An open API service indexing awesome lists of open source software.

https://github.com/florianwilhelm/mlstm4reco

Multiplicative LSTM for Recommendations
https://github.com/florianwilhelm/mlstm4reco

pytorch recommender-system spotlight

Last synced: 6 months ago
JSON representation

Multiplicative LSTM for Recommendations

Awesome Lists containing this project

README

          

==========
mlstm4reco
==========

Benchmark multiplicative LSTM vs. ordinary LSTM. Read this `blog post`_ about the evaluation.

Description
===========

Create a conda environment with::

conda env create -f environment-abstract.yml

or use::

conda env create -f environment-concrete.yml

to perfectly replicate the environment.
Then activate the environment with::

source activate mlstm4reco

and install it with::

python setup.py develop

Then change into the ``experiments`` directory and run:

./run.py 10m -m mlstm

to run the ``mlstm`` model on the Movielens 10m dataset. Check out
``./run.py -h`` for more help.

Note
====

This project has been set up using PyScaffold 3.0.2. For details and usage
information on PyScaffold see http://pyscaffold.org/.

.. _`blog post`: https://florianwilhelm.info/2018/08/multiplicative_LSTM_for_sequence_based_recos/