TensorFlow 2.9 Is Here: Present-day Use Cases

Author(s): Anil Tilbe

Originally published on Towards AI.

This member-only story is on us. Upgrade to access all of Medium.

Tensorflow is available as an open-source deep learning framework for machine learning under the MIT license. It provides a high-level API, which is geared towards readability for efficient information retrieval, and high-level abstractions, which enable fast customizations.

By Alex Lee from Unsplash

TensorFlow receives support from the deep learning community towards its features and libraries, including tensorflow_addons, tf.keras, and tf.keras_addons. TensorFlow has competitors currently from the other popular deep learning frameworks such as PyTorch, PySpark, and WSLint.

Focus on (1) CPU performance (oneDNN by default); (2) model parallelism with DTensor; (3) revamp… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI