Page History

...

Inference on a trained model has two different use-cases:1)

1. Real time or Online Inference - tasks that require immediate feedback, such as fraud detection

...

1. Batch or Offline Inference - tasks that don't require immediate feedback, these are use-cases where you have massive amounts of data and want to run Inference or pre-compute inference results 

Batch Inference is performed on big data platforms such as Spark using Scala or Java .while Real time Inference is typically performed and deployed on popular web frameworks such as Tomcat, Netty, Jetty, etc. which uses use Java. 

With this project, we want to build Java APIs that are easy to use for Inference and lowers the entry barrier is consuming MXNet for production use-cases. 

Goals

Proposed Approach

Alternative Approaches considered

Technical Challenges

Open Questions

...