End-To-End Memory Networks in MXNet (Gluon)

MXNet (using Gluon) implementation of End-To-End Memory Networks for language modelling. The original Tensorflow code from carpedm20 can be found here. MXNet Symbolic implementation can be found here.

Before Started

$ pip install -r requirements.txt

Usage

To train a model with 6 hops and memory size of 100, run the following command:

$ python main.py --nhop 6 --mem_size 100

To test a model with the lastest stored model:

$ python main.py --is_test True

To see all options, run:

$ python main.py --help