Skip to content

devilhyt/ecg-federated-learning-public

Repository files navigation

ECG Federated Learning

Overview

This is a federated learning project based on the PhysioNet/CinC Challenge 2017. The goal is to classify ECG signals into three categories: Normal, Atrial Fibrillation (AF), and Other.

Environment

  • OS: Linux Mint 22
  • Python: 3.11.10

How to run.

  1. Download the dataset.

    bash download_dataset.sh
  2. Install the requirements.

    pip install -r requirements.txt
  3. Login to Wandb.

    Choose one of the following methods:

    • Login to wandb using the following command.
      wandb login
    • Using .env file.
      echo "WANDB_API_KEY=your_wandb_api_key" > .env
    • Using the environment variable.
      export WANDB_API_KEY=your_wandb_api_key

    If you don't want to use wandb (Not Recommended), you can disable it using the following methods:

    • Using .env file.
      echo "WANDB_MODE=disabled" > .env
    • Using the environment variable.
      export WANDB_MODE=disabled
  4. Run the following .ipynb files in the order:

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages