journey to the latent space of a neural network, learn in depth how the networks that power Generative AI learn their mappings Special Bonus Section: Experience a guided visualization to exercise the generative model in your head while you learn many things about neural networks This course is ideal for individuals who are People interested in using A.I and deep learning to generate, imagine and create new things or People interested in generative adversarial networks and other advanced A.I generative architectures or People interested in how A.I can combine different modalities (text, images) to create new things (multimodal A.I.) or People interested in learning to code the type of advanced A.I architectures that are the present and future of the field It is particularly useful for People interested in using A.I and deep learning to generate, imagine and create new things or People interested in generative adversarial networks and other advanced A.I generative architectures or People interested in how A.I can combine different modalities (text, images) to create new things (multimodal A.I.) or People interested in learning to code the type of advanced A.I architectures that are the present and future of the field.

Enroll now: Generative AI, from GANs to CLIP, with Python and Pytorch

Summary

Title: Generative AI, from GANs to CLIP, with Python and Pytorch

Price: $109.99

Average Rating: 4.51

Number of Lectures: 104

Number of Published Lectures: 104

Number of Curriculum Items: 104

Number of Published Curriculum Objects: 104

Original Price: €99.99

Quality Status: approved

Status: Live

What You Will Learn

How to code generative A.I architectures from scratch using Python and Pytorch
How generative architectures work, in great depth, from GANs to multimodal A.I, understanding every little detail in the process
In addition to the coding, every section begins with an in-depth review of the key concepts related to these architectures
Examples: We will code a generative network that produces human faces, and also combine two advanced networks to transform text prompts into amazing images.
Examples: We will learn to edit the clothes of a person in a picture by combining a segmentation architecture with the Stable Diffusion generative model
Special Bonus Section: Journey to the latent space of a neural network, learn in depth how the networks that power Generative AI learn their mappings
Special Bonus Section: Experience a guided visualization to exercise the generative model in your head while you learn many things about neural networks

Who Should Attend

People interested in using A.I and deep learning to generate, imagine and create new things
People interested in generative adversarial networks and other advanced A.I generative architectures
People interested in how A.I can combine different modalities (text, images) to create new things (multimodal A.I.)
People interested in learning to code the type of advanced A.I architectures that are the present and future of the field

Target Audiences

People interested in using A.I and deep learning to generate, imagine and create new things
People interested in generative adversarial networks and other advanced A.I generative architectures
People interested in how A.I can combine different modalities (text, images) to create new things (multimodal A.I.)
People interested in learning to code the type of advanced A.I architectures that are the present and future of the field

April 2024 Update: Two new sections have been added recently.
New Section 5: learn to edit the clothes of a person in a picture by programming a combination of a segmentation model with the Stable Diffusion generative model.
New bonus section 6: Journey to the latent space of a neural network – dive deep into the latent space of the neural networks that power Generative AI in order to understand in depth how they learn their mappings.
____________________________

Generative A.I. is the present and future of A.I. and deep learning, and it will touch every part of our lives. It is the part of A.I that is closer to our unique human capability of creating, imagining and inventing. By doing this course, you gain advanced knowledge and practical experience in the most promising part of A.I., deep learning, data science and advanced technology.

The course takes you on a fascinating journey in which you learn gradually, step by step, as we code togethera range of generative architectures, from basic to advanced, until we reach multimodal A.I, where text and images are connected in incredible ways to produce amazing results.

At the beginning of each section, I explain the key concepts in great depth and then we code together, you and me, line by line, understanding everything, conquering together the challenge of building the most promising A.I architectures of today and tomorrow. After you complete the course, you will have a deep understanding of both the key concepts and the fine details of the coding process.

What a time to be alive! We are able to code and understand architectures that bring us home, home to our own human nature, capable of creating and imagining. Together, we will make it happen. Let’s do it!

