Skip to content

Latest commit

 

History

History
 
 

official

README.md

Logo

TensorFlow Official Models

The TensorFlow official models are a collection of models that use TensorFlow’s high-level APIs. They are intended to be well-maintained, tested, and kept up to date with the latest TensorFlow API. They should also be reasonably optimized for fast performance while still being easy to read. These models are used as end-to-end tests, ensuring that the models run with the same or improved speed and performance with each new TensorFlow build.

Model Implementations

Natural Language Processing

Model Description Reference
ALBERT A Lite BERT for Self-supervised Learning of Language Representations arXiv:1909.11942
BERT A powerful pre-trained language representation model: BERT (Bidirectional Encoder Representations from Transformers) arXiv:1810.04805
NHNet A transformer-based multi-sequence to sequence model: Generating Representative Headlines for News Stories arXiv:2001.09386
Transformer A transformer model to translate the WMT English to German dataset arXiv:1706.03762
XLNet XLNet: Generalized Autoregressive Pretraining for Language Understanding arXiv:1906.08237

Computer Vision

Model Description Reference
MNIST A basic model to classify digits from the MNIST dataset Link
ResNet A deep residual network for image recognition arXiv:1512.03385
RetinaNet A fast and powerful object detector arXiv:1708.02002
Mask R-CNN An object detection and instance segmentation model arXiv:1703.06870

Other models

Model Description Reference
NCF Neural Collaborative Filtering model for recommendation tasks arXiv:1708.05031

How to get started with the Model Garden official models

Please follow the below steps before running models in this repository.

Requirements

  • The latest TensorFlow Model Garden release and TensorFlow 2
    • If you are on a version of TensorFlow earlier than 2.1, please upgrade your TensorFlow to the latest TensorFlow 2.
pip3 install tf-nightly

Installation

Method 1: Install the TensorFlow Model Garden pip package

tf-models-nightly is the nightly Model Garden package created daily automatically. pip will install all models and dependencies automatically.

pip install tf-models-nightly

Please check out our example to learn how to use a PIP package.

Method 2: Clone the source

  1. Clone the GitHub repository:
git clone https://github.com/tensorflow/models.git
  1. Add the top-level /models folder to the Python path.
export PYTHONPATH=$PYTHONPATH:/path/to/models

If you are using a Colab notebook, please set the Python path with os.environ.

import os
os.environ['PYTHONPATH'] += ":/path/to/models"
  1. Install other dependencies
pip3 install --user -r official/requirements.txt

More models to come!

The team is actively developing new models. In the near future, we will add:

  • State-of-the-art language understanding models: More members in Transformer family
  • Start-of-the-art image classification models: EfficientNet, MnasNet and variants.
  • A set of excellent objection detection models.

If you would like to make any fixes or improvements to the models, please submit a pull request.

Contributions

Every model should follow our guidelines to uphold our objectives of readable, usable, and maintainable code.

General Guidelines

  • Code should be well documented and tested.
  • Runnable from a blank environment with ease.
  • Trainable on: single GPU/CPU (baseline), multiple GPUs & TPUs
  • Compatible with Python 3 (using six when being compatible with Python 2 is necessary)
  • Conform to Google Python Style Guide

Implementation Guidelines

These guidelines are to ensure consistent model implementations for better readability and maintainability.