Update app.py

app.py

@@ -1,41 +1,15 @@
+import zipfile
 import os
-
-# Set the environment variable before importing tensorflow
-os.environ['PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION'] = 'python'
-
-import streamlit as st
 import tensorflow as tf
-from tensorflow.keras.models import load_model
-from tensorflow.keras.preprocessing import image
-import numpy as np
-from PIL import Image
-
-# Load the trained model
-model = load_model('your_trained_model_resnet50.keras')
 
-# Streamlit UI for uploading an image
-st.title("Tree Decoration Prediction Model")
+# Path to the zipped model file in Hugging Face
+zip_model_path = '/app/your_trained_model.keras.zip'
+unzipped_model_path = '/app/your_trained_model.keras'
 
-# Upload an image
-uploaded_file = st.file_uploader("Choose a tree image...", type="jpg")
+# Unzip the model file if not already unzipped
+if not os.path.exists(unzipped_model_path):
+    with zipfile.ZipFile(zip_model_path, 'r') as zip_ref:
+        zip_ref.extractall('/app')
 
-if uploaded_file is not None:
-    # Open the image file
-    img = Image.open(uploaded_file)
-    
-    # Preprocess the image for ResNet50 (resize, scale, etc.)
-    img = img.resize((224, 224))  # Resize to ResNet50 input size
-    img_array = np.array(img) / 255.0  # Normalize pixel values to [0, 1]
-    img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension
-    
-    # Predict if the tree is decorated or undecorated
-    prediction = model.predict(img_array)
-    
-    # Display the prediction result
-    if prediction[0] > 0.5:
-        st.write("The tree is decorated!")
-    else:
-        st.write("The tree is undecorated.")
-    
-    # Display the uploaded image
-    st.image(img, caption="Uploaded Image.", use_column_width=True)
+# Load the model
+model = tf.keras.models.load_model(unzipped_model_path)