Course Curriculum

Chapter 1: The generative AI revolution

Lecture 1: The roadmap, from basic to advanced and beyond

Lecture 2: Javier sends greetings from his spacecraft

Lecture 3: The generative revolution: coming home

Lecture 4: The present and future of AI is generative

Lecture 5: Applications of generative AI

Lecture 6: Latent spaces and representation learning

Lecture 7: Navigating latent spaces

Lecture 8: GANS: Generative Adversarial Networks

Lecture 9: Benefits and possibilities of Generative AI

Lecture 10: Coming home: generative AI and human nature

Lecture 11: Javier sings a song dedicated to generative AI

Chapter 2: Coding a basic generative architecture

Lecture 1: Javier introduces section 2 from his spacecraft

Lecture 2: Understanding the battle between generator and discriminator

Lecture 3: Understanding Cross Entropy in depth

Lecture 4: Understanding the equation to calculate the discriminator loss

Lecture 5: Understanding the equation to calculate the generator loss

Lecture 6: (Optional) Google Colab Tutorial

Lecture 7: Coding: importing libraries and declaring a visualization function

Lecture 8: Coding: hyperparameters and the DataLoader

Lecture 9: Coding: the generator class

Lecture 10: Coding: the discriminator class

Lecture 11: Coding: the optimizer and testing the generator

Lecture 12: Coding: the loss values of generator and discriminator

Lecture 13: Coding: main training loop, discriminator part

Lecture 14: Coding: main training loop, generator and stats

Lecture 15: Coding: running the training

Lecture 16: Coding: results and conclusions

Chapter 3: Coding an advanced generative architecture

Lecture 1: Javier introduces section 3 from his spacecraft

Lecture 2: Challenges and issues of the basic GAN

Lecture 3: The Wasserstein Loss

Lecture 4: The Gradient Penalty

Lecture 5: Coding: setting up libraries and parameters

Lecture 6: Coding: Login and setup of the Wandb stats library

Lecture 7: Coding: Beginning the generator

Lecture 8: Coding: Understanding convolutions

Lecture 9: Coding: The generator class

Lecture 10: Coding: The critic class

Lecture 11: Coding: Alternative way to initialize parameters (optional)

Lecture 12: Coding: Loading the CelebA dataset

Lecture 13: Coding: Declaring dataset, dataloader and optimizers

Lecture 14: Coding: the gradient penalty

Lecture 15: Coding: saving and loading checkpoints

Lecture 16: Coding: training loop – critic training

Lecture 17: Coding: training loop – generator training

Lecture 18: Coding: stats and fixing issues

Lecture 19: Coding: reviewing the code before running the training

Lecture 20: Coding: running the training

Lecture 21: Coding: results after a few epochs

Lecture 22: Coding: results after a few more epochs

Lecture 23: Coding: results getting better and better

Lecture 24: Coding: morphing between points in latent space

Lecture 25: Coding: more morphing

Chapter 4: Generating images from text by combining two advanced architectures

Lecture 1: Javier introduces section 4 from his spacecraft

Lecture 2: Multimodal generation, an incredible adventure

Lecture 3: Coding: importing the libraries

Lecture 4: Coding: helper functions and hyperparameters

Lecture 5: Coding: Setting up the CLIP model

Lecture 6: Coding: Setting up the Generative transformer model

Lecture 7: Coding: Setting up the latent space parameters to be optimized

Lecture 8: Coding: encode the text prompts through CLIP

Lecture 9: Coding: creating crops from the generated image

Lecture 10: Coding: a function to display generated images and crops

Lecture 11: Coding: optimizing the latent space parameters

Lecture 12: Coding: the training loop

Lecture 13: Coding: running the training

Lecture 14: Coding: interpolating between points in the latent space

Lecture 15: Coding: creating a video of the interpolations and general review

Lecture 16: Coding: creating variations of the code

Lecture 17: Coding: Davinci Sfumato: Tweaking the code to create a new kind of texture

Lecture 18: Coding: Davinci Sfumato: reflecting about the process

Lecture 19: Final greetings from the spacecraft

Chapter 5: Editing people's clothes by combining segmentation and generative AI models

Lecture 1: Intro: people's clothes replacement and editing using Generative AI

Lecture 2: Coding: Setting up libraries and the segmentation model

Lecture 3: Coding: Setting up the Stable Diffusion generative model

Lecture 4: Coding: Loading a picture and running the segmentation process to produce masks

Lecture 5: Coding: Visualizing the generated masks

Lecture 6: Coding: Inpainting, running and experimenting with the Stable Diffusion model

Lecture 7: Coding: Guide the segmentation process with text prompts

Lecture 8: Coding: run the generative model in this alternative setup

Lecture 9: Ending of the section

Chapter 6: Bonus: Journey to the latent space of a Neural Network

Lecture 1: In Search of the Magical Mappings of Creativity

Lecture 2: The Search for the Perfect Mapping: datasets and dimensionality

Lecture 3: From Linearity to Complexity: Neural Networks and the Nonlinearities of Life

Lecture 4: Bending the Rules: Non-Linear transformations and the key to complexity

Lecture 5: Not Too Tight, Not Too Loose – Finding the perfect fit

Lecture 6: How increasing the dimensionality impacts the latent complexity of the network

Lecture 7: The Power of Depth: Creating Sophisticated Mappings with AI networks

Lecture 8: From high dimensional manifolds to dynamic and ever changing latent spaces

Lecture 9: Advanced digital representations of the latent complexity of neural networks

Lecture 10: Visualizing the Journey: Loss Landscapes and the Search for Optimal Weights

Lecture 11: Example of the dynamic Loss Landscape of a generative adversarial network

Lecture 12: Lucy – Real Time Visualization of the changing weights of a neural network

Lecture 13: Charting the hidden depths: a recap of our transformative latent space journey

Chapter 7: Bonus: Activating the Generative Model of your own mind

Instructors

Javier Ideami
Multidisciplinary engineer, researcher & creative director

Rating Distribution

1 stars: 40 votes
2 stars: 100 votes
3 stars: 740 votes
4 stars: 2991 votes
5 stars: 4039 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!

Menu