Downloads · 30 days
0
efficientad-metal-nut
MSherbinii/efficientad-metal-nut
efficientad-metal-nut is a machine learning model from MSherbinii. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
EfficientAD model for detecting scratches, bends, and flips in metal nuts
Access
Public
Updated Nov 13, 2025
Repo size
83 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth83 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Nov 13, 2025
- Updated
- Nov 13, 2025
- SHA
- 337d91ce
Model card
From the Hugging Face model README
EfficientAD - Metal Nut
EfficientAD model for detecting scratches, bends, and flips in metal nuts
Model Details
- Architecture: EfficientAD (Teacher-Student-Autoencoder)
- Model Size: Medium (512-dimensional features)
- Dataset: MVTec AD - Metal Nut
- AU-ROC: 99.7%
- Training: Custom training on Apple Silicon (MPS)
Files
teacher.pth: Pre-trained teacher network (31MB)student.pth: Trained student network (44MB)autoencoder.pth: Trained autoencoder (4.2MB)
Usage
import torch
# Load models
teacher = torch.load('teacher.pth')
student = torch.load('student.pth')
autoencoder = torch.load('autoencoder.pth')
Citation
@article{efficientad2023,
title={EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies},
author={Batzner, Kilian and Heckler, Lars and König, Rebecca},
journal={arXiv preprint arXiv:2303.14535},
year={2023}
}
Generated with Lumina Tech Platform
- License
- mit
- Created
- Nov 13, 2025
- Updated
- Nov 13, 2025