This is a tutorial on how to train a forward PINN, and inverse PINN for the massdamper (underdamped scenario); it also provides insight into the role of learning rates, and weights, and different activation functions and weights, and shows how sensitive the model is to such decisions.
-
Set up an environment (conda, venv, or other virtual environment).
-
(Optional) Activate your environment. Example for the included
myenvvirtualenv:source myenv/bin/activate -
Install the requirements:
python -m pip install --upgrade pip wheel python -m pip install -r requirements.txt
-
Run the tutorial notebook
mass-damper-PINN-tutorial-beta.ipynb.