YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Thalos Fall Protection (Harness) Detection – v1.0 (Roboflow β†’ HuggingFace export)

This repository contains the Fall Protection (Harness) Detection model used in the Thalos Safety Intelligence platform.

It identifies fall-related PPE and risk conditions including:

  • full-body harness usage
  • missing harness when working at height
  • workers attached vs. not attached to anchor points
  • potential fall-from-height scenarios
  • unsafe usage of lanyards, hooks, or anchorages
  • people working near edges with or without proper fall protection

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.


πŸš€ Usage (Python)

from ultralytics import YOLO

model = YOLO("thalostech2025/thalos-fall-protection-v1/fall_protection_harness_weights.pt")

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


βΈ»

πŸ”— Load From URL (Used by the Thalos YOLO Service)

import torch
import requests
from io import BytesIO

HF_URL = "https://huggingface.co/thalostech2025/thalos-fall-protection-v1/resolve/main/fall_protection_harness_weights.pt"

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


βΈ»

🏷️ Labels / Classes

Based on the v1.0 dataset, the following classes are included:

harness_worn
harness_missing
lanyard_attached
lanyard_not_attached
person_at_height
edge_zone

(Label names may vary slightly depending on your final dataset schema.)

βΈ»

πŸ“„ License

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

βΈ»

πŸ”’ Important Notes
    β€’	This repository contains only the model weights, not the training data.
    β€’	Thalos uses this model through the internal YOLO inference microservice.
    β€’	Future versions (v2.0+) may incorporate pose estimation or depth to refine fall-risk understanding.
    β€’	Migrating this model to HF removes reliance on Roboflow cloud inference and its credit system.

βΈ»

πŸ‘€ Maintainer

Thalos Tech (2025)
Safety Intelligence & Hazard Detection Platform
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support