Skip to content

A collection of research notes and experimental implementations on federated learning, medical image analysis, and PyTorch-based deep learning. 一系列关于联邦学习、医学图像分析和基于 PyTorch 的深度学习的研究笔记和实验实现。

Notifications You must be signed in to change notification settings

kancheng/fl-test-init

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

65 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Federated Learning

聯邦學習與科研的筆記

A PyTorch Implementation of Federated Learning http://doi.org/10.5281/zenodo.4321561

Dieses Repository bündelt meine Forschungsnotizen und experimentellen Implementierungen zu föderalem Lernen, medizinischer Bildverarbeitung und Deep Learning mit PyTorch.

このリポジトリは、フェデレーションラーニング、医用画像解析、そして PyTorch を用いた深層学習に関する私の研究ノートと実験的実装をまとめたものです。

Ce dépôt rassemble mes notes de recherche et mes implémentations expérimentales en apprentissage fédéré, analyse d’images médicales et deep learning avec PyTorch.

Federated Learning and Medical Imaging – Research Notes & Experiments

This repository is a collection of my research notes, experiment prototypes, and exploratory implementations across federated learning, medical image analysis, and PyTorch-based deep learning. It consolidates numerous small-scale demos, baseline replications, and dataset-specific experiments to support rapid testing and conceptual understanding.

The project includes:

  • Federated Learning Modules – prototypes such as FedAvg, FedDC, FedTP, and HarmoFL testbeds.
  • Medical Image Segmentation – UNet implementations, NIfTI preprocessing (SimpleITK), and brain/BRATS-2020 segmentation demos.
  • Medical Classification Tasks – CNN classifiers for MedMNIST, Tuberculosis datasets, and other medical benchmarks.
  • General Deep Learning Scripts – MNIST CNNs, LSTM samples, PyTorch basics, and utility notebooks.

This work complements and extends the reference implementation A PyTorch Implementation of Federated Learning (DOI: 10.5281/zenodo.4321561), and serves as a comprehensive sandbox for learning, experimentation, and research in federated learning and medical AI.

聯邦學習與醫療影像 – 研究筆記與實驗集合

本倉庫彙集了我在 聯邦學習(Federated Learning)醫療影像分析基於 PyTorch 的深度學習 領域中的研究筆記、實驗原型與探索性實作。 內容整合了多組小型 Demo、基線模型重現與特定資料集的測試,用於快速原型化、概念驗證與研究理解。

本專案涵蓋:

  • 聯邦學習模組 – FedAvg、FedDC、FedTP、HarmoFL 等原型測試環境。
  • 醫療影像分割 – UNet 實作、NIfTI 前處理(SimpleITK)、Brain/BRATS-2020 分割示例。
  • 醫療影像分類任務 – 針對 MedMNIST、結核病(Tuberculosis)資料集與其它醫療基準的 CNN 分類器。
  • 一般深度學習範例 – MNIST CNN、LSTM 範例、PyTorch 基礎程式與各式工具 Notebook。

About

A collection of research notes and experimental implementations on federated learning, medical image analysis, and PyTorch-based deep learning. 一系列关于联邦学习、医学图像分析和基于 PyTorch 的深度学习的研究笔记和实验实现。

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 98.9%
  • Python 1.1%