Update README.md

README.md

@@ -28,58 +28,3 @@ It combines **Temporal Convolutional Networks (TCN)**, **Bidirectional LSTMs**,
 - 💾 **Lightweight, Scalable Architecture** — works on CPU/GPU and deploys easily to Hugging Face Spaces or Streamlit
 
 ---
-
-## 🏗️ Project Structure
-
-CHRONOGUARD/
-│
-├── data/
-│ ├── synthetic_data.csv # demo dataset
-│ ├── heatmap_scores.png # anomaly attention map
-│ ├── heatmap_saliency.png # gradient-based saliency map
-│
-├── models/
-│ ├── tcn_block.py # Temporal Convolutional Network module
-│ ├── attention_block.py # Attention mechanism
-│ ├── chronoguard_model.py # Full hybrid model definition
-│
-├── train_chronoguard.py # training script
-├── inference_chronoguard.py # run inference & generate heatmaps
-├── utils.py # data loaders, metrics, helpers
-├── visualization.py # heatmap + explainability tools
-│
-├── notebooks/
-│ └── ChronoGuard_Demo.ipynb # ready-to-run Colab notebook
-│
-├── requirements.txt
-├── README.md
-├── LICENSE
-└── config.yaml
-
-
----
-
-## 📊 Example Workflow
-
-1. **Prepare Data**
-   ```bash
-   python utils.py --generate-synthetic
-   
-   
-2. **Train the Model**
-   ```bash
-   python train_chronoguard.py --epochs 10 --batch_size 32
-
-
-
-3. **Run Inference**
-   ```bash
-   python inference_chronoguard.py --input data/synthetic_data.csv
-
-
-4. **Visualize Heatmaps**
-   ```bash
-   python visualization.py --input results/predictions.csv
-
-
-Outputs are saved under data/heatmap_scores.png and data/heatmap_saliency.png.