Giter Club home page Giter Club logo

usableml_students's Introduction

Repository for the 'Usable ML' Software Project @ FU Berlin

General

This repository is for the 'Usable ML' software project course at FU Berlin, provided by Fraunhofer AISEC. Students will develop a graphical user interface that allows creating machine learning models and manipulating them. Possible features include:

  • Training Interface
    • start training (done)
    • interrupt training (done)
    • continue training (done)
    • adjust parameters (e.g., learning rate, loss function, momentum, dropout-rate) (0.5 P) (done)
      • before the training
      • during the training
    • revert to an earlier epoch (1 P) (done)
    • freeze parts of the model (1 P)
  • Training Monitor
    • display accuracy and loss over time for training set
    • indicate point in training where a parameter was changed
    • display accuracy and loss over time for test set (0.5 P)
    • display layer-specific information (e.g., gradients) (1 - 2 P)
    • compare different runs (1 P)
    • fork graph when parameters of earlier epochs are changed (1.5 P)
  • Model Creator
    • create models using a GUI (2 P)
    • change the composition of layers (1 P)
    • change aspects of the layers (e.g., sizes) (0.5 P)
  • Model Evaluator
    • select stored model to be evaluated (0.5 P)
    • evaluate per-class accuracy on test set (or training set, or arbitrary dataset) (1 P)
    • display special examples which (2 P)
      • are falsely predicted
      • are predicted with a small loss

Items in bold are expected as a minimum feature set.

Structure

This structure is required for Flask.

project/
    app.py
    templates/
        index.html
    static/
        script.js
        style.css

Installation

  1. Clone the environment and go into the folder.
git clone https://gitlab.cc-asp.fraunhofer.de/dar80083/usableml_students.git
cd usableml_students
  1. Install the requirements into a conda environment
conda env create -f env.yml
  1. Install PyTorch into your environment. Refer to this page for specific instructions: https://pytorch.org/get-started/locally/

Usage

Activate the environment

conda activate UsableML

Run the app

python3 app.py

License

This project is licensed under the GNU Affero General Public License v3.0.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.