Roboflow Courses

Vehicle Tracking and Speed Estimation Using Computer Vision - Open Source Tutorial

Learn to track vehicles and estimate their speed using computer vision techniques. Covers object detection, multi-object tracking, perspective transformation, and speed estimation with practical code implementation.

• YouTube
• 25 minutes
• Self-Paced
• Free Video

Fine-tuning PaliGemma for Custom Object Detection

Step-by-step guide to fine-tune PaliGemma for custom object detection, covering setup, dataset preparation, training, evaluation, and deployment. Includes practical tips and important considerations.

• YouTube
• 21 minutes
• Self-Paced
• Free Video

Fine-tuning Florence-2: Microsoft's Multimodal Model for Custom Object Detection

Comprehensive guide to fine-tuning Florence-2 for custom object detection, covering environment setup, dataset preparation, and model optimization using LoRA, with practical examples and performance comparisons.

• YouTube
• 26 minutes
• Self-Paced
• Free Video

How to Use OCR: Getting Started with Optical Character Recognition

Explore OCR models, benchmark performance, and follow a step-by-step guide to implement Optical Character Recognition in your projects.

• YouTube
• 10 minutes
• Self-Paced
• Free Video

RF-DETR, Batch Processing, Instant Training, Serverless Inference, and More - What's New in Roboflow

Discover the latest Roboflow innovations through six mini-presentations covering RF-DETR object detection, instant training, polygon zones, SQL integration, batch processing, and serverless inference for computer vision applications.

• YouTube
• 38 minutes
• Self-Paced
• Free Video

Real-time Video Analytics Using RTSP Stream and Computer Vision

Master real-time video analytics using RTSP streams and computer vision to build monitoring systems for object counting, duration tracking, and traffic analysis.

• YouTube
• 20 minutes
• Self-Paced
• Free Video

RF-DETR Architecture and How it Works - Why is DETR Better Than YOLO?

Discover RF-DETR, a state-of-the-art object detection model that outperforms YOLO. Learn how to train, test, compare, and deploy this model in your computer vision projects with insights from Roboflow's machine learning team.

• YouTube
• 16 minutes
• Self-Paced
• Free Video

How to Detect People in Danger Zones with AI

Learn how to enhance workplace safety with vision AI by tracking people and objects in danger zones, building red zone trackers, and integrating data systems for trend analysis.

• YouTube
• 13 minutes
• Self-Paced
• Free Video

Measure Objects with AI - Identifying Common Pitfalls and Increasing Precision

Discover how to train custom AI models to measure physical objects, avoid common mistakes, and improve accuracy through proper calibration and image processing techniques.

• YouTube
• 11 minutes
• Self-Paced
• Free Video

Building Computer Vision Applications with Workflows and Custom Python Blocks

Learn to create advanced computer vision applications by combining Workflows editor tools with custom Python blocks for gesture detection, data enrichment, and visualization customization.

• YouTube
• 24 minutes
• Self-Paced
• Free Video

How to Run Vision Models on Multiple Video Streams and Manage Everything in One Place

Master real-time vision model deployment across multiple video streams while centralizing management, reducing hardware needs, and streamlining monitoring for efficient AI implementation.

• YouTube
• 11 minutes
• Self-Paced
• Free Video

YOLOv12: Fine-Tuning for Custom Object Detection and Text Export to CSV

Master YOLOv12 object detection by learning model fine-tuning, custom training, and building applications to identify shipping containers with OCR text extraction and CSV export capabilities.

• YouTube
• 22 minutes
• Self-Paced
• Free Video

Testing VLMs on Real-World Problems - How Do They Compare?

Explore how different vision-language models (VLMs) perform on real-world visual tasks, with comparisons, observations about their future, and techniques for combining models to solve complex problems.

• YouTube
• 22 minutes
• Self-Paced
• Free Video

Use Depth Anything V2 to Measure Object Distances in Images and Videos

Discover how to implement AI depth estimation in computer vision projects using Depth Anything V2 to accurately measure distances between objects in images and videos.

• YouTube
• 14 minutes
• Self-Paced
• Free Video

Florence-2: Creating and Deploying Custom Vision Language Models

Master vision language modeling with Florence-2, from fine-tuning techniques to practical implementation in computer vision projects using Roboflow's Workflows for object detection and OCR tasks.

• YouTube
• 17 minutes
• Self-Paced
• Free Video