OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Recurrent Entity Networks

An open-source Python implementation of recurrent entity networks in TensorFlow, with scripts for preparing bAbI datasets and training on question-answering tasks.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Recurrent Entity Networks — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when studying or adapting a recurrent entity network with the repository's documented bAbI data-preparation and training workflow.

Who it is for

  • Researchers studying entity-tracking neural networks and question answering.
  • Learners who want to examine a TensorFlow implementation and train it on bAbI tasks.

Documented uses

  • Prepare bAbI datasets as TFRecords for model training.
  • Launch training on the QA1 question-answering task.
  • Inspect reported per-task error figures against the paper's results.
Before you choose

Requirements & limits

The public repository is open source under the MIT license.

  • The major listed dependency is TensorFlow v1.1.0; additional dependencies are specified in requirements.txt.
  • The README's repository result table contains unknown values for some tasks, so it does not provide a complete per-task comparison.
  • The README reports that tasks 16 and 19 needed a different learning-rate schedule to converge reliably.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare bAbI data and start QA1 training

Follow the repository's documented path from bAbI dataset download through launching QA1 training.

Before you start

  • Python environment with TensorFlow v1.1.0, the listed major dependency
  • bAbI datasets, downloadable with the repository script or from the bAbI Project
  • Additional dependencies are listed in requirements.txt

Steps

  1. Download the datasets by running download_babi.sh or obtain them from the bAbI Project.

  2. Run entity_networks/prep_data.py to convert the datasets into TFRecords.

  3. Run python -m entity_networks.main to begin training on QA1.

Expected outcome

The documented command begins training on the QA1 task using the prepared data.

Guide limitations

  • The README lists TensorFlow v1.1.0 and refers to requirements.txt for other dependencies.
  • The repository notes that tasks 16 and 19 required a changed learning-rate schedule to converge reliably.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
jimfleming/recurrent-entity-networks · Official homepage title · retained in its source language
How we review sourcesSuggest a correction

Related options

Original Torch implementation of EntNet-babi — The README identifies this as the paper author's separate original implementation.