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

Focused View

Javier Ideami

10:34:29

20 View

01 - The generative AI revolution

001 The roadmap, from basic to advanced and beyond.mp4

01:57

002 Javier sends greetings from his spacecraft.mp4

01:15

003 The generative revolution coming home.mp4

05:35

004 The present and future of AI is generative.mp4

06:48

005 Applications of generative AI.mp4

04:09

006 Latent spaces and representation learning.mp4

08:54

007 Navigating latent spaces.mp4

09:10

008 GANS Generative Adversarial Networks.mp4

06:41

009 Benefits and possibilities of Generative AI.mp4

06:01

010 Coming home generative AI and human nature.mp4

04:21

010 images-used-presentation-creative-commons.txt

011 Javier sings a song dedicated to generative AI.mp4

02:07

external-links.txt

02 - Coding a basic generative architecture

001 Javier introduces section 2 from his spacecraft.mp4

00:27

002 Understanding the battle between generator and discriminator.mp4

08:58

003 Understanding Cross Entropy in depth.mp4

10:23

004 Understanding the equation to calculate the discriminator loss.mp4

05:19

005 Understanding the equation to calculate the generator loss.mp4

03:05

006 (Optional) Google Colab Tutorial.mp4

12:20

007 Coding importing libraries and declaring a visualization function.mp4

13:49

008 Coding hyperparameters and the DataLoader.mp4

09:15

009 Coding the generator class.mp4

08:17

010 Coding the discriminator class.mp4

06:34

011 Coding the optimizer and testing the generator.mp4

07:35

012 Coding the loss values of generator and discriminator.mp4

08:52

013 Coding main training loop, discriminator part.mp4

06:12

014 Coding main training loop, generator and stats.mp4

07:08

015 Coding running the training.mp4

01:18

016 Coding results and conclusions.mp4

01:04

016 basic-gan-generative-a-i-course-by-ideami.zip

03 - Coding an advanced generative architecture

001 Javier introduces section 3 from his spacecraft.mp4

00:54

002 Challenges and issues of the basic GAN.mp4

06:54

003 The Wasserstein Loss.mp4

07:31

004 The Gradient Penalty.mp4

05:26

005 Coding setting up libraries and parameters.mp4

13:27

006 Coding Login and setup of the Wandb stats library.mp4

04:47

007 Coding Beginning the generator.mp4

04:36

008 Coding Understanding convolutions.mp4

13:18

009 Coding The generator class.mp4

13:39

010 Coding The critic class.mp4

13:08

011 Coding Alternative way to initialize parameters (optional).mp4

03:19

012 Coding Loading the CelebA dataset.mp4

07:00

013 Coding Declaring dataset, dataloader and optimizers.mp4

17:29

014 Coding the gradient penalty.mp4

06:53

015 Coding saving and loading checkpoints.mp4

07:05

016 Coding training loop - critic training.mp4

05:18

017 Coding training loop - generator training.mp4

01:32

018 Coding stats and fixing issues.mp4

10:27

019 Coding reviewing the code before running the training.mp4

05:25

020 Coding running the training.mp4

04:16

021 Coding results after a few epochs.mp4

03:12

022 Coding results after a few more epochs.mp4

01:30

023 Coding results getting better and better.mp4

02:07

024 Coding morphing between points in latent space.mp4

12:01

025 Coding more morphing.mp4

01:35

025 advanced-gan-generative-a-i-course-by-ideami.zip

external-links.txt

04 - Generating images from text by combining two advanced architectures

001 Javier introduces section 4 from his spacecraft.mp4

00:58

002 Multimodal generation, an incredible adventure.mp4

12:01

003 Coding importing the libraries.mp4

05:26

004 Coding helper functions and hyperparameters.mp4

07:26

005 Coding Setting up the CLIP model.mp4

03:20

006 Coding Setting up the Generative transformer model.mp4

11:47

007 Coding Setting up the latent space parameters to be optimized.mp4

06:35

008 Coding encode the text prompts through CLIP.mp4

11:40

009 Coding creating crops from the generated image.mp4

10:17

010 Coding a function to display generated images and crops.mp4

03:30

011 Coding optimizing the latent space parameters.mp4

08:49

012 Coding the training loop.mp4

06:13

013 Coding running the training.mp4

13:27

014 Coding interpolating between points in the latent space.mp4

08:23

015 Coding creating a video of the interpolations and general review.mp4

10:47

016 Coding creating variations of the code.mp4

06:45

017 Coding Davinci Sfumato Tweaking the code to create a new kind of texture.mp4

07:21

018 Coding Davinci Sfumato reflecting about the process.mp4

04:24

018 multimodal-generation-generative-a-i-course-by-ideami.zip

018 solution-to-taming-transformers-issue-section-4.txt

019 Final greetings from the spacecraft.mp4

00:53

019 advanced-gan-generative-a-i-course-by-ideami.zip

019 basic-gan-generative-a-i-course-by-ideami.zip

019 multimodal-generation-generative-a-i-course-by-ideami.zip

019 solution-to-taming-transformers-issue-section-4.txt

05 - Editing peoples clothes by combining segmentation and generative AI models

001 Intro people's clothes replacement and editing using Generative AI.mp4

12:55

002 Coding Setting up libraries and the segmentation model.mp4

10:16

003 Coding Setting up the Stable Diffusion generative model.mp4

05:34

004 Coding Loading a picture and running the segmentation process to produce masks.mp4

09:40

005 Coding Visualizing the generated masks.mp4

07:28

006 Coding Inpainting, running and experimenting with the Stable Diffusion model.mp4

12:26

007 Coding Guide the segmentation process with text prompts.mp4

09:15

008 Coding run the generative model in this alternative setup.mp4

06:08

008 clothes-inpainting-research-case-clipseg.zip

008 clothes-inpainting-research-case-sam-by-ideami.zip

009 Ending of the section.mp4

00:30

009 clothes-inpainting-research-case-clipseg.zip

009 clothes-inpainting-research-case-sam-by-ideami.zip

06 - Bonus Activating the Generative Model of your own mind

001 A guided visualization experience to exercise the generative model in your head.mp4

05:26

002 Intro to the journey to the center of the neuron.mp4

04:44

003 The container, the salty ocean and the 150000 cortical columns.mp4

07:58

004 Visualizing the pyramidal neuron.mp4

17:50

005 The Synapse, visualizing the input-output interface.mp4

06:01

006 Biological vs Artificial Neurons Inputs, Outputs, Speed, etc.mp4

08:37

007 Learning in biological and artificial neurons.mp4

07:54

008 Planning, decision making and world models.mp4

12:32

009 Efficiency sparsity in biological vs artificial networks.mp4

03:08

010 Consciousness within the neurons.mp4

02:51

011 The future, towards AGI ASI.mp4

02:51

Description

Learn to code with the most creative and exciting AI architectures, generative AI networks, from basic to advanced

What You'll 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 Final Section: experience a guided visualization to exercise the generative model in your head while you learn many things about neural networks

Who is this for?

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

What You Need to Know?

Basic knowledge of python. It's enough with the very basics, as we will code every little thing together, line by line

Access to an internet connection, as we will use the free online Google Colab service to code together

Plenty of enthusiasm as we will go deep into every little detail, let's do it! :)

More details

Description
September 2023:Â Update:Â TwoÂ new sections have been added recently. In Section 5 you will 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. The other new section is a final Bonus Extra. In this course you do programming of different generative models. In the new Section 6, you will be the generative model yourself. You will practice to exercise the generative model of your own head by doing a guided visualization journey with me, a journey to the center of a neuron. You will learn about biological and artificial neurons, as well as their learning and planning processes, while you exercise the generative model in your head, guided by the GPT-like generative model in my head.
____________________________
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 together a 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!Â 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!
Who this course is for:
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

User Reviews

Rating

average 0

Total votes0

Focused display

Javier Ideami is an expert in A.I and deep learning, specialized in advanced visualization, computer vision and generative architectures. He is a multidisciplinary engineer, researcher, creative director, artist and entrepreneur. Javier Ideami’s projects and talks have taken him from Silicon Valley to the jungles of Bali, including Stanford University and UC Berkeley, the United Nations FAO HQ, the financial center of London, the International Cultural Diplomacy Conference in Berlin and many others.

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.