Update README.md

README.md

@@ -81,6 +81,61 @@ results[0].show()
 path = model.export(format="onnx")  # return path to exported model
 ```
 
+
+### Inference
+
+You can use the model with this code to see how it detects, the style you plot or save detected object is up to you, but here is an example:
+
+```python
+from ultralytics import YOLO
+import matplotlib.pyplot as plt
+import cv2
+
+# Load the YOLO model
+model = YOLO("path/to/local/model.pt")
+
+# Define the input image file path
+file_path = "path/to/image"
+
+# Get the prediction results
+results = model([file_path])
+
+# Read the input image
+img = cv2.imread(file_path)
+
+# Iterate over the results to extract bounding box and display both input and cropped output
+for result in results:
+    maxa = result.boxes.conf.argmax()  # Get the index of the highest confidence box
+    x, y, w, h = result.boxes.xywh[maxa]  # Extract coordinates and size
+    print(f"Bounding box: x={x}, y={y}, w={w}, h={h}")
+    
+    # Crop the detected object from the image
+    crop_img = img[int(y-h/2):int(y+h/2), int(x-w/2):int(x+w/2)]
+
+    # Convert the image from BGR to RGB for display with matplotlib
+    img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+    crop_img_rgb = cv2.cvtColor(crop_img, cv2.COLOR_BGR2RGB)
+
+    # Plot the input image and cropped image side by side
+    plt.figure(figsize=(10, 5))
+
+    # Display the input image
+    plt.subplot(1, 2, 1)
+    plt.imshow(img_rgb)
+    plt.title("Input Image")
+    plt.axis("off")
+
+    # Display the cropped image (output)
+    plt.subplot(1, 2, 2)
+    plt.imshow(crop_img_rgb)
+    plt.title("Cropped Output")
+    plt.axis("off")
+
+    plt.show()
+```
+
+
+
 See YOLOv8 [Python Docs](https://docs.ultralytics.com/usage/python/) for more examples.
 
 </details>