FL Tutorial (UQ CSSE4011)

Federated learning tutorial given as part of the UQ course on Advanced Embedded Systems CSSE4011.
In this tutorial we use Flower and Pytorch frameworks.

Setup

Local setup. If you wish to run the notebooks locally, type the following in your terminal.
```
conda install -c conda-forge flower
```
Online Notebook. Just click the "Open in Colab" button below and it will launch it in Google Collab. Ensure that you run the cell with the command below to install requirements
```
pip install -q flwr[simulation] torch torchvision matplotlib
```
- GPU acceleration on Collab : Runtime > Change runtime type > Hardware acclerator: GPU > Save).
- If you see an error related to GPU availability in one of the following sections, consider switching back to CPU-based execution by setting DEVICE = torch.device("cpu").

Centralized Image Classification
- Image classification example on CIFAR dataset using Pytorch.
Federated Learning Image Classification
- Image classification on multiple FL clients using Flower.

Name		Name	Last commit message	Last commit date
Latest commit History 19 Commits
imgs		imgs
presentation		presentation
FL_main.ipynb		FL_main.ipynb
FL_main_.ipynb		FL_main_.ipynb
README.md		README.md
centralized.ipynb		centralized.ipynb