SuzukiWest / CIFAR-CentralBigTransfer Public

Notifications You must be signed in to change notification settings
Fork 0
Star 1

This project aimed to determine the ideal hyperparameters to classify the CIFAR-100 dataset.

1 star 0 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 5 Commits
Federated_Learning_CIFAR.pdf		Federated_Learning_CIFAR.pdf
README.md		README.md
central_big_transfer_cifar.py		central_big_transfer_cifar.py

Repository files navigation

Using Transfer Learning in Building Federated Learning Models on Edge Devices

Senior Research Project - Completed at Mount Royal University - By Jordan Suzuki

Credit to Yasaman Amannejad & Saba F. Lameh for the help with the code and paper

Summary

This project aimed to determine the ideal hyperparameters to classify the CIFAR-100 dataset.

In addition to Federated Learning (FL) Transfer Learning (TL) was used to pre-train base models.

These hyperparameters consist of:

The base model (TL).
The amount of clients involved (FL).
The number of classification labels.
Number of model training rounds.
Constant vs. Variable client selection.

About

This project aimed to determine the ideal hyperparameters to classify the CIFAR-100 dataset.

transfer-learning cifar-100 federated-learning colaboratory ilsvrc2012 imagenet-21k

Report repository

Languages

Python 100.0%