Overview
Learn how to integrate and fine-tune the Florence-2 vision language model in computer vision projects through this 17-minute technical demonstration. Follow along as a machine learning engineer provides hands-on guidance for implementing the model using Roboflow's Workflows tool, covering essential applications like object detection and optical character recognition (OCR). Discover practical techniques for multimodal dataset labeling and gain insights into deploying custom vision language solutions for real-world applications.
Syllabus
Florence-2: Create and Deploy a Custom Vision Language Model
Taught by
Roboflow