Code for the publication "Physics-Informed Long-Short Term Memory Neural Network Performance on Holloman High-Speed Test Track Sled Study" from the proceedings of the ASME 2022 Fluids Engineering Division Summer Meeting.
Paper available here
The raw CSV files (21GBs) and the split .npy files for the training (562MBs) and validation dataset (563MBs) can be provided when inquired.
- Install pyenv and use it to install Python 3.10,
pyenv install 3.10
- Install poetry
- Run
poetry install
- To verify your torch installation is using CUDA, run
poetry run python dev_test_installation.py
- Set-up the experiment details/configuration in
physics_lstm / config / paper.yaml
- Run the experiment
cd physics_lstm
poetry run python lstm_pytorch.py