CRAN Task View: Model Deployment with R

Maintainer:Yuan Tang
Contact:terrytangyuan at gmail.com
Version:2018-11-09
URL:https://CRAN.R-project.org/view=ModelDeployment

This CRAN task view contains a list of packages, grouped by topic, that provides functionalities to streamline the process of deploying models to various environments, such as mobile devices, edge devices, cloud, and GPUs, for scoring or inferencing on new data.

Model deployment is often challenging due to various reasons. Some example challenges are:

Many of the areas discussed in this Task View are undergoing rapid changes in industries and academia. Please send any suggestions to the task view maintainer or submit a pull request or issue to the Github repository of this task view .

Suggestions and corrections by Achim Zeileis and Dirk Eddelbuettel (as well as others I may have forgotten to add here) are gratefully acknowledged.

Suggestions and corrections by Achim Zeileis, Dirk Eddelbuettel, and Kevin Kuo (as well as others I may have forgotten to add here) are gratefully acknowledged. Thanks to Dirk Eddelbuettel who made the initial .ctv file and the Markdown conversion script available at the Github repository of CRAN Task View for High Performance Computing . Last but not least, thanks to Dirk Eddelbuettel and Achim Zeileis who helped me get started on organizing this task view.

Deployment through Different Types of Artifacts

This section includes packages that provides functionalities to export the trained model to an artifact that could fit in small devices such as mobile devices (e.g. Android, iOS) and edge devices (Rasberri Pi). These packages are built based on different model format.

Deployment through Cloud/Server

Many deployment environments are based on cloud/server. The following packages provides functionalities to deploy models in those types of environments:

CRAN packages:

Related links: