Material for the imaging lunch on pytorch
Join us for a hands-on Introductory PyTorch Workshop, led by our in-house expert Florian Aymanns, designed for EPFL PhD students and postdocs interested in applying neural networks to image analysis. (Registration required.)
This session is best suited for participants with basic knowledge of Python who want to learn the foundations of neural networks and their implementation in PyTorch.
We’ll start by introducing tensors, highlighting their differences from NumPy arrays, and demonstrating autograd with simple examples. Moving forward, we’ll cover key neural network components like convolutional and fully connected layers, and use them to construct a neural network from scratch.
Participants will gain an understanding of loss functions, autograd, and stochastic gradient descent, learning how weights are updated during training. Finally, we’ll apply these concepts to train an image classification network using PyTorch.
This workshop offers a code-along experience on EPFL’s RCP cluster and is perfect for those eager to begin their journey into machine learning for image analysis.
- Understand the components of a convolutional neural network in code
- Train your first neural network to classify images using Pytorch
- Basic python knowledge
- Familiarity with NumPy arrays
- Basic understanding of neural networks
- Understanding of object oriented programming (classes and inheritance) is a plus but not required
Memento events: