Update app.py

app.py

@@ -1,31 +1,39 @@
 import streamlit as st
-from tensorflow.keras.models import load_model  # Use TF 2.x compatible import
-from tensorflow.keras.preprocessing import image
-from tensorflow.keras.applications.vgg16 import preprocess_input  # Import preprocessing function
+from keras.models import load_model
+from keras.applications.vgg16 import preprocess_input
 import numpy as np
+from PIL import Image
+import tensorflow as tf
 
-def load_model():
-    """Loads the pre-trained chest X-ray classification model."""
-    return load_model('chest_xray.h5')  # Assuming the model is saved as 'chest_xray.h5'
+# Load your pre-trained model
+model = load_model('chest_xray.h5')
 
-# Cache the model loading process for efficiency
-model = st.cache(load_model, allow_output_mutation=True)()
+st.title('Pneumonia Detection from Chest X-Ray Images')
 
-st.title("Pneumonia Detection App")
+# Create a file uploader to upload images
+uploaded_file = st.file_uploader("Choose an X-ray image...", type=["jpg", "jpeg", "png"])
 
-uploaded_file = st.file_uploader("Upload a chest X-ray image", type=["jpg", "jpeg", "png"])
+def predict(image):
+    # Preprocess the image to get it into the right format for the model
+    img = image.resize((224,224))
+    x = tf.keras.preprocessing.image.img_to_array(img)
+    x = np.expand_dims(x, axis=0)
+    img_data = preprocess_input(x)
+    
+    # Make the prediction
+    classes = model.predict(img_data)
+    return int(classes[0][0])
 
 if uploaded_file is not None:
-    img = image.load_img(uploaded_file, target_size=(224, 224))  # Load image with target size
-    x = image.img_to_array(img)  # Convert image to array
-    x = np.expand_dims(x, axis=0)  # Add a dimension for batch processing
-    img_data = preprocess_input(x)  # Preprocess image for VGG16
-
-    prediction = model.predict(img_data)
-    result = int(prediction[0][0])
-
+    # Display the uploaded image
+    st.image(uploaded_file, caption='Uploaded X-ray Image', use_column_width=True)
+    st.write("")
+    st.write("Classifying...")
+    image = Image.open(uploaded_file)
+    
+    # Predict and display the results
+    result = predict(image)
     if result == 0:
-        st.write("**Person is Affected By PNEUMONIA**")
+        st.write("Person is Affected By PNEUMONIA")
     else:
-        st.write("**Result is Normal**")
-
+        st.write("Result is Normal")