Update app.py

app.py

@@ -1,52 +1,40 @@
 import streamlit as st
-from tensorflow.keras.models import load_model
+import tensorflow as tf
 from tensorflow.keras.preprocessing import image
 import numpy as np
 from PIL import Image
 
 # Function to load and preprocess the uploaded image
 def load_and_preprocess_image(uploaded_image, target_size=(224, 224)):
-    img = Image.open(uploaded_image)  # Open the uploaded image
-    img = img.resize(target_size)     # Resize to match model's input shape
-    img_array = np.array(img)         # Convert to numpy array
-    img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension
-    img_array = img_array / 255.0     # Normalize pixel values
+    img = Image.open(uploaded_image)
+    img = img.resize(target_size)
+    img_array = np.array(img)
+    img_array = np.expand_dims(img_array, axis=0)
+    img_array = img_array / 255.0
     return img_array
 
-# Load your pre-trained model (assuming it's in HDF5 format)
-@st.cache(allow_output_mutation=True)  # Cache the model to avoid reloading it each time
+# Load your pre-trained model
 def load_cnn_model():
-    model = load_model('dementia_cnn_model.h5')  # Replace with your model path
+    model = tf.keras.models.load_model('dementia_cnn_model.h5')  # Ensure correct loading
     return model
 
 # Streamlit App UI
 st.title("Dementia Detection using CNN")
 st.write("Upload a brain scan (JPG format), and the model will predict its class.")
 
-# Upload image button
 uploaded_file = st.file_uploader("Choose a JPG image...", type="jpg")
 
-# If an image is uploaded, process it
 if uploaded_file is not None:
     st.image(uploaded_file, caption="Uploaded Image", use_column_width=True)
     st.write("Classifying...")
+
+    processed_image = load_and_preprocess_image(uploaded_file)
     
-    # Preprocess the uploaded image
-    processed_image = load_and_preprocess_image(uploaded_file, target_size=(224, 224))
-    
-    # Load the model
-    model = load_cnn_model()
-    
-    # Make predictions
+    model = load_cnn_model()  # Load the model
     predictions = model.predict(processed_image)
     predicted_class = np.argmax(predictions, axis=1)
     
-    # Map the class index to the actual class names
     class_names = ['Moderate Dementia', 'Very Mild Dementia', 'Mild Dementia', 'Non Demented']
     result = class_names[predicted_class[0]]
     
-    # Display the prediction
     st.write(f"Predicted Class: **{result}**")
-else:
-    st.write("Please upload an image to classify.")
-