Update app.py

app.py

@@ -10,29 +10,23 @@ model = load_model('cnn_model.h5')
 label_binarizer = pickle.load(open('label_transform.pkl', 'rb'))
 
 # Function to convert images to array
-def convert_image_to_array(image):
+def convert_image_to_array(image_dir):
     try:
-        # Debugging: Print image type and size
-        print(f"Image type: {type(image)}")
-        print(f"Image size: {len(image)} bytes")
-
-        image = cv2.imdecode(np.frombuffer(image, np.uint8), cv2.IMREAD_COLOR)
-
+        image = cv2.imdecode(np.frombuffer(image_dir, np.uint8), cv2.IMREAD_COLOR)
         if image is not None:
-            print(f"Decoded image shape: {image.shape}")
-            image = cv2.resize(image, (256, 256))
-            print(f"Resized image shape: {image.shape}")
+            image = cv2.resize(image, (256, 256))   
             return img_to_array(image)
         else:
-            print("Image decoding returned None")
             return np.array([])
     except Exception as e:
-        print(f"Error: {e}")
+        print(f"Error : {e}")
         return None
 
-def predict_image(image):
+def predict(image):
     try:
-        image_array = convert_image_to_array(image)
+        # Convert the image to an array
+        _, image_data = cv2.imencode('.jpg', image)
+        image_array = convert_image_to_array(image_data.tobytes())
 
         if image_array.size == 0:
             return "Invalid image"
@@ -51,14 +45,15 @@ def predict_image(image):
     except Exception as e:
         return str(e)
 
-# Define Gradio interface
-interface = gr.Interface(
-    fn=predict_image, 
-    inputs=gr.Image(type="numpy"), 
+# Create a Gradio interface
+iface = gr.Interface(
+    fn=predict, 
+    inputs=gr.inputs.Image(type="numpy", label="Upload an image"), 
     outputs="text",
     title="Image Classification",
-    description="Upload an image to get the predicted class."
+    description="Upload an image to classify it."
 )
 
+# Launch the interface
 if __name__ == "__main__":
-    interface.launch(share=True)
+    iface.launch()