├── True_eigfunc_Prinz.npz
└── README.md


/True_eigfunc_Prinz.npz:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/markovmodel/deep_rev_msm/master/True_eigfunc_Prinz.npz


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | Deep_rev_msm
 2 | Deep learning Markov and Koopman models with physical constraints.
 3 | 
 4 | 
 5 | ## What is it?
 6 | 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.
 7 | 
 8 | 
 9 | ## Citation
10 | If you use Deep reversible models presented in this paper in scientific work, please cite:
11 | 
12 |     Mardt, A., Pasquali, L., Noé, F. & Wu, H. (2019). 
13 |     Deep learning Markov and Koopman models with physical constraints. 
14 |     arXiv, 1912.07392.
15 | 
16 | ## Installation
17 | 
18 | We are using the package vampnet from the repo https://github.com/markovmodel/deeptime/tree/master/vampnet
19 | IMPORTANT: We are using tensorflow 1.14
20 | 
21 | This package requires [Tensorflow](https://www.tensorflow.org) to be used.
22 | Please install either tensorflow or tensorflow-gpu. Installation instructions:
23 | 
24 | https://www.tensorflow.org/install/
25 | 
26 | To use the notebook yourself, first clone the repository:
27 | 
28 | git clone https://github.com/markovmodel/deep_rev_msm.git
29 | 
30 | Then you can directly start.
31 | 


--------------------------------------------------------------------------------