Views
No views yet
YOLOEPESegTrainer. yoloe-11s-seg backbone, imgsz 640, 30 epochs, prompt
augmentation (paraphrase per batch).| Task | Dice | mIoU | Precision | Recall | ms/img |
|---|---|---|---|---|---|
| Crack | 0.681 | 0.547 | 0.690 | 0.757 | ~30 |
| Taping | 0.859 | 0.774 | 0.807 | 0.956 | ~30 |
1from huggingface_hub import hf_hub_download
2from ultralytics import YOLOE
3
4ckpt = hf_hub_download(repo_id="ravindrakapse/drywall-yoloe", filename="best.pt")
5model = YOLOE(ckpt)
6results = model.predict("image.jpg", imgsz=640, conf=0.05)load_models.py.