tensorflow/models

Models and examples built with TensorFlow

What it solves

It provides a centralized repository of state-of-the-art (SOTA) model implementations and modeling solutions, helping TensorFlow users avoid building models from scratch and demonstrating best practices for research and product development.

How it works

The project is organized into four main sections: official implementations that are optimized and maintained by TensorFlow, research implementations provided by researchers, a curated list of community-driven models, and Orbit, a lightweight library for customized training loops that integrates with tf.distribute across CPU, GPU, and TPU.

Who it’s for

Machine learning researchers and developers using TensorFlow who want to access high-quality, reproducible model implementations and training tools.

Highlights

  • Official SOTA model implementations using latest TensorFlow 2 APIs.
  • Support for training logs via TensorBoard.dev for transparency and reproducibility.
  • Orbit library for flexible, customized training loop code.
  • Available as a pip package (tf-models-official) for easy installation.

Related

  • Project
    tensorflow/tfjs

    A hardware-accelerated JavaScript library for training and deploying machine learning models in the browser and Node.js.

  • Project
    tensorflow/tensorflow

    An end-to-end open source platform for machine learning that provides a flexible ecosystem of tools and libraries for building and deploying ML-powered applications.

  • Project
    LongxingTan/Time-series-prediction

    A TensorFlow-based time series package that provides a unified interface for prediction, classification, and anomaly detection using state-of-the-art deep learning models.

  • Project
    google-ai-edge/litert-samples

    A collection of official and community samples, model recipes, and deployment tools for LiteRT and LiteRT-LM to enable high-performance on-device machine learning.

  • Project
    tensorflow/serving

    A high-performance serving system for machine learning models designed to manage model lifetimes and provide versioned inference via gRPC and HTTP in production environments.