---
language: 
- en
license: mit
library_name: pytorch
tags:
- autoencoder
- anomaly-detection
- computer-vision
- manufacturing
- onnx
- openvino
- edge-ai
pipeline_tag: image-classification
base_model: custom/autoencoder
datasets:
- custom
metrics:
- reconstruction-error
---

# Anomaly Detection Model – Edge AI for Casting Defect Inspection

## Overview
The **Anomaly Detection Model** is an **autoencoder-based anomaly detection system** fine-tuned for industrial **casting defect inspection**. It identifies whether a metal casting image is *normal (OK)* or *defective* by reconstructing input images and analyzing reconstruction errors.

This model is designed for **Edge AI deployment**, optimized via **ONNX** and **OpenVINO IR** formats to run efficiently on low-power Intel edge devices.

---

## Model Details
- **Architecture:** Convolutional Autoencoder
- **Framework:** PyTorch
- **Training Objective:** Minimize reconstruction loss (MSE) for normal samples
- **Optimization:** ONNX and OpenVINO IR export for edge inference
- **Task:** Unsupervised anomaly detection
- **Domain:** Industrial visual inspection

---

## Repository Structure
```
├── casting_autoencoder.pth    # Trained PyTorch model
├── casting_autoencoder.onnx   # ONNX export
├── model.bin                  # OpenVINO IR model (bin)
├── model.xml                  # OpenVINO IR model (xml)
├── model_card.yaml
├── requirements.txt           # Dependencies
├── inference.py               # inference code
└── README.md                  # Model card (this file)
```

---

## Dataset
**Dataset:** Casting Product Image Dataset (Kaggle)
- **Classes:** Defective / Normal
- **Modality:** Grayscale industrial images
- **Training Strategy:** Only *normal* samples used for training the autoencoder.

---

## Key Configuration Parameters

- **Image Size**: 304×304 pixels
- **Batch Size**: 32
- **Learning Rate**: 1e-3
- **Epochs**: 10
- **Loss Function**: MSE Loss
- **Optimizer**: Adam


## Model Outputs

The training script generates:

- `casting_autoencoder.pth` - PyTorch model weights
- `casting_autoencoder.onnx` - ONNX export for deployment
- Calibrated anomaly threshold based on defective samples


## Anomaly Detection Process

1. **Training Phase**: Model learns to reconstruct normal casting images
2. **Threshold Calibration**: Uses defective samples to determine optimal threshold
3. **Inference**: Images with reconstruction error > threshold are flagged as defective

## Performance

- **Final Training Loss**: 0.0005
- **Suggested Threshold**: 0.0004
- **Model Type**: Unsupervised anomaly detection
- **Architecture**: Convolutional Autoencoder


## Applications

This model is designed for:

- Quality control in metal casting manufacturing
- Real-time defect detection on production lines
- Automated visual inspection systems
- Edge deployment in industrial environments


## Model Features

- **Unsupervised Learning**: Trained only on normal samples
- **Real-time Capable**: Optimized for edge deployment
- **ONNX Compatible**: Ready for production deployment
- **Automatic Thresholding**: Self-calibrating anomaly detection
- **Industrial Grade**: Tested on real manufacturing data


## Technical Details

The model uses a symmetric encoder-decoder architecture with:

- Stride-2 convolutions for downsampling
- Transposed convolutions for upsampling
- ReLU activation in hidden layers
- Sigmoid output activation for pixel reconstruction.

---

## Export & Deployment
| Format | Purpose |
|---------|----------|
| `.pth` | Original PyTorch model |
| `.onnx` | Framework-independent inference |
| `.xml` / `.bin` | OpenVINO IR format for edge devices |

**Edge Optimization:** Model converted and optimized using `openvino.convert_model()`.


---

## Intended Use
- Automated visual inspection for manufacturing/QA systems.
- Real-time edge deployment in industrial environments.

**Not recommended for:**
- Non-industrial datasets.
- Scenarios with significant domain drift (e.g., lighting changes or non-casting objects).

---

## Limitations
- Accuracy depends on lighting and background consistency.
- Model trained primarily on grayscale casting images.
- Thresholds for anomaly detection must be tuned for specific deployment environments.

---

## License
This project is released under the MIT License.

---

## Author
**Arunima Surendran**  
Applied AI  Engineer  
[GitHub Repository](https://github.com/arunimakanavu/anomalydetectionmodel)

---