Violence Detection Yolov26
A single-class object detector that localizes violence in images/video frames. Fine-tuned from Ultralytics yolo26s.pt (COCO-pretrained).
Model source
- Kind
- Other
- File size
- 57.4 MB
- Version
- vRevision 3cdcd5f
- Updated
- Sep 16, 2026
- Downloads
- 68
- Source
- Hugging Face
Source description
Violence Detection — YOLOv26-s
A single-class object detector that localizes violence in images/video frames.
Fine-tuned from Ultralytics yolo26s.pt (COCO-pretrained).
Model details
| Architecture | YOLOv26-s (Ultralytics), task: detect |
| Base weights | yolo26s.pt (COCO-pretrained) |
| Classes | 1 — Violence |
| Input size | 512 × 512 |
| Training | 20 epochs, batch 12, cosine LR, AMP |
| Framework | Ultralytics 8.4.12 |
Evaluation (validation set)
| Metric | Value |
|---|---|
| mAP@50 | 0.928 |
| mAP@50-95 | 0.901 |
| Precision | 0.918 |
| Recall | 0.784 |
Training data
Trained on a custom YOLO-format dataset derived from surveillance/anomaly sources. The dataset-preparation scripts reference:
- ShanghaiTech Campus anomaly dataset
- UCF-Crime dataset
⚠️ These source datasets are released under their own academic/research-use terms and are not redistributed here. Only the fine-tuned weights are shared. Verify you have the right to use this model for your use case.
Usage
from ultralytics import YOLO
model = YOLO("best.pt")
results = model("image.jpg") # or a video / webcam stream
for r in results:
r.show() # display detections
print(r.boxes.xyxy, r.boxes.conf) # boxes + confidence
License
This model is derived from Ultralytics YOLO, which is AGPL-3.0. The weights are therefore distributed under AGPL-3.0. For closed-source/commercial use, obtain an Ultralytics Enterprise License.
Limitations
- Single-class detector — flags "violence" regions only; no fine-grained action labels.
- Trained on surveillance-style footage; may not generalize to other domains.
- Not validated for safety-critical or real-world deployment. Human review required.
Sources
1 source
Sources
1 sourceVerified Sep 2
Model artifacts
1 artifact
Model artifacts
1 artifactSource excerpts
2 excerpts
Source excerpts
2 excerpts--- license: agpl-3.0 library_name: ultralytics pipeline_tag: object-detection tags: - object-detection - yolo - yolov26 - ultralytics - violence-detection - surveillance - safety metrics: - mean_average_precision --- # Violence Detection — YOLOv26-s A single-class object detector that localizes **violence** in images/video frames. Fine-tuned from Ultralytics `yolo26s.pt` (COCO-pretrained). ## Model details | | | |---|---| | Architecture | YOLOv26-s (Ultralytics), task: `detect` | | Base weights | `yolo26s.pt` (COCO-pretrained) | | Classes | 1 — `Violence` | | Input size | 512 × 512 | | Training | 20 epochs, batch 12, cosine LR, AMP | | Framework | Ultralytics 8.4.12 | ## Evaluation (validation set) | Metric | Value | |---|---| | mAP@50 | **0.928** | | mAP@50-95 | 0.901 | | Precision | 0.918 | | Recall | 0.784 | ## Training data Trained on a custom YOLO-format dataset derived from surveillance/anomaly sources. The dataset-preparation scripts reference: - **ShanghaiTech Campus** anomaly dataset - **UCF-Crime** dataset > ⚠️ These source datasets are released under their own academic/research-use > terms and are **not redistributed** here. Only the fine-tuned weights are shared. > Verify you have the right to use this model for your use case. ## Usage ```python from ultralytics import YOLO model = YOLO("best.pt") results = model("image.jpg") # or a video / webcam stream for r in results: r.show() # display detections print(r.boxes.xyxy, r.boxes.conf) # boxes + confidence ``` ## License This model is derived from Ultralytics YOLO, which is **AGPL-3.0**. The weights are therefore distributed under **AGPL-3.0**. For closed-source/commercial use, obtain an [Ultralytics Enterprise License](https://ultralytics.com/license). ## Limitations - Single-class detector — flags "violence" regions only; no fine-grained action labels. - Trained on surveillance-style footage; may not generalize to other domains. - Not validated for safety-critical or real-world deployment. Human review required.
Source context: 68 downloads · 0 likes · Pipeline object-detection · Library ultralytics · Repo Manas-Maahir/violence-detection-yolov26
