Florence-2 uses a text-based format for annotations. You can use annotated data to fine-tune Florence-2 for tasks like object detection.
Below, learn the structure of Florence-2.
With Roboflow supervision, an open source Python package with utilities for completing computer vision tasks, you can merge and split detections in Florence-2. Read our dedicated guides to learn how to merge and split Florence-2 detections.
Below, see model architectures that require data in the Florence-2 format when training a new model.
On each page below, you can find links to our guides that show how to plot predictions from the model, and complete other common tasks like detecting small objects with the model.
