Google LLC today launched an enterprise version of TensorFlow, the popular open-source artificial intelligence framework it created to run machine learning, deep learning and other statistical and predictive analytics workloads.

The TensorFlow framework simplifies the process of acquiring data, training models, serving predictions and refining future results. Common use cases include training algorithms for image recognition and recurrent neural networks, as well as sequence-to-sequence models for machine translation and natural language processing.

In a launch at the O’Reilly TensorFlow World conference in Santa Clara, California, Craig Wiley (pictured), director of product management at Google Cloud AI Platform, said the launch of TensorFlow Enterprise was necessary to meet the “higher demands and expectations” of enterprises that need to scale up their machine learning projects.

TensorFlow Enterprise customers will be able to take advantage of what Google says is enterprise-grade support, including long-term support for older versions of the framework. Although TensorFlow is updated regularly, not everyone is able to upgrade to the newest releases immediately.

“For certain versions of TensorFlow, we will provide security patches and select bug fixes for up to three years,” Wiley added in a blog post. “These versions will be supported on Google Cloud, and all patches and bug fixes will be available in the mainline TensorFlow code repository.”

The enterprise-grade support also includes a “white-glove service” that comes with engineer-to-engineer assistance from Google Cloud’s experts, Wiley said.

Another advantage of TensorFlow Enterprise is the ability to scale with confidence. “Many models begin as an idea and a single-node on-prem, and scaling to the performance potential of the cloud can be daunting,” Wiley said.

But that’s no longer the case for TensorFlow Enterprise customers, who can take advantage of an array of compute options in Google Cloud, including Deep Learning VMs and Deep Learning Containers, which take advantage of Google’s customized Cloud Tensor Processing Units for AI workloads.

In addition to scalability, TensorFlow Enterprise customers can also benefit from easy access to a range of Google Cloud’s managed services, including Google Kubernetes Engine and the Google AI Platform, Wiley said.

TensorFlow Enterprise should fit the bill for companies that need enterprise-grade security, stability, maintenance and support said Holger Mueller, principal analyst and vice president at Constellation Research Inc. “That is what Google is providing with TensorFlow Enterprise with a three-year maintenance window,” he said.

“Google cares for performance, supporting both Google TPUs and Nvidia GPUs,” Mueller continued. “We will see if Google can attract more enterprise workloads with this move, effectively using its ‘homecourt advantage’ as the original provider of TensorFlow to the open source community. The battle here is really to deliver AI insights at highest speed and lowest cost.”

Photo: Robert Hof/SiliconANGLE