Project Description
The outcome of this project will be a static web page that can be used to diagnose different diseases based on a Chest X-Ray.
Goal for this Hackweek
The goal is to learn TensorflowJS and to put on practice what I have learn in week 1 of https://www.coursera.org/learn/ai-for-medical-diagnosis.
Resources
- https://www.coursera.org/learn/ai-for-medical-diagnosis
- https://nihcc.app.box.com/v/ChestXray-NIHCC
- https://observablehq.com/@tvirot/machine-learning-in-javascript-with-tensorflow-js-part-ii
- https://www.tensorflow.org/js/tutorials/conversion/import_keras
Looking for hackers with the skills:
This project is part of:
Hack Week 21
Activity
Comments
-
over 3 years ago by jordimassaguerpla | Reply
code in https://github.com/jordimassaguerpla/susehackweek2022 results in https://github.com/jordimassaguerpla/susehackweek2022#results
Similar Projects
Kudos aka openSUSE Recognition Platform by lkocman
Description
Relevant blog post at news-o-o
I started the Kudos application shortly after Leap 16.0 to create a simple, friendly way to recognize people for their work and contributions to openSUSE. There’s so much more to our community than just submitting requests in OBS or gitea we have translations (not only in Weblate), wiki edits, forum and social media moderation, infrastructure maintenance, booth participation, talks, manual testing, openQA test suites, and more!
Goals
Kudos under github.com/openSUSE/kudos with build previews aka netlify
Have a kudos.opensuse.org instance running in production
Build an easy-to-contribute recognition platform for the openSUSE communit a place where everyone can send and receive appreciation for their work, across all areas of contribution.
In the future, we could even explore reward options such as vouchers for t-shirts or other community swag, small tokens of appreciation to make recognition more tangible.
Resources
(Do not create new badge requests during hackweek, unless you'll make the badge during hackweek)
- Source code: openSUSE/kudos
- Badges: openSUSE/kudos-badges
- Issue tracker: kudos/issues
Song Search with CLAP by gcolangiuli
Description
Contrastive Language-Audio Pretraining (CLAP) is an open-source library that enables the training of a neural network on both Audio and Text descriptions, making it possible to search for Audio using a Text input. Several pre-trained models for song search are already available on huggingface
Goals
Evaluate how CLAP can be used for song searching and determine which types of queries yield the best results by developing a Minimum Viable Product (MVP) in Python. Based on the results of this MVP, future steps could include:
- Music Tagging;
- Free text search;
- Integration with an LLM (for example, with MCP or the OpenAI API) for music suggestions based on your own library.
The code for this project will be entirely written using AI to better explore and demonstrate AI capabilities.
Resources
- CLAP: The main model being researched;
- huggingface: Pre-trained models for CLAP;
- Free Music Archive: Creative Commons songs that can be used for testing;
- Colab: To be used as the development environment;
- hw25-song-search: Github repo of the project.