yolov26-fire-smoke-detection_v3
Fine-tuned from yolov26-fire-detection (YOLOv26-S) using Ultralytics.
Classes
Dataset
- Images: 3202 train / 403 valid / 395 test
- Check the dataset page above for its license -- not necessarily the same as this repo's
license field, which reflects the base model's license.
Training
| Parameter |
Value |
| Epochs |
100 |
| Image size |
640 |
| Batch size |
16 |
| Optimizer |
AdamW |
| Initial LR (lr0) |
0.001 |
| Patience (early stop) |
20 |
Results (held-out validation split)
| Metric |
Value |
| mAP50 |
0.7262 |
| mAP50-95 |
0.4937 |
| Precision |
0.7062 |
| Recall |
0.6608 |
Usage
from ultralytics import YOLO
model = YOLO("best.pt")
results = model.predict("image.jpg", conf=0.25)
for r in results:
for box in r.boxes:
print(model.names[int(box.cls[0])], float(box.conf[0]))
