update app

app.py

@@ -5,7 +5,7 @@ import gradio as gr
 from gradio.themes.base import Base
 import cv2
 from tensorflow.keras.models import load_model
-model_path = "/content/drive/MyDrive/Pneumonia Classification/model/xray_model.h5"
+model_path = "xray_model.h5"
 model = load_model(model_path)
 def load_and_prepare_image(image_path):
     # Load the image
@@ -20,7 +20,7 @@ def load_and_prepare_image(image_path):
 
 def predict(image_path):
     if image_path is None:
-        return "Please upload an image.", "/content/How-AI-is-Used-in-Healthcare.png"
+        return "Please upload an image.", "How-AI-is-Used-in-Healthcare.png"
 
     # Prepare the image
     img = load_and_prepare_image(image_path)
@@ -35,15 +35,15 @@ def predict(image_path):
         else 'The X-ray indicates that the patient\'s lungs are normal.'
     )
 
-    return label, "/content/drive/MyDrive/Pneumonia Classification/images/How-AI-is-Used-in-Healthcare.png"
+    return label, "How-AI-is-Used-in-Healthcare.png"
 
 # Fixed image URL
-fixed_image_url = "/content/drive/MyDrive/Pneumonia Classification/images/How-AI-is-Used-in-Healthcare.png"
+fixed_image_url = "How-AI-is-Used-in-Healthcare.png"
 
 # Example images and their descriptions
 examples = [
-    ["/content/drive/MyDrive/Pneumonia Classification/images/normal.jpeg", "Normal X-ray image."],
-    ["/content/drive/MyDrive/Pneumonia Classification/images/pne.jpeg", "X-ray image indicating pneumonia."]
+    ["normal.jpeg", "Normal X-ray image."],
+    ["pne.jpeg", "X-ray image indicating pneumonia."]
 ]
 # Create the Gradio interface
 iface = gr.Interface(