Give a diagnosis using FHE to preserve the privacy of the patient. We show how to train several models using Concrete ML and choose the one that provides the best accuracy with the lowest inference time. Finally, we export the model in order to use it in the Hugging Face space which provides a live interactive demo this model in use.
- First, create a virtual env and activate it:
python3.8 -m venv .venv
source .venv/bin/activate
- Then, install required packages:
pip3 install -U pip wheel setuptools --ignore-installed
pip3 install -r requirements.txt --ignore-installed