title

Lessons learned from using Dataflow for local ML batch inference | Beam Summit 2021

charset

utf-8

viewport

width=device-width,initial-scale=1,maximum-scale=1

description

The Beam Summit brings together experts and community to share the exciting ways they are using, changing, and advancing Apache Beam and the world of data and stream processing.

author

Software Guru

og:title

Lessons learned from using Dataflow for local ML batch inference

og:description

At BenchSci, we mine the world’s biological research papers with the aim of extracting information that will accelerate future pharmaceutical research programs by enabling more reproducible experiments. Machine Learning and specifically our in-house Deep Learning models play an important role in extracting these key pieces of information and organizing the knowledge into a meaningful and easy-to-use structure. While we have the luxury of processing this information in batch, the size and number of our models along with the size of the input data eventually outgrew our on-premise model serving infrastructure.

og:type

article

og:url

https://web.archive.org/web/20220122120503/https://2021.beamsummit.org/sessions/lessons-learned-dataflow-ml-batch-inference/

og:image

https://web.archive.org/web/20220122120503im_/https://2021.beamsummit.org/images/card.png

twitter:card

summary_large_image

twitter:image

https://web.archive.org/web/20220122120503im_/https://2021.beamsummit.org/images/card.png

twitter:title

Lessons learned from using Dataflow for local ML batch inference

twitter:description

At BenchSci, we mine the world’s biological research papers with the aim of extracting information that will accelerate future pharmaceutical research programs by enabling more reproducible experiments. Machine Learning and specifically our in-house Deep Learning models play an important role in extracting these key pieces of information and organizing the knowledge into a meaningful and easy-to-use structure. While we have the luxury of processing this information in batch, the size and number of our models along with the size of the input data eventually outgrew our on-premise model serving infrastructure.

icon

/web/20220122120503im_/https://2021.beamsummit.org/favicon.ico

shortcut icon

/web/20220122120503im_/https://2021.beamsummit.org/favicon.ico

stylesheet

https://web-static.archive.org/_static/css/banner-styles.css?v=1B2M2Y8A

stylesheet

https://web-static.archive.org/_static/css/iconochive.css?v=1B2M2Y8A

stylesheet

/web/20220122120503cs_/https://2021.beamsummit.org/plugins/bootstrap/css/bootstrap.min.css