infyni

Gen AI with Python and TensorFlow 2.0

This course aims to provide participants with a deep understanding of Generative Artificial Intelligence (Gen AI) using Python & TensorFlow 2.0. Participants will learn the foundations of generative models, explore advanced techniques, & gain practical experience through hands-on projects.

Live Course

Live Class: Sunday, 03 Dec

Duration: 30 Hours

Enrolled: 0

Offered by: infyni

Live Course
$125 70% off

$38

About Course

Creating a Generative Adversarial Network (GAN) using Python and TensorFlow 2.0 can be an exciting project! GANs are known for their ability to generate new data that resembles a given dataset, and TensorFlow is a powerful library for building and training neural networks

This course aims to provide participants with a deep understanding of Generative Artificial Intelligence (Gen AI) using Python and TensorFlow 2.0. Participants will learn the foundations of generative models, explore advanced techniques, and gain practical experience through hands-on projects.


While representing operations in the dataflow graph as primitives allows flexibility in defining new layers within the Python client API, it also can result in a lot of "boilerplate" code and repetitive syntax. For this reason, the high-level API Keras14 was developed to provide a high-level abstraction; layers are represented using Python classes, while a particular runtime environment (such as TensorFlow or Theano) is a "backend" that executes the layer, just as the atomic TensorFlow operators can have different underlying implementations on CPUs, GPUs, or TPUs. While developed as a framework-agnostic library, Keras has been included as part of TensorFlow's main release in version 2.0. For the purposes of readability, we will implement most of our models in this book in Keras, while reverting to the underlying TensorFlow 2.0 code where it is necessary to implement particular operations or highlight the underlying logic. Please see Table 2.3 for a comparison between how various neural network algorithm concepts are implemented at a low (TensorFlow) or high (Keras) level in these libraries.

Course Offerings

  • Instructor-led interactive classes
  • Clarify your doubts during class
  • Access recordings of the class
  • Attend on mobile or tablet
  • Live projects to practice
  • Case studies to learn from
  • Lifetime mentorship support
  • Industry specific curriculum
  • Certificate of completion
  • Employability opportunity
  • Topics
  • Instructor (1)
  • Understanding Generative AI: Overview and Applications
  • Introduction to TensorFlow 2.0
  • Basics of Python for Machine Learning
  • Tensor operations and flow in TensorFlow
  • "> Building simple neural networks with TensorFlow 2.0

  • Overview of Generative Models (GANs, VAEs, etc.)
  • Probability and Statistics for Generative Models
  • Loss functions and optimization in generative models
  • Training dynamics and convergence in generative models
  • Implementing a basic GAN from scratch
  • Deep Convolutional GANs (DCGAN)
  • Wasserstein GANs (WGAN)
  • Conditional GANs
  • Image-to-Image Translation with Pix2Pix
  • StyleGAN and StyleGAN2
  • Progressive Growing GANs
  • Transfer learning with pre-trained models
  • Hyperparameter tuning for generative models
  • Introduction to text-to-image generation
  • Implementing text-to-image models using GANs
  • Handling textual data with Natural Language Processing (NLP)
  • Applications of text-to-image generation
  • Understanding sequence generation tasks
  • Introduction to Recurrent Neural Networks (RNNs)
  • Implementing sequence generation models with TensorFlow 2.0
  • Applications in music, language, and beyond
  • Overview of reinforcement learning
  • Generative models and reinforcement learning
  • Implementing reinforcement learning in TensorFlow 2.0
  • Applications of reinforcement learning in generative AI