Machine Learning Models

the analytics module allows you to upload machine learning (ml) models, feed live data into the model, and receive live output from the model note to work with ml models in analytics, your computer has to meet certain tensorflow requirements https //www tensorflow\ org/install/gpu if it does not, the ml specific processors will not be available for flow building create a machine learning model for upload to upload a model to analytics, you need a savedmodel format from tensorflow https //www tensorflow\ org/guide/saved model once you have created and saved a model, you must compress and zip it prior to uploading it to analytics savedmodel is a directory containing serialized signatures and the state needed to run them, including variable values and vocabularies the savedmodel ( saved model pb ) file stores the tensorflow model and a set of named signatures, each identifying a function that accepts tensor inputs and produces tensor outputs savedmodels may contain multiple variants of the model once your ml model is ready, proceed as follows upload the model see upload a model docid\ ucnjentjscin zrr2jjth for details create an analytics flow based on your model tensorflow processor for time series data see create an analytics flow docid\ ewmyjslrbisgimpdgq82a for details tensorflow images processor for images see tensorflow images processor docid\ ndgx8taklqpymprnxq5ux for details (optional) add the tengo script processor to modify the model output see tengo script docid\ scqmhggjpmszenhxn2z4z for details visualize the ml based output in the flows manager docid\ jghnqyhxbik8x2nhh5vte or through applications docid\ iipan4olp8rqznjc q8br access analytics models ui to access analytics models log in to litmus edge from the navigation panel, navigate to analytics > models the models pane appears next steps upload a model docid\ ucnjentjscin zrr2jjth obtain field values from a model docid\ c2sdfjnl6epoeymmxzwu3 model types docid\ d28f1cyhcb3w7n3qqlyey