TensorFlow 2.0 Alpha

TensorFlow 2.0 focuses on simplicity and ease of use, with updates like eager execution, intuitive higher-level APIs, and flexible model building on any platform. Start with the beginner notebook tutorial and the Effective TensorFlow 2.0 guide. Install the TensorFlow 2.0 Alpha preview package:

 pip install tensorflow==2.0.0-alpha0 

See the GPU guide for CUDA®-enabled cards. The TensorFlow 2.0 community testing FAQ contains additional compatibility and migration details.

For beginners

The best place to start is with the user-friendly Sequential API. Create models by plugging together building blocks.
Run this “Hello World” example, then read the guides and tutorials to learn more.

For experts

The Subclassing API provides a define-by-run interface for advanced research. Create a class for your model, then write the forward pass imperatively. Easily write custom layers, activations, and training loops.
Run this “Hello, World” example, then read the guides and and tutorials to learn more.

What’s coming in TensorFlow 2.0

TensorFlow 2.0 will focus on simplicity and ease of use: easy model building, robust model deployment in production on any platform, and powerful experimentation for research.

Standardizing on Keras: Guidance on High-level APIs in TensorFlow 2.0

With Keras as the high-level API for TensorFlow, it's easier for developers new to machine learning to get started with TensorFlow.

Contribute to TensorFlow: SIGs, RFCs, Testing, Docs

TensorFlow has always been shaped by the community, and we’re excited to build on several years of great contributions with our new community groups and processes.