Data-Analysis: TensorFlow models

Mon, 01 Jan 0001 00:00:00 +0000

Tensorflow is a framework for creating neural networks. It implements basic linear algebra and multi-variable calculus operations in a scalable fashion, and allows users to easily chain these operations into a computation graph.

Vertica supports importing, exporting, and making predictions with TensorFlow 1.x and 2.x models trained outside of Vertica.

In-database TensorFlow integration with Vertica offers several advantages:

Your models live inside your database, so you never have to move your data to make predictions.
The volume of data you can handle is limited only by the size of your Vertica database, which makes Vertica particularly well-suited for machine learning on Big Data.
Vertica offers in-database model management, so you can store as many models as you want.
Imported models are portable and can be exported for use elsewhere.

When you run a TensorFlow model to predict on data in the database, Vertica calls a TensorFlow process to run the model. This allows Vertica to support any model you can create and train using TensorFlow. Vertica just provides the inputs - your data in the Vertica database - and stores the outputs.

Data-Analysis: Using PMML models

Mon, 01 Jan 0001 00:00:00 +0000

Vertica can import, export, and make predictions with PMML models of version 4.4 and below.

Vertica Documentation – Using external models with Vertica

Data-Analysis: TensorFlow models

Data-Analysis: Using PMML models