TensorFlow Models
A repository of state-of-the-art model implementations and examples built with TensorFlow, demonstrating best practices for machine learning.
What is TensorFlow Models?
TensorFlow Model Garden is a repository containing implementations of state-of-the-art machine learning models and modeling solutions built with TensorFlow. It provides reference examples that demonstrate best practices for TensorFlow users, enabling them to leverage these models for research and product development. The repository includes officially maintained models, research implementations, and community-curated resources.
Machine learning researchers, data scientists, and developers working with TensorFlow who need reference implementations of SOTA models or want to learn best practices for model development and training.
Developers choose TensorFlow Model Garden because it provides officially maintained, optimized implementations of cutting-edge models with training logs for transparency, along with the Orbit library for flexible training loop customization. It serves as a trusted resource for production-ready model code and best practices directly from the TensorFlow team.
Overview
Models and examples built with TensorFlow
Use Cases
Best For
- Finding production-ready implementations of state-of-the-art machine learning models
- Learning TensorFlow 2 best practices through reference code examples
- Customizing training loops with the Orbit library for distributed training
- Research reproducibility with provided training logs on TensorBoard.dev
- Exploring community-curated TensorFlow 2 model implementations
- Developing machine learning products with optimized, readable model code
Not Ideal For
- Projects requiring minimal setup and dependency management, as manual cloning and environment configuration are needed
- Teams exclusively using non-TensorFlow frameworks like PyTorch, since implementations are TensorFlow-specific
- Applications needing optimized, production-ready deployment pipelines, as the focus is on reference implementations and training
- Individuals seeking beginner-friendly, simplified tutorials with extensive hand-holding, due to the advanced nature of SOTA models
Pros & Cons
Pros
The official directory provides SOTA implementations kept up-to-date with TensorFlow 2 APIs, ensuring reliability and best practices for production use, as stated in the README.
Training logs on TensorBoard.dev are provided for many models, enhancing reproducibility and allowing users to verify performance claims directly.
Orbit offers a lightweight way to write customized training loops with seamless tf.distribute integration, supporting multi-device training like TPUs, as highlighted in the features.
Includes a curated list of external TensorFlow 2 repositories, expanding the available model implementations beyond official offerings.
Cons
Cloning the source requires setting PYTHONPATH and installing dependencies manually, which can be error-prone, especially on Windows, as noted in the installation steps.
Research models may use TensorFlow 1 or 2, leading to compatibility issues and added complexity for users relying solely on TensorFlow 2.
Not all models have provided training logs, limiting transparency and reproducibility for some implementations, as admitted in the README.
Frequently Asked Questions
Related Projects
TensorFlow Slim ModelsModels and examples built with TensorFlow
Caffe Model ZooCaffe: a fast open framework for deep learning.
ColorizationAutomatic colorization using deep neural networks. "Colorful Image Colorization." In ECCV, 2016.
Image AnalogyThe source code of 'Visual Attribute Transfer through Deep Image Analogy'.
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.