added instructions for extracting bounding boxes

YOLONAS.md

@@ -27,11 +27,13 @@ YOLO-NAS's architecture employs quantization-aware blocks and selective quantiza
 
 ## Quickstart
 
+## Extract bounding boxes 
 ```python
-import super_gradients
-
-yolo_nas = super_gradients.training.models.get("yolo_nas_l", pretrained_weights="coco").cuda()
-yolo_nas.predict("https://deci-pretrained-models.s3.amazonaws.com/sample_images/beatles-abbeyroad.jpg").show()
+prediction = output[0].prediction
+bboxes = prediction.bboxes_xyxy                     # [[Xmin,Ymin,Xmax,Ymax],..] list of all annotation(s) for detected object(s) 
+class_names = prediction.class_names.               # ['Class1', 'Class2', ...] List of the class names
+class_name_indexes = prediction.labels.astype(int)  # [2, 3, 1, 1, 2, ....] Index of each detected object in class_names(corresponding to each bounding box)
+confidences =  prediction.confidence.astype(float)  # [0.3, 0.1, 0.9, ...] Confidence value(s) in float for each bounding boxes
 ```
 
 ![YOLO-NAS Predict Demo](documentation/source/images/yolo_nas_predict_demo.png)