Vision-Language Models in QGIS

Introduction¶

Learning Objectives¶

Loading the Moondream Model¶

Image Captioning¶

Visual Question Answering¶

Object Detection¶

Point Localization¶

Tips and Limitations¶

Key Takeaways¶

Exercises¶

Exercise 1: Comparing Caption Lengths¶

Exercise 2: Iterative Visual Question Answering¶

Exercise 3: Object Detection and Counting¶

Exercise 4: Comparing Detection and Point Modes¶