A character-level language model trained on the British National Formulary (BNF) A-Z of clinical medicines and a minigame to challenge it.
What's in the box?
- Keras/Tensorflow pipeline for a character-level language model.
- Inference in the browser with Tensorflow.js.
- Quick n' Dirty minigame, built in react.
The training code in this repo was executed on an Ubuntu 18.04 paperspace instance with a Nvidia Quadro P4000 GPU, NVIDIA Driver: 410.48, CUDA 10.0.130-1.
-
git clone git@github.com:coxy1989/rx
-
cd rx/rx_model
-
conda env create -f environment.yml
-
source activate rx
-
jupyter notebook
-
git clone git@github.com:coxy1989/rx
-
cd rx/rx_spa
-
docker build -t rx .
-
docker run -it -v $PWD:/app -p 3000:3000 --entrypoint bash rx
-
cd app
-
npm start