GenshinYOLO23 is here!

GenshinYOLO23 is my final project for my Computer Vision class. I call it GenshinYOLO because it’s a YOLO model designed for real-time Genshin monster detection in Genshin Impact game scene. Basically it’s just a pretrained YOLOv5s model finetuned on a custom-made Genshin monster dataset of ~1700 manually annotated images of monsters in game scene with 23 classes. Detailed information and link to my dataset and model checkpoint can be found in this github repository. Here’s also a demo on YouTube.