Update README.md

README.md

@@ -48,7 +48,6 @@ Our custom threat detection dataset was meticulously curated and annotated to en
 
 The model is trained to detect threats across various scales, from small concealed weapons to larger explosive devices.
 
----
 ## Performance Metrics
 
 ### Training Performance
@@ -85,52 +84,6 @@ The training process demonstrates excellent convergence with:
 - **Consistent recall** of 83-85% across all threat categories
 - **Robust generalization** from validation to test performance
 
-
-
-# Install dependencies
-pip install torch torchvision
-pip install supervision
-pip install rfdetr
-pip install pillow requests numpy
-```
-
-### Basic Usage
-
-```python
-import numpy as np
-import supervision as sv
-from PIL import Image
-from rfdetr import RFDETRNano
-
-# Load the model
-model = RFDETRNano(
-    resolution=640, 
-    pretrain_weights="checkpoint_best_total.pth"
-)
-model.optimize_for_inference()
-
-# Load and process image
-image = Image.open("your_image.jpg")
-detections = model.predict(image, threshold=0.5)
-
-# Threat class mapping
-THREAT_CLASSES = {
-    1: "gun",
-    2: "explosive", 
-    3: "grenade",
-    4: "knife"
-}
-
-# Generate labels
-labels = [
-    f"{THREAT_CLASSES[class_id]} {confidence:.2f}"
-    for class_id, confidence in zip(detections.class_id, detections.confidence)
-]
-
-print(f"Detected {len(labels)} threats: {labels}")
-```
-
-
 ## Model Architecture
 
 - **Base Architecture**: RF-DETR Nano