Computer vision algorithms, which process video and image data, have many applications. The development of convolutional neural networks, alongside hardware improvements, have led to a proliferation of highly accurate computer vision models. In this tutorial, you will learn how to build new, and use existing, computer vision models using PyTorch.
This tutorial is a practical, hands-on, introduction to computer vision with PyTorch.
In this tutorial, you will learn about:
- An overview of deep learning for computer vision
- How to implement neural networks in PyTorch
You will gain hands-on experience with important computer vision tasks:
- Image classification
- Object detection
- Semantic segmentation
- Generative models
Tutorial materials are available on GitHub in Jupyter notebook format.
Laptops are encouraged, but not required.