talk-data.com

Join this free, 90-minute hands-on workshop to learn how to leverage the open source FiftyOne computer vision toolset for greater visibility into the quality of your computer vision datasets and models. The workshop will cover:

• Object detection
• Embeddings
• Mistakenness
• Deduplication

The session emphasizes a data-centric approach to computer vision workflows. Participants will start by importing and exploring visual data, then move on to querying and filtering. The workshop will also demonstrate how to extend FiftyOne’s functionality and simplify tasks using plugins and native integrations. Attendees will learn to generate candidate ground truth labels and evaluate the results of fine-tuning a foundational model.

Prerequisites: Working knowledge of Python and basic computer vision concepts. All attendees will receive access to the tutorials, videos, and code examples used in the workshop

Instructor:

Antonio Rueda-Toicen, AI Engineer in Berlin and Research Scientist at the Hasso Plattner Institute, will lead the session. Antonio has extensive experience deploying machine learning models and has taught over 300 professionals. He specializes in computer vision, cloud technologies, and machine learning, and is a certified instructor of deep learning and diffusion models in NVIDIA’s Deep Learning Institute.

About the Workshop

Want greater visibility into the quality of your computer vision datasets and models? Then join us for this free 90-minute, hands-on workshop to learn how to leverage the open source FiftyOne computer vision toolset. At the end of the workshop you’ll be able to:

• Visualize complex datasets
• Explore embeddings
• Analyze and improve models
• Perform advanced data curation
• Integrations

This workshop will explore the importance of taking a data-centric approach to computer vision workflows. We will start with importing and exploring visual data, then move to querying and filtering. Next, we’ll look at ways to extend FiftyOne’s functionality and simplify tasks using plugins and native integrations. We’ll generate candidate ground truth labels, and then wrap things up by evaluating the results of fine tuning a foundational model. Prerequisites: working knowledge of Python and basic computer vision concepts. All attendees will get access to the tutorials, videos, and code examples used in the workshop

Access link: please remember to register through Voxel51's website to get the access link to this event.