MEDomicsLab-docs
V0
V0
  • 👋Welcome!
  • 👊Quick start
  • 👀Overview
  • 🧑‍🏫Tutorials
    • 🔵Design
      • Extraction Module
        • Image Extraction Page
        • Text Extraction Page
        • Time Series Extraction Page
        • MEDimage
      • Input Module
        • Feature Reduction Tool
        • MEDprofiles
          • MEDprofiles Viewer
      • Exploratory Module
    • 🟠Development
      • Learning Module
      • Evaluation Module
      • Federated Learning Module
        • Overview
        • Configure database
        • Create pipelines
        • Pipeline results
        • Hyperparameters optimization
        • Merge results
        • Crash tutorial
    • 🟢Deployment
      • Application Module
    • 🛠️Miscellaneous
  • 📄Testing Phase with MIMIC
    • MIMIC data access
    • Step 1: Install and Explore
    • Step 2: Extract Data
    • Step 3: Prepare ML tables
    • Step 4: Explore Data
    • Step 5: Vacations
    • Step 6: Create Model
    • Step 7: Evaluate & Apply Model
    • Step 8: Challenge
    • Wrap-Up
  • 👩‍💻Contributing
    • Our coding standards
    • How to push my modification ?
  • 🤕Troubleshooting
  • ❓FAQ
  • 🤓About us
  • Important Links
    • Official Website
    • 📔Release Notes
    • 🥲Known Issues
    • 😎Project Board
    • 🧬Physionet
  • MEDIA
    • ⚛️MEDomics
    • 👾Discord
    • 😺Github
    • 📺YouTube
  • Forms
    • 🗣️Contact us
    • 📝Report an issue
    • ‼️Join the testing phase
Powered by GitBook
On this page
  • Video tutorial
  • Visualizing the pipeline results
  • Saving the results
  1. Tutorials
  2. Development
  3. Federated Learning Module

Pipeline results

PreviousCreate pipelinesNextHyperparameters optimization

In this tutorial, we will learn how to visualize the pipeline results, save them, and use them in various formats.

Video tutorial

Visualizing the pipeline results

  1. When you run the pipelines, you will see a success message. Then, you can click on the "See Results" button to view the results.

  2. On the top left of the results page, there is a tab to switch between configurations. There are three available types of results:

  • Global Results: These are the general results on the central server, representing the average results of all clients.

  • Results by Node: This shows the results for a single client. A drop-down menu at the top allows you to switch between clients.

  • Compare Results: This type of result allows you to compare results between different clients. You can select the clients you want to compare using the provided options.

Saving the results

To save the results, you have two options:

  1. Auto Save: This occurs when you add the "Save Results" node to the pipeline. The node contains a single input field where you specify the name of the file to save the results.

  1. Manual Save: After visualizing the results, you can save them manually by clicking the "Save" button on the results page. When you click the button, an input field will appear for you to enter the name of the file.

The results can be saved in two different formats, and you can visualize them by double-clicking on them directly from the working directory:

EXPERIMENTS                          
    ├───FL                 
        └─── Results  
             └─── results.json       -> json file 
             └─── results.medflres   -> medflres file 
              
  • JSON Format

  • medflres Format

These options ensure you can easily store and manage your pipeline results.

🧑‍🏫
🟠