Downloads · 30 days
0
helmet-detector
TristanF04/helmet-detector
helmet-detector is a machine learning model from TristanF04. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Goal: Classify if a person is wearing a safety helmet from an image.
Access
Public
Updated Sep 25, 2025
Parameters
11.2M
224 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors134 MB · 60%
At a glance
- Access
- Public
- Created
- Sep 25, 2025
- Updated
- Sep 25, 2025
- SHA
- adedc4a3
Model card
From the Hugging Face model README
Helmet vs No-Helmet Classifier (ResNet18)
Goal: Classify if a person is wearing a safety helmet from an image.
Tech: PyTorch, TorchVision, transfer learning (ResNet18), ONNX export.
Results (from Kaggle run)
- Train/Val/Test split: 70/15/15 on a small demo dataset (49 images total)
- Best validation accuracy: 100%
- Test accuracy: 90%
- Confusion Matrix (test):
Quickstart (Local)
python -m venv .venv
.venv\Scripts\activate
pip install -r requirements.txt
python infer.py sample_images/Helmet6.jpg
python infer.py sample_images/WithoutHelmet9.jpg
- Created
- Sep 25, 2025
- Updated
- Sep 25, 2025