Updated Models Checkpoints

README.md

@@ -1,3 +1,167 @@
----
-license: mit
----
+# VAE-GAN Checkpoints for MVTec Anomaly Detection
+
+This repository contains pre-trained VAE-GAN model checkpoints for visual anomaly detection on the MVTec AD dataset.
+
+## Overview
+
+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

checkpoints/model_bottle_64.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e7e4f788c7a4adfa9ab69d32121e5bb24c70dd81fe8e2e0c35fa3f00733ce90
+size 243981714

checkpoints/model_cable_64.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c926d9e723c50f8bd128b5c5985ce9348ba3115c27c392312f01f215a09d758a
+size 243984142

checkpoints/model_capsule_64.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de1abe968776b819d7960d3ac7269237e31b05a850fa9f68d248f4ad2480f27
+size 243981782

checkpoints/model_carpet_64.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96534c58540fe2df4e9d9b29a02e447bafef3b6e04af32f6f063a0379cdc8a84
+size 243974162

checkpoints/model_grid_64.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77d81e5ac0c555830f7b64f521835bd757c4750c7485e108ae48d62d745b9927
+size 243975882

checkpoints/model_hazelnut_64.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:454c1e6eed8e1db67ffb661abdc505bd52159284158f3d9a6d0bb77b8b9c52fe
+size 243981850

checkpoints/model_leather_64.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe660e2b757e317455c2f8dec1ab2350fa61c628a75976bddd7c6173c06f89d
+size 243983702

checkpoints/model_metal_nut_64.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed4ca546d20fb798b777a4f70242edeab7182018fcfbf1feadb0ba662f26c817
+size 243982174

checkpoints/model_pill_64.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920d916b7fcdb726e658f7b297c788d84c9881c54c6b20c33da580859aaf8e51
+size 243974922

checkpoints/model_screw_64.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b18a892ea06ea0f199ce5b6a06a697a06b94c4fcb9dcaa9651d4d1be108c2777
+size 243982606

checkpoints/model_tile_64.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26f4ac0c2feb6c385368ef18b7399bb71ef813476d3d1297a0b4b9fafe235fa6
+size 243979402

checkpoints/model_toothbrush_64.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62f898daa40983db6953f3a206385b427afde0fa068bea28753833ce4eafc8f
+size 243975266

checkpoints/model_transistor_64.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33d2b687364ad425198bbe6129bdf8713a8c780e20c82e21ade26a877581d0f4
+size 243982114

checkpoints/model_wood_64.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15c05f7abbaf91310d43ffea1ae6ca1ed8c6631123426e99ff5ea0c6ccad96c8
+size 243983114

checkpoints/model_zipper_64.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc2464f10125594b15302c906add22a5410c66b6eb178748b633b769b1e79b70
+size 243982994