/SPT_Pytorch

Pytorch implementation of Scalable approximate Bayesian inference for particle tracking data [ICML 2018]

Primary LanguageJupyter NotebookMIT LicenseMIT

Welcome

This is the Pytorch implementation for

Scalable approximate Bayesian inference for particle tracking data

Ruoxi Sun, Liam Paninski

https://www.biorxiv.org/content/early/2018/03/05/276253 (ICML 2018) ,where the original code implementation is in python 2.7 and Keras 2.0.5 (tensorflow backend)

Raw data simulations and intermediate results (blurry observations, trained neural networks, inputs of neural networks, etc) can be downloaded from https://drive.google.com/open?id=1AO6du609gYup2mcyKIWEqU5dH5p8Fa4K. download and upzip the data to your working directory.

neural networks are trained on one Nvidia RTX5000, using ~7GB.

Please cite the original paper and this repo if you use our implementation. Thanks.