thalostech2025/thalos-electrical-safety-v1

Thalos Electrical Safety Detection – v1.0 (Roboflow → HuggingFace export)

This repository contains the Electrical Safety Detection model used in the Thalos Safety Intelligence pipeline.
It identifies electrical safety hazards such as:

• damaged outlets
• overloaded sockets
• melted or burned receptacles
• exposed wiring
• unsafe electrical panels

This model was originally trained in Roboflow (Object Detection Large / YOLOv8-derived) and exported as a PyTorch .pt file.
It is now hosted on HuggingFace for independent, cost-controlled inference.

---

🔧 Model Details

• Architecture: Roboflow 3.0 Object Detection (Large) — YOLOv8-derived
• Format: PyTorch .pt
• Input Size: 640×640 (auto-resize enabled)
• Export Date: Dec 2025
• License: AGPL-3.0
• Intended Use: Workplace safety hazard detection (electrical module)

---

🚀 Usage (Python)

from ultralytics import YOLO

model = YOLO("thalostech2025/thalos-electrical-safety-v1/weights.pt")

results = model("example.jpg")
results.show()

---

📥 Load From URL (used by Thalos YOLO Service)

import torch
import requests
from io import BytesIO

HF_URL = "https://huggingface.co/thalostech2025/thalos-electrical-safety-v1/resolve/main/weights.pt"

response = requests.get(HF_URL)
model = torch.load(BytesIO(response.content), map_location="cpu")

---

📤 Labels / Classes

The following classes are included:

burned_socket
damaged_wire
faulty_board
exposed_circuit

(May include other hazard classes based on v1.0 dataset.)

---

📄 License

This model is distributed under the AGPL-3.0 license, consistent with Roboflow export requirements.

---

🔒 Important Notes

• This repository only contains the weights, not the training data.
• Thalos will use this model via server-side inference inside the YOLO service.
• Future versions (v2.0+) may be distilled or retrained to reduce size and improve recall.

---

✨ Maintainer

Thalos Tech (2025)
Safety Intelligence & Hazard Detection Platform
```