https://github.com/markovmodel/deep_rev_msm
https://github.com/markovmodel/deep_rev_msm
Last synced: 10 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/markovmodel/deep_rev_msm
- Owner: markovmodel
- Created: 2019-12-16T13:27:20.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2020-01-21T17:36:53.000Z (over 6 years ago)
- Last Synced: 2025-08-14T12:00:01.381Z (11 months ago)
- Language: Jupyter Notebook
- Size: 2.29 MB
- Stars: 2
- Watchers: 7
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
Deep_rev_msm
Deep learning Markov and Koopman models with physical constraints.
## What is it?
Deep_rev_msm is summarized the implementations of the work presented in the paper "Deep learning Markov and Koopman models with physical constraints." (described in https://arxiv.org/abs/1912.07392). It includes a Jupyter notebook able to reproduce the results presented in the paper and a benchmark file.
## Citation
If you use Deep reversible models presented in this paper in scientific work, please cite:
Mardt, A., Pasquali, L., Noé, F. & Wu, H. (2019).
Deep learning Markov and Koopman models with physical constraints.
arXiv, 1912.07392.
## Installation
We are using the package vampnet from the repo https://github.com/markovmodel/deeptime/tree/master/vampnet
IMPORTANT: We are using tensorflow 1.14
This package requires [Tensorflow](https://www.tensorflow.org) to be used.
Please install either tensorflow or tensorflow-gpu. Installation instructions:
https://www.tensorflow.org/install/
To use the notebook yourself, first clone the repository:
git clone https://github.com/markovmodel/deep_rev_msm.git
Then you can directly start.