e1250 commited on
Commit
9f04171
·
verified ·
1 Parent(s): 3bd709e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -2
README.md CHANGED
@@ -9,14 +9,15 @@ base_model:
9
  - Ultralytics/YOLO26
10
  ---
11
 
12
- # Safety Detection Model
13
 
14
  A fine-tuned YOLO model for detecting fire and smoke in images and video streams, built for real-time safety monitoring.
15
 
16
  ## Model Details
17
  - **Architecture:** YOLOv26 (fine-tuned)
18
  - **Framework:** PyTorch
19
- - **Task:** Object Detection
 
20
 
21
  ## Classes
22
  | ID | Label |
@@ -27,6 +28,18 @@ A fine-tuned YOLO model for detecting fire and smoke in images and video streams
27
  ## Dataset
28
  Fine-tuned on the [Home Fire Dataset](https://www.kaggle.com/datasets/pengbo00/home-fire-dataset) from Kaggle.
29
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  ## Usage
31
  ```python
32
  from ultralytics import YOLO
@@ -37,4 +50,5 @@ results = model("image.jpg")
37
 
38
  ## Limitations
39
  - Trained on home fire scenarios — performance may degrade in industrial or outdoor environments
 
40
  - Not validated for production safety-critical systems without further testing
 
9
  - Ultralytics/YOLO26
10
  ---
11
 
12
+ # Safety Detection
13
 
14
  A fine-tuned YOLO model for detecting fire and smoke in images and video streams, built for real-time safety monitoring.
15
 
16
  ## Model Details
17
  - **Architecture:** YOLOv26 (fine-tuned)
18
  - **Framework:** PyTorch
19
+ - **Epochs:** 52
20
+ - **Experiment Tracking:** ClearML
21
 
22
  ## Classes
23
  | ID | Label |
 
28
  ## Dataset
29
  Fine-tuned on the [Home Fire Dataset](https://www.kaggle.com/datasets/pengbo00/home-fire-dataset) from Kaggle.
30
 
31
+
32
+ - **Training Logs:** [ClearML Experiment](https://app.clear.ml/projects/bffe65b5fe1649dd9d202e181ba92fe0/tasks/f57871573c9d4d969dd5867004857d99/scalars)
33
+
34
+
35
+ ## Evaluation Metrics
36
+ | Metric | Value |
37
+ |-----------|-------|
38
+ | mAP@50 | 0.930 |
39
+ | mAP@50-95 | 0.626 |
40
+ | Precision | 0.913 |
41
+ | Recall | 0.891 |
42
+
43
  ## Usage
44
  ```python
45
  from ultralytics import YOLO
 
50
 
51
  ## Limitations
52
  - Trained on home fire scenarios — performance may degrade in industrial or outdoor environments
53
+ - Detection confidence decreases at stricter IoU thresholds (mAP@50-95: 0.626)
54
  - Not validated for production safety-critical systems without further testing