thalostech2025/thalos-industrial-ppe-v1

Thalos Industrial PPE Detection – v1.0 (Roboflow → HuggingFace export)

This repository contains the Industrial PPE Detection model used in the Thalos Safety Intelligence platform.
It identifies PPE compliance and workplace hazards related to industrial personal protective equipment, including:

• gloves
• safety glasses
• hard hats
• respirators / masks
• high-visibility vests
• protective clothing
• missing or incorrect PPE
• improper PPE usage in industrial settings

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 inside the Thalos YOLO service.

---

🧪 Usage (Python)

from ultralytics import YOLO

model = YOLO("thalostech2025/thalos-industrial-ppe-v1/industrial_ppe_weights.pt")

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


⸻

🔗 Load From URL (Used by the Thalos YOLO Service)

import torch
import requests
from io import BytesIO

HF_URL = "https://huggingface.co/thalostech2025/thalos-industrial-ppe-v1/resolve/main/industrial_ppe_weights.pt"

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


⸻

🏷️ Labels / Classes

gloves
safety_glasses
hard_hat
hi_vis_vest
respirator_mask
protective_clothing
no_ppe_detected

(Note: label names may vary slightly depending on v1.0 dataset; update if needed.)

⸻

📄 License

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

⸻

🔒 Important Notes
    •	This repository includes only the model weights, not the training data.
    •	Thalos uses this model for server-side inference through the YOLO service.
    •	Future versions (v2.0+) may be consolidated with construction-PPE models or retrained with multi-industry datasets.

⸻

👤 Maintainer

Thalos Tech (2025)
Safety Intelligence & Hazard Detection Platform

---

# 🧪 **PHASE 4 — Ready for Cursor**
Once you upload the weights & commit the model card:

Tell me:  
**“Ready for the Cursor integration prompt.”**  

I will generate:

- the exact `HOUSEKEEPING_MODEL_URL`-style env variable  
- the YOLO service registry entry  
- everything Cursor needs to add the new detector cleanly and safely  

---