updated app.py

app.py

@@ -17,7 +17,7 @@ torch_model.fc = nn.Sequential(
 tf_model = tf.keras.models.load_model('./models/tensorflow_model.keras')
 torch_model.load_state_dict(torch.load('./models/pytorch_model.pth', weights_only=True, map_location='cpu'))
 torch_model.eval()
-
+st.title("Pneumonia detection using CNNs")
 selected_model = st.selectbox(
     label = 'Select the model to make a prediction',
     options = ['TensorFlow', 'PyTorch'],
@@ -34,9 +34,6 @@ if uploaded_file is not None:
     # Convert to PIL Image
     image = Image.open(uploaded_file).convert("RGB")
 
-    # Display Uploaded Image
-    st.image(image, caption="Uploaded X-ray", use_container_width=True)
-
     image_size = 256  # Match model input size
     if selected_model == "PyTorch":
         # PyTorch Preprocessing
@@ -62,5 +59,10 @@ if uploaded_file is not None:
         prediction = tf_model.predict(image_array)[0][0]  # Extract single value
 
     # Display Prediction
-    st.write(f"**According to the model, there is a {prediction:.2f}% chance of having pneumonia!**")
+    st.header(
+        f"**According to the model, there is a {prediction*100:.2f}% chance of having pneumonia!**",
+        divider='blue'
+    )
+    # Display Uploaded Image
+    st.image(image, caption="Uploaded X-ray", use_container_width=True)