Views
No views yet
无人机林地巡检烟火检测模型 · 基于 YOLOv26m 在 FASDD 数据集上微调

| 指标 Metric | 数值 Value |
|---|---|
| mAP@0.5 | 0.843 |
| mAP@0.5:0.95 | 0.594 |
| Precision | 0.808 |
| Recall | 0.821 |
| 输入尺寸 Input Size | 640 × 640 |
| 参数 Params | YOLOv26m(约 40M) |
指标取自最优 epoch(156),使用 SGD + cosine LR 训练 200 epochs。

| 配置项 | 值 |
|---|---|
| 基础模型 Base | YOLOv26m(COCO 预训练) |
| 数据 Data | FASDD(fire / smoke 两类) |
| 优化器 Optimizer | SGD |
| 学习率策略 LR Schedule | cosine (lr0=0.005, lrf=0.001) |
| Epochs | 200(patience=30) |
| Batch Size | 16 |
| Image Size | 640 |
| 增强 Augmentation | degrees=30, flipud=0.5, fliplr=0.5, scale=0.5, hsv 等 |
| 其他 | label_smoothing=0.1, multi_scale=0.3, mosaic=0 |
1from ultralytics import YOLO
2
3model = YOLO("yolo26m-fasdd-fire-smoke-detection.pt") # 或你的本地 best.pt 路径
4
5# 图片检测
6results = model.predict("aerial_image.jpg", conf=0.25, imgsz=640)
7
8# 视频检测(无人机巡检视频)
9results = model.predict("drone_video.mp4", conf=0.25, imgsz=640)
10
11# 验证指标
12metrics = model.val()1from huggingface_hub import hf_hub_download
2from ultralytics import YOLO
3
4model_path = hf_hub_download(
5 "YOUR_HF_USERNAME/yolo26m-fasdd-fire-smoke-detection",
6 "weights/best.pt",
7)
8model = YOLO(model_path)yolo predict model=weights/best.pt source=aerial_image.jpg imgsz=640 conf=0.25yolo26m-fasdd-fire-smoke-detection/
├── README.md # 模型说明(本文件)
├── args.yaml # 完整训练参数
├── results.png # 训练曲线
├── BoxPR_curve.png # P-R 曲线
├── confusion_matrix.png # 混淆矩阵
├── val_batch0_pred.jpg # 验证集预测示例
└── weights/
└── best.pt # 最优权重(44 MB)conf=0.25,可视场景密度调整(0.15–0.35)。max_det=300。1@misc{outsideguy2026yolo26mfasdd,
2 title={YOLOv26m UAV Forest Patrol Fire and Smoke Detection},
3 author={OutsideGuy},
4 year={2026},
5 howpublished={\url{https://huggingface.co/YOUR_HF_USERNAME/yolo26m-fasdd-fire-smoke-detection}},
6}