You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@ignite.apache.org by "Anton Dmitriev (JIRA)" <ji...@apache.org> on 2018/11/09 08:10:00 UTC
[jira] [Created] (IGNITE-10201) ML: TensorFlow model inference on
Apache Ignite
Anton Dmitriev created IGNITE-10201:
---------------------------------------
Summary: ML: TensorFlow model inference on Apache Ignite
Key: IGNITE-10201
URL: https://issues.apache.org/jira/browse/IGNITE-10201
Project: Ignite
Issue Type: New Feature
Components: ml
Affects Versions: 2.8
Reporter: Anton Dmitriev
Assignee: Anton Dmitriev
Fix For: 2.8
Machine learning pipeline consists of two stages: *model training* and *model inference* _(model training is a process of training a model using existing data with known target values, model inference is a process of making predictions on a new data using trained model)._
It's important that a model can be trained in one environment/system and after that is used for inference in another. A trained model is an immutable object without any side-effects (a pure mathematical function in math language). As result of that, an inference process has an excellent linear scalability characteristics because different inferences can be done in parallel in different threads or on different nodes.
The goal of "TensorFlow model inference on Apache Ignite" is to allow user to easily import pre-trained TensorFlow model into Apache Ignite, distribute it across nodes in a cluster, provide a common interface to call these models to make inference and finally perform load balancing so that all node resources are properly utilized.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)