updated with debug and error log msgs

app/Hackathon_setup/face_recognition.py

@@ -108,59 +108,85 @@ def get_similarity(img1, img2):
 ##Caution: Don't change the definition or function name; for loading the model use the current_path for path example is given in comments to the function
 def get_face_class(img1):
     device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+    print(f"[DEBUG] Using device: {device}")
     
     det_img1 = detected_face(img1)
     if(det_img1 is None):
         det_img1 = Image.fromarray(cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY))
+        print("[DEBUG] No face detected, using full image")
+    else:
+        print("[DEBUG] Face detected successfully")
     
     try:
         # Load the Siamese model for feature extraction
         model = SiameseNetwork().to(device)
         model_path = current_path + '/siamese_model.t7'
+        print(f"[DEBUG] Looking for model at: {model_path}")
+        print(f"[DEBUG] Model file exists: {os.path.exists(model_path)}")
         
         if os.path.exists(model_path):
             ckpt = torch.load(model_path, map_location=device)
             model.load_state_dict(ckpt['net_dict'])
             model.eval()
+            print("[DEBUG] Siamese model loaded successfully")
             
             # Preprocess the image
             face_tensor = trnscm(det_img1).unsqueeze(0).to(device)
+            print(f"[DEBUG] Face tensor shape: {face_tensor.shape}")
             
             # Extract features using Siamese network
             with torch.no_grad():
                 features = model.forward_once(face_tensor)
                 features_np = features.cpu().numpy()
+                print(f"[DEBUG] Extracted features shape: {features_np.shape}")
             
             # Load the classifier and scaler
             classifier_path = current_path + '/face_recognition_classifier.pkl'
             scaler_path = current_path + '/face_recognition_scaler.pkl'
             
+            print(f"[DEBUG] Looking for classifier at: {classifier_path}")
+            print(f"[DEBUG] Classifier file exists: {os.path.exists(classifier_path)}")
+            print(f"[DEBUG] Looking for scaler at: {scaler_path}")
+            print(f"[DEBUG] Scaler file exists: {os.path.exists(scaler_path)}")
+            
             if os.path.exists(classifier_path):
                 classifier = joblib.load(classifier_path)
+                print("[DEBUG] Classifier loaded successfully")
                 
                 # Load the scaler used during training
                 if os.path.exists(scaler_path):
                     scaler = joblib.load(scaler_path)
                     # Scale the features before prediction (crucial for K-NN)
                     features_scaled = scaler.transform(features_np)
-                    print("Using saved StandardScaler for feature scaling")
+                    print("[DEBUG] Using saved StandardScaler for feature scaling")
                 else:
-                    print("Warning: Scaler not found. Creating StandardScaler and fitting on current features.")
-                    print("This is a temporary fix - you should train and save the scaler properly.")
+                    print("[DEBUG] Warning: Scaler not found. Creating StandardScaler and fitting on current features.")
+                    print("[DEBUG] This is a temporary fix - you should train and save the scaler properly.")
                     # Temporary fix: create and fit scaler on current features
                     # Note: This is not ideal but will work for now
                     scaler = StandardScaler()
                     features_scaled = scaler.fit_transform(features_np)
                 
                 predicted_class_idx = classifier.predict(features_scaled)[0]
-                predicted_class = classes[predicted_class_idx]
-                return predicted_class
+                print(f"[DEBUG] Predicted class index: {predicted_class_idx}")
+                print(f"[DEBUG] Available classes: {classes}")
+                print(f"[DEBUG] Number of classes: {len(classes)}")
+                
+                if predicted_class_idx < len(classes):
+                    predicted_class = classes[predicted_class_idx]
+                    print(f"[DEBUG] Predicted class: {predicted_class}")
+                    return predicted_class
+                else:
+                    print(f"[ERROR] Class index {predicted_class_idx} out of bounds! Available classes: {len(classes)}")
+                    return "Unknown"
             else:
-                print(f"Classifier file not found: {classifier_path}")
+                print(f"[ERROR] Classifier file not found: {classifier_path}")
                 return "Unknown"
         else:
-            print(f"Model file not found: {model_path}")
+            print(f"[ERROR] Model file not found: {model_path}")
             return "Unknown"
     except Exception as e:
-        print(f"Error in face classification: {str(e)}")
+        print(f"[ERROR] Exception in face classification: {str(e)}")
+        import traceback
+        traceback.print_exc()
         return "Unknown"