Tutorials And Examples

Welcome to Ivy’s tutorials webpage! Our goal is to provide you with a comprehensive learning experience on a variety of topics. We have organized our tutorials into three main sections to help you find exactly what you need.

If you are in a rush, you can jump straight into the Quickstart, a quick and general introduction to Ivy’s features and capabilities!

• In the Learn the basics section, you will find basic and to the point tutorials to help you get started with Ivy.

• The Guides section includes more involved tutorials for those who want to dive deeper into the framework.

• Finally, in the Examples and Demos section, you will find start-to-finish projects and applications that showcase real-world applications of Ivy. Whether you’re a beginner or an advanced user, we’ve got you covered!

Note

Want to use Ivy locally? Check out the Get Started section of the docs!

Learn the basics

Write Ivy Code

Get familiar with Ivy’s basic concepts and start writing framework-agnostic code.

Unify Code

Unify a simple torch function and use it alongside any ML framework!

Trace Code

Turn your Ivy code into an efficient fully-functional graph, removing wrappers and unused parts of the code.

Transpile Code

Convert a torch function to jax with just one line of code.

Lazy vs Eager

Understand the difference between eager and lazy tracing and transpilation.

How to use decorators

Learn about the different ways to use tracing and transpilation functions.

Transpile any library

Transpile the kornia library to jax with just one line of code.

Transpile any model

Transpile a Keras model into a PyTorch module.

Guides

Transpiling a PyTorch model to build on top

Transpile a timm model to tensorflow and build a new model around it.

Transpiling a Tensorflow model to build on top

Transpile a keras model to torch and build a new model around it.

Examples and Demos

Using Ivy ResNet

Use the Ivy ResNet model for image classification.

Accelerating PyTorch models with JAX

Accelerate your Pytorch models by converting them to JAX for faster inference.

Accelerating MMPreTrain models with JAX

Accelerate your MMPreTrain models by converting them to JAX for faster inference.

Image Segmentation with Ivy UNet

Use the Ivy UNet model for image segmentation.

Ivy AlexNet demo

In this demo, we show how an AlexNet model written in…

Accelerating XGBoost with JAX

Accelerate your XGBoost by converting them to JAX.

Convert PyTorch Models to PaddlePaddle

In this demo, we convert the DINOv2 model to PaddlePaddle

Using TensorFlow Models in your PyTorch Projects

In this demo, we convert the ConvNeXt model to PyTorch