This Python script implements an anomaly detection system using a combination of a Transformer-based autoencoder and a Generative Adversarial Network (GAN). The system is designed to detect anomalies in credit card transaction data.
- Utilizes a Transformer Autoencoder to learn the underlying patterns in the data.
- Incorporates a GAN architecture to enhance the detection of anomalies.
- Implements contrastive learning for improved feature representation learning.
- Provides evaluation metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and accuracy.
- Python 3.x
- PyTorch
- pandas
- matplotlib
-
Clone the repository:
git clone https://github.com/your_username/your_repository.git cd your_repository