Update app.py

app.py

@@ -9,59 +9,51 @@ import os
 # Load the model and label encoder
 @st.cache_resource
 def load_resources():
-    model = load_model('captains_cv2_model.keras')
+    # Custom loading to handle compatibility
+    try:
+        model = load_model('captains_cv2_model.keras', compile=False)  # Load without compiling first
+    except Exception as e:
+        st.error(f"Model loading failed: {str(e)}")
+        raise
     with open('label_encoder.pkl', 'rb') as file:
         le = pickle.load(file)
     return model, le
 
 # Preprocess the image
 def preprocess_image(image_path):
-    # Read and convert image
     img1 = cv2.imread(image_path)
     img1 = cv2.resize(img1, (64, 64))  # Resize to 64x64
-    img1 = np.asarray(img1)  # Convert to numpy array, shape will be (64, 64, 3)
+    img1 = np.asarray(img1)  # Shape: (64, 64, 3)
+    img1 = img1[np.newaxis, :, :, :]  # Shape: (1, 64, 64, 3)
     return img1
 
 # Main app
 def main():
-    # Load resources
     model, le = load_resources()
     
-    # Streamlit UI
     st.title("Image Classification App")
     st.write("Upload an image to get a prediction")
     
-    # File uploader
     uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
     
     if uploaded_file is not None:
-        # Display uploaded image
         image = Image.open(uploaded_file)
         st.image(image, caption='Uploaded Image', use_column_width=True)
         
-        # Get original file extension
         file_extension = os.path.splitext(uploaded_file.name)[1].lower()
         temp_filename = f"temp_image{file_extension}"
         
-        # Save temporary file with original extension
         with open(temp_filename, "wb") as f:
             f.write(uploaded_file.getvalue())
         
         try:
-            # Preprocess image
             processed_img = preprocess_image(temp_filename)
-            
-            # Display shape for debugging
             st.write(f"Processed image shape: {processed_img.shape}")
             
-            # Make prediction
             prediction = model.predict(processed_img)
             predicted_class = le.inverse_transform([np.argmax(prediction)])
             
-            # Display prediction
             st.write("Prediction:", predicted_class[0])
-            
-            # Display prediction probabilities
             st.write("Prediction Probabilities:")
             for class_name, prob in zip(le.classes_, prediction[0]):
                 st.write(f"{class_name}: {prob:.4f}")
@@ -69,7 +61,6 @@ def main():
         except Exception as e:
             st.error(f"An error occurred: {str(e)}")
         
-        # Clean up temporary file
         if os.path.exists(temp_filename):
             os.remove(temp_filename)