World Congress 2024 • Aug 20, 2024 • Session details

Using Containers to deploy AI Models across our microscopy platform

Sebastian Rhode

Tired of dependency hell when shipping AI models to client environments? Discover how containerizing workloads with Docker and WSL2 unlocks native GPU access and decouples your stack.

Pause

Mute

Enter Fullscreen

#1 about 2 min

Introduction to Zeiss and microscopy technology

An overview of the Zeiss business units focused on industrial quality and research microscopy.

#2 about 2 min

Exploring common AI workflows in microscopy tasks

How computer vision handles classification and instance segmentation of biological samples.

#3 about 4 min

Managing large data sets in microscopy workflows

The transition from gigabyte to terabyte datasets when capturing time-lapse imaging of growing cells.

#4 about 4 min

Customer requirements for AI model delivery

The need for robust AI performance across cloud and local platforms without requiring IT expertise.

#5 about 2 min

Challenges in traditional AI deployment methods

Why decoupling the model from client software caused persistent and difficult dependency mismatches.

#6 about 3 min

Shifting to containerized AI deployment environments

Bundling models and all necessary dependencies into Linux containers ensures consistent execution across environments.

#7 about 5 min

The containerized model training and deployment pipeline

Generating a containerized artifact after cloud training drastically simplifies distribution to image analysis clients.

#8 about 2 min

Executing containerized AI in production workflows

Downloading and running the self-contained AI module locally integrates smoothly into the user perspective.

#9 about 2 min

Business value of independent AI module updates

Delivering improved AI features quickly via containers speeds up progress without risking client software stability.

#10 about 4 min

Practical learnings from deploying containerized AI solutions

Starting with prototypes and open container standards minimized deployment risk in a traditional engineering company.

Matching moments

2:04 min

Optimizing and deploying containerized AI inference workloads

Ankit Patel

Ankit Patel · World Congress 2024

3:34 min

Standardizing AI model and tool execution using containers

Jim Clark

Jim Clark +3 · World Congress 2025

2:59 min

Adopting AI tools for developer container workflows

Ali Alp

Ali Alp · World Congress 2026 Europe

2:40 min

Optimizing AI deployments with bootable containers

Cedric Clyburn

Cedric Clyburn +1 · World Congress 2025

3:28 min

Deploying machine learning models locally and remotely with containers

Linda Mohamed · LIVE

3:34 min

Bridging application containerization and modern AI agent development

Jim Clark

Jim Clark +3 · World Congress 2025

More from World Congress 2024

Beyond the Hype: Real-World AI Strategies Panel thumbnail

Beyond the Hype: Real-World AI Strategies Panel

Mike Butcher, Jürgen Müller, Katrin Lehmann, Tobias Regenfuss

Carl Lapierre - Exploring Advanced Patterns in Retrieval-Augmented Generation thumbnail

almost 2 years ago

Carl Lapierre - Exploring Advanced Patterns in Retrieval-Augmented Generation

Carl Lapierre

Coding an Immersive Copilot using Unity / .NET and Azure OpenAI! thumbnail

about 2 years ago

Coding an Immersive Copilot using Unity / .NET and Azure OpenAI!

Zaid Zaim

Building a diverse tech company: The power of Diversity, Equity, Inclusion, and Belonging thumbnail

about 2 years ago

Building a diverse tech company: The power of Diversity, Equity, Inclusion, and Belonging

Sue Quackenbush

Dapr in Practice thumbnail

about 2 years ago

Dapr in Practice

marcklefter

Minimising the Carbon Footprint of Workloads thumbnail

about 2 years ago

Minimising the Carbon Footprint of Workloads

Michael Mueller

Related videos

Industrializing your Data Science capabilities thumbnail

World Congress 2021 • about 5 years ago

Industrializing your Data Science capabilities

Dubravko Dolic, Hüdaverdi Cakir

Containers and Kubernetes made easy: Deep dive into Podman Desktop and new AI capabilities thumbnail

World Congress 2024 • about 2 years ago

Containers and Kubernetes made easy: Deep dive into Podman Desktop and new AI capabilities

Stevan Le Meur

Leverage Cloud Computing Benefits with Serverless Multi-Cloud ML thumbnail

LIVE • almost 6 years ago

Leverage Cloud Computing Benefits with Serverless Multi-Cloud ML

Linda Mohamed

Compose the Future: Building Agentic Applications, Made Simple with Docker thumbnail

World Congress 2025 • about 1 year ago

Compose the Future: Building Agentic Applications, Made Simple with Docker

Jim Clark, Mark Cavage, Tushar Jain, Yunong Xiao

Bootable AI Containers with Podman Desktop thumbnail

World Congress 2025 • about 1 year ago

Bootable AI Containers with Podman Desktop

Cedric Clyburn, Kevin Dubois

Supercharge your cloud-native applications with Generative AI thumbnail

World Congress 2024 • about 2 years ago

Supercharge your cloud-native applications with Generative AI

Cedric Clyburn

Related articles

DC

Daniel Cranney

Stephan Gillich - Bringing AI Everywhere

In the ever-evolving world of technology, AI continues to be the frontier for innovation and transformation. Stephan Gillich, from the AI Center of Excellence at Intel, dove into the subject in a r...

almost 2 years ago

Stephan Gillich - Bringing AI Everywhere

DC

Daniel Cranney

Building AI Solutions with Rust and Docker

In recent years, artificial intelligence has surged in popularity in the world of development. While Python remains a popular choice in the realm of AI, Rust - often known as Rust Lang - is quickly...

almost 2 years ago

Building AI Solutions with Rust and Docker

BB

Benedikt Bischof

MLOps – What’s the deal behind it?

Welcome to this issue of the WeAreDevelopers Live Talk series. This article recaps an interesting talk by Nico Axtmann who introduced us to MLOpsAbout the speaker:Nico Axtmann is a seasoned machine...

almost 4 years ago

MLOps – What’s the deal behind it?

BB

Benedikt Bischof

MLops – Deploying, Maintaining And Evolving Machine Learning Models in Production

Welcome to this issue of the WeAreDevelopers Live Talk series. This article recaps an interesting talk by Bas Geerdink who gave advice on MLOps.‍About the speaker:‍Bas is a programmer, scientist, a...

about 4 years ago

MLops – Deploying, Maintaining And Evolving Machine Learning Models in Production

From learning to earning

Jobs that call for the skills explored in this talk.

Principal Solutions Architect, Professional Services

Zaragoza, Spain

€119k–170k Okta Docker OpenID

Principal Solutions Architect, Professional Services

€119k–170k Okta Docker OpenID

27 days ago • Verified

ML Engineer

Seattle, United States

Expert Remote Go

Principal Solutions Architect, Professional Services

€119k–170k Okta Docker OpenID

Principal Solutions Architect, Professional Services

Barcelona, Spain

€119k–170k Okta Docker OpenID

Principal Solutions Architect, Professional Services

Valencia, Spain

€119k–170k Okta Docker OpenID