Using Docker Containers to Serve Deep Learing Predictions at Booking.com
![Using Docker Containers to Serve Deep Learing Predictions at Booking.com](/2017/images/all/lf_huffc03acb4b89c823f315cae16e4b2e6b_29065_900x500_fit_q75_box.jpg)
Each day, over 1.2 million room nights are reserved on Booking.com. That gives us access to huge amount of data which we can utilise in order to provide a better experience to our customers. We under …
Talk Title | Using Docker Containers to Serve Deep Learing Predictions at Booking.com |
Speakers | Sahil Dua (Software Developer, Booking.com) |
Conference | Open Source Summit Europe |
Conf Tag | |
Location | Prague, Czech Republic |
Date | Oct 21-27, 2017 |
URL | Talk Page |
Slides | Talk Slides Talk Slides |
Video | |
Each day, over 1.2 million room nights are reserved on Booking.com. That gives us access to huge amount of data which we can utilise in order to provide a better experience to our customers. We understand that while there are a lot of machine learning frameworks and libraries available, putting the models in production at large scale is still a challenge. I’d like to talk about how we took on the challenge of deploying deep learning models in production: how we chose our tools and developed our internal deep learning infrastructure. I’ll cover how we do model training in Docker containers, distributed TensorFlow training in a cluster of containers, automated re-training of models and finally - deployment of models using Kubernetes. I’ll also talk about how we optimise our model prediction infrastructure for latency or throughput depending on the use case.