Detecting Underwater Trash with YOLO World

Learn how to train a custom YOLO-World model to detect specific objects like underwater trash! In this tutorial, we move beyond zero-shot detection to fine-tune YOLO-World on a custom dataset using Python and PyTorch. YOLO-World is changing the game for real-time object detection. While it's famous for "Open Vocabulary" tasks, fine-tuning it on your own specific data yields incredible professional-grade results. What you will learn: ✅ Setting up a Conda environment with CUDA 12.8 & PyTorch 2.9.1. ✅ Visualizing YOLO annotations using OpenCV. ✅ Configuring data.yaml for custom classes ✅ Fine-tuning the YOLO-World model with the Ultralytics API. ✅ Running inference on images and saving results to MP4 video. Download the code for the tutorial here : https://eranfeit.lemonsqueezy.com/che... or here : https://ko-fi.com/s/7416c60dc3 Link to the full post and code here : https://eranfeit.net/how-to-train-yol... Link to the post and code for Medium users :   / how-to-fine-tune-yolo-world-for-vision-tas...   You can find more computer vision tutorials in my blog page : https://eranfeit.net/blog/ You can find more Visual Language models tutorials tutorials in this playlist :    • Visual Language Models tutorials 2026   You can find more Object Detection tutorials in this playlist :    • Object detection tutorials 2026   ~~~~~~~~~~~~~~~ Best AI Photo Tools (Backgrounds, Objects, Headshots) ~~~~~~~~~~~~~~~ ✅ Phot-AI packs more than 30 AI powered tools into one place—covering background and object removal/replacement, image extension and a suite of creative generators for art, icons and logos. follow the link and start creating : https://phot.ai?ref=eran33 ✅ Pixelcut uses AI to help you create professional photos and videos. You can instantly remove backgrounds, retouch, expand and upscale images, or generate new images and even videos from a simple text prompt or reference picture. tap the link and start creating today! : https://pixelcut.ai/?via=eran ✅ PhotoGPT AI acts as your personal photographer—just describe what you need and the platform generates high quality headshots or casual images within minutes. Its built in photo editor lets you remove objects, replace backgrounds and make studio quality corrections with a single click. You can even train your own AI model using a few selfies, receive context aware prompt suggestions and upscale images for print ready results. Dive into ~~~~~~~~~~~~~~~ recommended courses and books ~~~~~~~~~~~~~~~ 🚀 Want to get started with Computer Vision or take your skills to the next level ? Great Interactive Course : "Deep Learning for Images with PyTorch" here : https://datacamp.pxf.io/zxWxnm If you’re just beginning, I recommend this step-by-step course designed to introduce you to the foundations of Computer Vision : https://trk.udemy.com/9LoE7E If you’re already experienced and looking for more advanced techniques, check out this deep-dive course : https://trk.udemy.com/EEDyMD I also recommend this book, https://amzn.to/3GBMNLC : "Practical Machine Learning for Computer Vision" by Oreilly ~~~~~~~~~~~~~~~ CONNECT ~~~~~~~~~~~~~~~ ☕ Buy me a coffee - https://ko-fi.com/eranfeit 🖥️ Email : [email protected] 🌐 https://eranfeit.net 🤝 Fiverr : https://www.fiverr.com/s/mB3Pbb 🐦 Twitter -   / eran_feit   📸 Instagram -   / eran_feit   ▶️ Subscribe -    / @eranfeit   🐙 Facebook -   / 3080601358933585   📝 Medium -   / feitgemel   ~~~~~~~~~~~~~~ SUPPORT ME 🙏~~~~~~~~~~~~~~ 🅿 Patreon -   / eranfeit   ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #EranFeit #ultralytics #YoloWorld ~~~~~~~~~~~~~~ Chapters ~~~~~~~~~~~~~ 00:00 Introduction and Demo 01:15 Installation 03:29 Step 1 - Prepare the data 11:38 Step 2 - Display one image 18:13 Step 3 - Train the model 24:52 Step 4 - Test the model on one image 33:47 Step 5 - Test the model on a video ~~~~~~~~~~~~~~ Credits ~~~~~~~~~~~~~ Music by Vincent Rubinetti Download the music on Bandcamp: https://vincerubinetti.bandcamp.com/a... Stream the music on Spotify: https://open.spotify.com/album/1dVyjw...