jacobandreas/nmn2

This library provides code for training and evaluating neural module networks (NMNs). An NMN is a neural network that is assembled dynamically by composing shallow network fragments called modules into a deeper structure. These modules are jointly trained to be freely composable. At present the code supports predicting network layouts from natural-language strings, with end-to-end training of modules. Various extensions should be straightforward to implement--alternative layout predictors, supervised training of specific modules, etc. Please cite the CVPR paper for the general NMN framework, and the NAACL paper for dynamic structure selection.