Update app.py

app.py

@@ -7,12 +7,29 @@ from tensorflow.keras.applications.vgg16 import preprocess_input
 from tensorflow.keras.preprocessing import image
 
 # Loading Models
-# braintumor_model = load_model('models/brain_tumor_binary.h5')
-braintumor_model = load_model('models/braintumor.h5')
+braintumor_model = load_model('models/brain_tumor_binary.h5')
 
 # Configuring Streamlit
-st.set_page_config(page_title="Brain Tumor Prediction App", page_icon=":brain:")
+st.set_page_config(
+    page_title="Brain Tumor Prediction App",
+    page_icon=":brain:",
+    layout="centered",
+)
+
+# Streamlit app title and description
+st.title("Brain Tumor Prediction App")
+st.write(
+    "Upload an image, and the app will predict whether a brain tumor is present or not."
+)
 
+# Add Streamlit sidebar for additional information or options
+st.sidebar.title("About")
+st.sidebar.info(
+    "This app uses a trained model to predict brain tumors from images. "
+    "The model is based on VGG16 architecture."
+)
+
+# Function to preprocess the image
 def preprocess_image(img):
     # If it's a NumPy array, use it directly
     if isinstance(img, np.ndarray):
@@ -79,6 +96,31 @@ iface = gr.Interface(
     fn=predict_braintumor,
     inputs="image",
     outputs="text",
-    examples=[["examples/1_no.jpeg"], ["examples/2_no.jpeg"], ["examples/3_no.jpg"], ["examples/Y1.jpg"], ["examples/Y2.jpg"], ["examples/Y3.jpg"]]
+    examples=[["examples/1_no.jpeg"], ["examples/2_no.jpeg"], ["examples/3_no.jpg"], ["examples/Y1.jpg"], ["examples/Y2.jpg"], ["examples/Y3.jpg"]],
+    live=True  # Allows real-time updates without restarting the app
 )
+
+# Display Gradio interface
 iface.launch()
+
+# Streamlit components below the Gradio interface
+uploaded_file = st.file_uploader("Choose an MRI image", type=["jpg", "jpeg"])
+
+if uploaded_file is not None:
+    # Display the uploaded image
+    st.image(uploaded_file, caption="Uploaded MRI Image.", use_column_width=True)
+    
+    # Perform prediction when the "Predict" button is clicked
+    if st.button("Predict"):
+        # Preprocess the image
+        img_array = preprocess_image(uploaded_file)
+
+        # Make prediction
+        pred = braintumor_model.predict(img_array)
+
+        # Handle binary decision
+        confidence = pred[0][0]
+        result = "Brain Tumor Not Found!" if binary_decision(confidence) == 1 else "Brain Tumor Found!"
+
+        # Display the prediction result
+        st.write(result)