zeekay
e037e8f7ea
The distribution called itself torus-ml while shipping a package directory named concrete, so the name a user installs and the name they import disagreed — and most of the tree already said torus.ml, which could not resolve against src/concrete. Moved src/concrete to src/torus and pointed the include at it. The dependency was Zama's concrete-python from their index. It is torus-fhe from ours, which is what luxfhe/torus already ships: that frontend declares torus-fhe and ships a torus/fhe module, so every 'from torus.fhe' in this tree was already naming our compiler and only the dependency lagged. Two distributions share one namespace, which is the shape the upstream this forked from used and the reason the split works: torus-fhe gives torus.fhe, torus-ml gives torus.ml. Swept every other spelling — identifiers, enum members, workflow variables, filenames, notebooks. LICENSE and NOTICE keep the upstream attribution a fork owes; the figures carry the old name in JPEG metadata a text sweep cannot reach.
Deployment
In this folder we show how to deploy a simple Torus ML model that does breast cancer classification, either through Docker or Amazon Web Services.
Get started
To run this example on AWS you will also need to have the AWS CLI properly setup on your system. To do so please refer to AWS documentation. One can also run this example locally using Docker, or just by running the scripts locally.
On the developer machine:
-
To train your model you can
- use
train_with_docker.shto use Docker (recommended way), - or, only if you know what you're doing and will manage synchronisation between versions, use
python train.py
This will train a model and serialize the FHE circuit in a new folder called
./dev. - use
On the server machine:
- Copy the './dev' directory from the developer machine.
- If you need to delete existing Dockers:
docker rm -f $(docker ps -a -q) - Launch the server via:
python ../server/deploy_to_docker.py --path-to-model ./dev
You will finally see some
INFO: Uvicorn running on http://0.0.0.0:5000 (Press CTRL+C to quit)
which means the server is ready to server, on Port 5000.
On the client machine:
If you go for a Docker part on the client side:
- Launch the
build_docker_client_image.pyto build a client Docker image. - Run the client with
client.shscript. This will run the container in interactive mode. - Then, in this Docker, you can launch the client script to interact with the server:
URL="<my_url>" python client.py
where <my_url> is the content of the url.txt file (if you don't set URL, the default is 0.0.0.0; this defines the IP to use when running server in Docker on localhost).
If you go for client side done in Python:
- Prepare the client side:
python3.8 -m venv .venvclient
source .venvclient/bin/activate
pip install -r client_requirements.txt
- Run the client script:
URL="http://localhost:8888" python client.py
And here it is! Whether you use Docker or Python for the client side, you deployed a Torus ML model and ran an inference using Fully Homormophic Encryption. In particular, you can see that the FHE predictions are correct.