Train and deploy TensorFlow models in Go

The final step of the machine learning workflow is the deployment to production. In this phase, we want the trained model to be deployed on a device, but more than often the device has an entirely different runtime environment with respect to the one used during training.

Abstract

The final step of the machine learning workflow is the deployment to production. In this phase, we want the trained model to be deployed on a device, but more than often the device has an entirely different runtime environment with respect to the one used during training. TensorFlow, thanks to its SavedModel serialization format, allows deploying a trained model to several “deployment platforms”. Your model can run on a browser, in a Java application, in a Python script, and last but not least on every device that can run a C program. There is, in fact, a TensorFlow C API that can also be used for generating language bindings – and that is where Go, with its FFI for the C language, jumps in. In this talk, we will learn the basics of the TensorFlow Go bindings, their limitations, and how the tfgo library simplifies their usage. Moreover, the flexibility of the SavedModel serialization format is presented, and we will be able to design a deployment environment for incremental learning – in Go!

Video

Stay connected

You can subscribe to our newsletter to stay updated on the latest news and announcements. Follow us on social media to join our community and engage with other attendees, speakers, and staff. We're on Twitter, Mastodon, Youtube and Facebook. Don't forget to use our official hashtag #GoLab2023 to share your experience and connect with other attendees on social media.

Subscribe to our newsletter

We hate spam just as much as you do, which is why we promise to only send you relevant communications. We respect your privacy and will never share your information with third parties.
©2023 GoLab | The international conference on Go in Florence-Design & devCantiere Creativo-Made withDatoCMS