DevOps Conference
The Conference for Continuous Delivery, Microservices,
Containers, Clouds and Lean Business

Serverless Deep Learning

Session
Until the conference starts:
✓ Team discount
✓ Specials for freelancers and academics
Register now
Bis konferenz-beginn:
✓ Kollegenrabatt
✓ Freelancer special
Jetzt anmelden
Until September 24:
✓ Save up to 510 €
✓ Raspberry Pi or PlayStation Classic for free
✓ Group Discount
Register now
Bis 24. September
✓ Über 510 € sparen
✓ Raspberry Pi oder PlayStation Classic for free
✓ Kollegenrabatt
Jetzt anmelden

Thank you for joining!
✓ See you next in Berlin or in Munich

Register Now

Thank you for joining!
✓ See you next in Berlin or in Munich

Register Now

Until June 18:
✓ Workshop Day for free
✓ Raspberry Pi or C64 Mini for free
✓ Save over $840
Register now
Until June 18:
✓ Workshop Day for free
✓ Raspberry Pi or C64 Mini for free
✓ Save over $840
Register now
Until July 2:
✓ Raspberry Pi or C64 Mini for free
✓ Save up to $330
Register now
Until July 2:
✓ Raspberry Pi or C64 Mini for free
✓ Save up to $330
Register now
Infos

Deep learning achieves the best performance for many computer vision, natural language processing, and recommendation tasks and thus it’s becoming increasingly more popular. However, it’s quite difficult to use deep learning in production as it requires a lot of effort to develop proper infrastructure for serving deep learning models.Platforms for serverless computing, such as AWS Lambda, provide a good alternative: they take care of scaling up and down and offer attractive pricing based only on actual usage. These platforms, unfortunately, have other limitations that make it problematic. In this talk, we show how to come around these limitations and be able to use AWS lambda and TensorFlow to serve deep learning models. We also discuss important maintenance aspects such as cost optimization, monitoring, deploying, and release management. Finally, we cover the limitations of AWS lambda, compare it with “serverful” solutions, and suggest workloads for which serverless is not the best option.

This Session Diese Session Take me to the current program of . Hier geht es zum aktuellen Programm von Berlin Berlin , Munich München , London London , New York New York or oder Singapore Singapur .

Stay tuned:

Behind the Tracks

 

Kubernetes Ecosystem

Docker, Kubernetes & Co

Microservices & Software Architecture

Maximize development productivity

Continuous Delivery & Automation

Build, test and deploy agile

Cloud Platforms & Serverless

Cloud-based & native apps

Monitoring, Traceability & Diagnostics

Handle the complexity of microservices applications

Security

DevSecOps for safer applications

Business & Company Culture

Radically optimize IT

Organizational Change

Overcome obstacles on the way towards DevOps

Live Demo #slideless

Showing how technology really works