TensorFlow is a free and open-source software library for dataflow and differentiable programming across a range of tasks. It is a symbolic math library, and is also used for machine learning applications such as neural networks.
TensorFlow is an end-to-end platform that makes it easy for you to build and deploy ML models.
- High-level Keras API, which makes getting started with TensorFlow and machine learning easy.
- Eager execution allows for immediate iteration and intuitive debugging.
- Distribution Strategy API for distributed training on different hardware configurations without changing the model definition.
- TensorFlow Extended (TFX) for full production ML pipeline.
- TensorFlow Lite for running inference on mobile and edge devices.
- Training and deploying models in JavaScript environments using TensorFlow.js.
- Supports an ecosystem of powerful add-on libraries and models to experiment with, including Ragged Tensors, TensorFlow Probability, Tensor2Tensor and BERT.
TensorFlow is Google Brain’s second-generation system. While the reference implementation runs on single devices, TensorFlow can run on multiple CPUs and GPUs (with optional CUDA and SYCL extensions for general-purpose computing on graphics processing units).