Computer Vision with PyTorch

My name is Yassine, I am an experienced computer vision engineer and I am the author of the "Computer Vision with PyTorch" book.

With this book, you will learn how to develop computer vision deep learning applications using PyTorch and its rich ecosystem.

No prior knowledge is required except a familiarity with programming or willingness to learn some Python.

The book is organized in 7 chapters with an introduction and a conclusion:

1. Data Processing: an introduction to some common computer vision data processing concepts and tasks.
2. Setup: how to setup a Python environment with the necessary packages for computer vision.
3. Pipeline: how to write a deep learning pipeline to train and validate a computer vision model.
4. Backbones: ResNet and Transformers models explored in details (theory and implementation).
5. Metrics and Losses: some concepts and examples of computer vision metrics and losses.
6. Deploying: how to deploy a trained deep learning computer vision model.
7. Classification: an application of everything seen so far to build a classification model from data collection to deployment.

Here is a dependency map to show you how the different chapters are interconnected and how you can read them.

Please enjoy this book!

For any reported errors or additional queries, you can send an email to: alouinimohamedyassine@gmail.com