Add debug logging and alpha channel fix

app.py

@@ -5,72 +5,89 @@ from tensorflow.keras.preprocessing import image
 import numpy as np
 from PIL import Image
 import io
+import sys # Added for logging
 
-# Initialize Flask with standard folders
 app = Flask(__name__, template_folder='templates', static_folder='static')
 
-# 1. Load Model
+# 1. Load Model (Safe Mode)
 MODEL_PATH = 'model.h5'
 try:
-    model = load_model(MODEL_PATH)
-    print("Model loaded successfully!")
+    # compile=False prevents crashing if the model was trained on a different TF version
+    model = load_model(MODEL_PATH, compile=False)
+    print("SUCCESS: Model loaded!", file=sys.stderr)
 except Exception as e:
-    print(f"Error loading model: {e}")
+    print(f"CRITICAL ERROR: Failed to load model. {e}", file=sys.stderr)
 
 CLASS_NAMES = ['NonDemented', 'VeryMildDemented', 'MildDemented', 'ModerateDemented']
 
 def prepare_image(img_bytes):
-    img = Image.open(io.BytesIO(img_bytes))
-    img = img.resize((224, 224))
-    img_array = image.img_to_array(img)
-    img_array = np.expand_dims(img_array, axis=0)
-    img_array = img_array / 255.0
-    return img_array
+    try:
+        img = Image.open(io.BytesIO(img_bytes))
+        
+        # FIX 1: Convert to RGB to remove Alpha channel (transparency) if present
+        if img.mode != 'RGB':
+            img = img.convert('RGB')
+            
+        # FIX 2: Resize
+        img = img.resize((224, 224))
+        
+        img_array = image.img_to_array(img)
+        img_array = np.expand_dims(img_array, axis=0)
+        img_array = img_array / 255.0
+        return img_array
+    except Exception as e:
+        print(f"Error processing image: {e}", file=sys.stderr)
+        raise e
 
 # --- ROUTES ---
 
-# 1. Main Page
 @app.route('/')
 def home():
     return render_template('index.html')
 
-# 2. FIX: Explicitly serve the assets folder
 @app.route('/assets/<path:filename>')
 def serve_assets(filename):
     return send_from_directory('static/assets', filename)
 
-# 3. FIX: Serve root files (like brain.svg)
 @app.route('/<path:filename>')
 def serve_root_files(filename):
-    # Only serve if the file exists in static (avoids crashing on bad links)
     if os.path.exists(os.path.join('static', filename)):
         return send_from_directory('static', filename)
     return "File not found", 404
 
-# 4. Handle Predictions
-# Updated Predict Function - Accepts ANY file name
+# Predict Route (Accepts any file key)
 @app.route('/api/classify', methods=['POST'])
 def predict():
-    # Check if ANY file was uploaded
     if not request.files:
         return jsonify({'error': 'No file uploaded'}), 400
     
-    # Grab the first file found, regardless of its key name ('file', 'image', 'img', etc.)
+    # Grab the first file
     file = next(iter(request.files.values()))
     
     try:
+        # Debug print
+        print(f"Received file: {file.filename}", file=sys.stderr)
+        
         processed_img = prepare_image(file.read())
+        
+        print("Image processed. predicting...", file=sys.stderr)
         prediction = model.predict(processed_img)
+        
         class_index = np.argmax(prediction)
         confidence = float(np.max(prediction))
         
+        result_class = CLASS_NAMES[class_index]
+        print(f"Prediction success: {result_class}", file=sys.stderr)
+        
         result = {
-            'class': CLASS_NAMES[class_index],
+            'class': result_class,
             'confidence': f"{confidence:.2%}"
         }
         return jsonify(result)
         
     except Exception as e:
+        # This will show up in the Logs tab!
+        print(f"PREDICTION CRASHED: {str(e)}", file=sys.stderr)
         return jsonify({'error': str(e)}), 500
 
 if __name__ == '__main__':