Analysis and modeling from data collected for the VR Exoskeleton project.
To create a virtual environment and install dependencies from pip:
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
python -m ipykernel install --user --name=vr-exoskeleton
On Windows, instead activate the environment (the second line above) by:
venv\Scripts\activate
Navigate to the dataset hosted on Figshare.
Click the Download all button.
Extract the content to the data directory:
unzip ~/Downloads/25749378.zip data
Train a MLP model:
python -m vr_exoskeleton.train mlp --run_name my_run --seed 1
Train a LSTM model:
python -m vr_exoskeleton.train lstm --run_name my_other_run --seed 2
Export the trained model to the ONNX format:
python vr_exoskeleton/export.py
You can check that the model exported with proper dimensions and input/output layer names via Netron.
From the repository root, open Jupyter Lab by:
jupyter-lab