YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Thalos Construction PPE Detection β v1.0 (Roboflow β HuggingFace export)
This repository contains the Construction PPE Detection model used in the Thalos Safety Intelligence platform.
It identifies construction-specific PPE compliance and related hazards, including:
- hard hats (helmets)
- safety glasses
- high-visibility vests
- gloves
- missing PPE on workers
- partially worn or incorrectly used PPE
- workers present on active construction sites without adequate PPE
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.
π Usage (Python)
from ultralytics import YOLO
model = YOLO("thalostech2025/thalos-construction-ppe-v1/construction_ppe_weights.pt")
results = model("example.jpg")
results.show()
βΈ»
π Load From URL (Used by the Thalos YOLO Service)
import torch
import requests
from io import BytesIO
HF_URL = "https://huggingface.co/thalostech2025/thalos-construction-ppe-v1/resolve/main/construction_ppe_weights.pt"
response = requests.get(HF_URL)
model = torch.load(BytesIO(response.content), map_location="cpu")
βΈ»
π·οΈ Labels / Classes
Based on the v1.0 Roboflow dataset, the following classes are included:
hard_hat
no_hard_hat
safety_glasses
no_safety_glasses
hi_vis_vest
no_hi_vis_vest
gloves
no_gloves
(Class names may vary slightly depending on the finalized dataset schema.)
βΈ»
π License
This model is distributed under the AGPL-3.0 license, consistent with Roboflow export requirements.
βΈ»
π Important Notes
β’ This repository contains only the model weights, not training data.
β’ Thalos uses this model via server-side inference in the YOLO microservice.
β’ Future versions (v2.0+) may unify Construction PPE and Industrial PPE into a shared multi-industry PPE model.
β’ This migration removes reliance on Roboflow cloud inference to control cost and eliminate external runtime dependencies.
βΈ»
π€ Maintainer
Thalos Tech (2025)
Safety Intelligence & Hazard Detection Platform
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support