Create app.py

app.py

@@ -0,0 +1,66 @@
+import cv2
+import gradio as gr
+import requests
+import pickle
+import numpy as np
+
+# Function to predict and show bounding boxes
+def predict_and_show_bounding_boxes(image_path):
+    try:
+        # Load the image using cv2
+        img = cv2.imread(image_path)
+        if img is None:
+            print(f"Error: Could not load image at {image_path}")
+            return None, "Error: Could not load image"
+
+        # Perform inference using the loaded YOLO model (assuming 'model' is loaded)
+        results = model.predict(source=image_path, save=False, conf=0.5)
+        result = results[0]
+        boxes = result.boxes
+
+        if len(boxes) == 0:
+            # No defects found, show the zero defects image
+            zero_defects_img = cv2.imread('zero_defects.png')  # Assuming 'zero_defects.png' is in the same directory
+            if zero_defects_img is not None:
+                img = zero_defects_img
+                return img
+            else:
+                return None, "Error: Could not load zero defects image"
+
+        for box in boxes:
+            xyxy = box.xyxy[0].tolist()
+            x_min, y_min, x_max, y_max = int(xyxy[0]), int(xyxy[1]), int(xyxy[2]), int(xyxy[3])
+            conf = box.conf[0].item()
+            cls = int(box.cls[0])
+            cv2.rectangle(img, (x_min, y_min), (x_max, y_max), (0, 255, 0), 2)
+            label = f"{result.names[cls]}: {conf:.2f}"
+            cv2.putText(img, label, (x_min, y_min - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2)
+
+        # Return the processed image
+        return img
+
+    except Exception as e:
+        print(f"An error occurred during prediction: {e}")
+        return None, str(e)
+
+
+try:
+    with open('yolo_modelnano.pkl', 'rb') as file:  # Assuming 'yolo_modelnano.pkl' is in the same directory
+        model = pickle.load(file)
+    print("YOLO model loaded successfully.")
+except FileNotFoundError:
+    print("Error: 'yolo_modelnano.pkl' not found.")
+except Exception as e:
+    print(f"An error occurred while loading the model: {e}")
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=predict_and_show_bounding_boxes,
+    inputs=gr.Image(type="filepath"),
+    outputs=[gr.Image()],
+    title="Defect Detection",
+    description="Upload an image to detect defects"
+)
+
+# Launch the interface with appropriate settings for PythonAnywhere
+iface.launch(server_name="0.0.0.0", server_port=8080)  # Example settings, adjust as needed