Update app.py

app.py

@@ -1,6 +1,12 @@
+import os
+# Set the environment variable to use the pure-Python implementation of protobuf
+os.environ['PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION'] = 'python'
+
+# Now import TensorFlow
 import tensorflow as tf
 import streamlit as st
-import os
+from PIL import Image
+import numpy as np
 
 # Load the model
 model = tf.keras.models.load_model('your_model.keras')
@@ -10,7 +16,19 @@ st.title('Tree Decoration Prediction')
 
 # Example usage in your Streamlit app
 uploaded_image = st.file_uploader("Upload an image", type=["jpg", "png"])
+
 if uploaded_image:
-    st.image(uploaded_image, caption="Uploaded Image.", use_column_width=True)
-    prediction = model.predict(uploaded_image)
-    st.write(f"Prediction: {prediction}")
+    # Open and display the image
+    img = Image.open(uploaded_image)
+    st.image(img, caption="Uploaded Image.", use_column_width=True)
+
+    # Preprocess the image to match model input
+    img = img.resize((224, 224))  # Resize if necessary to match your model input size
+    img_array = np.array(img) / 255.0  # Normalize the image (if necessary)
+    img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension
+
+    # Get the prediction
+    prediction = model.predict(img_array)
+
+    # Show prediction result
+    st.write(f"Prediction: {prediction[0][0]}")  # Adjust according to your model's output format