Install TensorFlow

TensorFlow is tested and supported on the following 64-bit systems:

  • Ubuntu 16.04 or later
  • Windows 7 or later
  • macOS 10.12.6 (Sierra) or later (no GPU support)
  • Raspbian 9.0 or later

Download a package

Install TensorFlow with Python's pip package manager.

Official packages available for Ubuntu, Windows, macOS, and the Raspberry Pi.

GPU packages require a CUDA®-enabled GPU card.

Read the pip install guide
# Current release for CPU-only
pip install tensorflow

# Nightly build for CPU-only (unstable)
pip install tf-nightly

# GPU package for CUDA-enabled GPU cards
pip install tensorflow-gpu

# Nightly build with GPU support (unstable)
pip install tf-nightly-gpu

Run a TensorFlow container

The TensorFlow Docker images are already configured to run TensorFlow. A Docker container runs in a virtual environment and is the easiest way to set up GPU support. 

docker pull tensorflow/tensorflow                  # Download latest image
docker run -it -p 8888:8888 tensorflow/tensorflow  # Start a Jupyter notebook server
Read the Docker install guide

Google Colab: An easy way to learn and use TensorFlow

No install necessary—run the TensorFlow tutorials directly in the browser with Colaboratory, a Google research project created to help disseminate machine learning education and research. It's a Jupyter notebook environment that requires no setup to use and runs entirely in the cloud. Read the blog post.

Build your first ML app

Create and deploy TensorFlow models on web and mobile.

Web developers

TensorFlow.js is a WebGL accelerated, JavaScript library to train and deploy ML models in the browser and for Node.js.

Mobile developers

TensorFlow Lite is lightweight solution for mobile and embedded devices.