The models were trained in a one-class anomaly detection setting using only normal training images. During inference, each input image is reconstructed by the VAE-GAN model, and anomaly scores are computed from the reconstruction error between the input and reconstructed image.

These checkpoints are useful for:

Reconstruction-based anomaly detection
Threshold selection experiments
Multi-point threshold evaluation
Anomaly localization
Explainable anomaly detection
Baseline comparison with AE, VAE, PatchCore, PaDiM, and other methods

Dataset

The checkpoints are trained on MVTec AD object and texture categories.

Reference:

bibtex

@article{bergmann2021mvtec,
  title={The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection},
  author={Bergmann, Paul and Batzner, Kilian and Fauser, Michael and Sattlegger, David and Steger, Carsten},
  journal={International Journal of Computer Vision},
  year={2021}
}

Available Checkpoints

Category	Checkpoint
Bottle	model_bottle_64.pt
Cable	model_cable_64.pt
Capsule	model_capsule_64.pt
Carpet	model_carpet_64.pt
Grid	model_grid_64.pt
Hazelnut	model_hazelnut_64.pt
Leather	model_leather_64.pt
Metal Nut	model_metal_nut_64.pt
Pill	model_pill_64.pt
Screw	model_screw_64.pt
Tile	model_tile_64.pt
Toothbrush	model_toothbrush_64.pt
Transistor	model_transistor_64.pt
Wood	model_wood_64.pt
Zipper	model_zipper_64.pt

Model Details

Property	Value
Model	VAE-GAN
Training Setting	One-Class Learning
Training Data	Normal Samples Only
Input Size	128 × 128 × 3
Latent Dimension	64
Framework	PyTorch

Checkpoint Structure

Each checkpoint contains:

python

{
    "encoder_state_dict": ...,
    "decoder_state_dict": ...,
    "discriminator_state_dict": ...
}

Loading a Checkpoint

python

import torch

checkpoint = torch.load(
    "model_bottle_64.pt",
    map_location="cpu",
    weights_only=False
)

encoder.load_state_dict(checkpoint["encoder_state_dict"])
decoder.load_state_dict(checkpoint["decoder_state_dict"])
discriminator.load_state_dict(checkpoint["discriminator_state_dict"])

encoder.eval()
decoder.eval()
discriminator.eval()

Example Anomaly Score

python

with torch.no_grad():
    mu, logvar = encoder(image)
    z = reparameterize(mu, logvar)
    reconstruction = decoder(z)

anomaly_map = torch.abs(image - reconstruction).mean(dim=1)
anomaly_score = anomaly_map.mean().item()

Device Support

The checkpoints can be loaded on:

CPU
NVIDIA CUDA GPUs
Apple Silicon (MPS)

python

import torch

if torch.cuda.is_available():
    device = "cuda"
elif torch.backends.mps.is_available():
    device = "mps"
else:
    device = "cpu"

Intended Use

This repository is intended for research on:

Visual Anomaly Detection
Reconstruction-Based Anomaly Scoring
Threshold Calibration
Multi-Point Thresholding
Explainable Anomaly Detection
Industrial Inspection Systems

Limitations

Models are trained on resized 128×128 images.
Performance depends on preprocessing, anomaly score design, and threshold selection.
These checkpoints are intended for research purposes and should be validated before deployment in industrial or safety-critical environments.

Citation

bibtex

@misc{rao2026vaeganmvtec,
  title={VAE-GAN Checkpoints for MVTec Anomaly Detection},
  author={Rao, Rashid},
  year={2026},
  publisher={Hugging Face},
  url={https://huggingface.co/rashidrao/AnomalyDetection}
}

Author

Rashid Rao
Industrial PhD Researcher
University of Turin, Italy

Research Areas:

Explainable AI (XAI)
Visual Anomaly Detection
Trustworthy AI
Industrial AI Systems

rashidrao/AD_MVTec

VAE-GAN Checkpoints for MVTec Anomaly Detection

Overview

Dataset

Available Checkpoints

Model Details

Checkpoint Structure

Loading a Checkpoint

Example Anomaly Score

Device Support

Intended Use

Limitations

Citation

Author

rashidrao/
AD_MVTec