In this video, we look at *Moondream* - a *Vision Language Model* capable of seeing the world similarly to how a human does. Moondream can be *asked questions* in natural human language and *generate responses in natural human language* as well. It uses *context* and an understanding of the image as a whole to do more *advanced tasks* than things like object detection. We will also be looking at how you can use it practically in *maker projects* and how to set it up on the *Pi 5.*
💡❓ If you have any questions about this content or want to share a project you're working on head over to our *maker forum:* _http://coreelec.io/forum_
0:00 Intro to Moondream 1:06 What is Moondream? 4:40 How to set up Moondream 8:00 Running Moondream with Python 9:20 The limitations of Moondream 0.5b 10:00 Practical Example: Checking the Bins 11:31 Breakdown of Processing Time 14:43 Practical Example: Delivery Package Monitoring 18:28 Processing Images from a Pi Camera 20:42 Outro
🌏🦘 *Core Electronics* is located in the heart of Newcastle, Australia. We're powered by makers, for makers. Drop by if you are looking for: