Intro to Object Detection & Computer Vision Pipelines - AI Workshop

Workshop links to follow along:
https://signup.union.ai/ (can take 3-5 min to process)
https://github.com/unionai-oss/object...
https://huggingface.co/
https://slack.flyte.org/


This workshop will equip you with the skills to effectively build your computer vision and ML pipelines using Python, PyTorch and Flyte/Union.

We'll cover data annotation for object detection, model fine-tuning, versioning, building an effcient AI pipeline, and running batch inference on the trained CV model.

Afterwards you'll be able to build your own computer vision object detetection models and custom datasets! What you'll learn can also be transferred to different types of AI and ML pipelines.

The workflow we'll build hands-on together:

Download Dataset
Download pre-trained model weights
Initialize object detection model
Pre-process Data & Visualize Datasets
Fine-tune model with PyTorch
Evaluating Object Detection Models
Save model to Hugging Face Hub
Perform batch predictions in Cloud


This workshop will cover:

Data Annoatation for Object Detection
Computer Vision Models & Use cases
Reliable & Reproducible ML pipelines
Hands-on Building an ML pipeline


What you'll need to follow along:

A free Union.ai account(https://www.union.ai/)
A GitHub account for authentication
A Google account to run code in Colab
A Hugging Face Account to save CV models (Optional)
Note: For ease of setup we'll be using Union's serverless AI orchestration platform for the workshop, but you can also implement computer vision pipelines in Flyte, the open-source platform on your own compute clusters. https://github.com/flyteorg/flyte



Who should attend:

Anyone interested in building better computer vision pipelines, AI applications and MLOps best practices should attend. This workshop is designed to be approachable for most skill levels. Familiarity with machine learning and Python is strongly encouraged but not required.

By the end of this workshop, you'll be able to build a reliable computer vision pipeline with Python, PyTorch, and Union. What you'll learn can be transferred to more complex AI pipelines and libraries.



About the Speaker:

Sage an AI engineer and developer advocate who loves educating people and making ML applications more reliable. He's taught thousands of people during live workshops how to get started with Python, machine learning, computer vision, and AI observability.

Connect with Sage:   / sageelliott  



About Union.ai

Union is an AI platform powered by Flyte that simplifies ML infrastructure so you can develop, deploy, and innovate faster.

Write your code in Python, collaborate across departments, and enjoy full reproducibility and auditability. Union lets you focus on what matters.



💬 Join our AI and MLOps Slack Community: https://slack.flyte.org/

⭐ Check out Flyte on GitHub: https://github.com/flyteorg/flyte

🤝 Learn about everything else we’re doing at https://union.ai/