face recognition

app/Hackathon_setup/face_recognition.py

@@ -102,147 +102,147 @@ def get_similarity(img1, img2):
 #4) Perform necessary transformations to the input(detected face using the above function).
 #5) Along with the siamese, you need the classifier as well, which is to be finetuned with the faces that you are training
 ##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")
+    BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+
+    # 1 Load the Decision Tree classifier
+    # clf_path = os.path.join(BASE_DIR, "decision_tree_model.sav")
+    clf_path = os.path.join(BASE_DIR, "logistic_regression_5.sav")
+    clf = joblib.load(clf_path)
+
+    scaler_path = os.path.join(BASE_DIR, "standar_scaler.sav")
+    scaler = joblib.load(scaler_path)
+
+    # 2 Load the Siamese feature extractor
+    myModel = Siamese().to(device)
+    ckpt_path = os.path.join(BASE_DIR, "siamese_model.t7")
+    ckpt = torch.load(ckpt_path, map_location=device)
+    myModel.load_state_dict(ckpt['net_dict'])
+    myModel.eval()
+
+    # 3 Face detection (if available)
+    # det_img1 = detected_face(img1)   # returns cropped face or 0 if not detected
+    # if det_img1 == 0:
+        # fallback: use original image
+        # det_img1 = Image.fromarray(cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY))
+
+    # 4 Transform the face
+    img_tensor = trnscm(img1).unsqueeze(0)
+
+    # 5 Extract embeddings
+    with torch.no_grad():
+        embedding = myModel.forward_once(img_tensor)
+        embedding = embedding.view(embedding.size(0), -1).cpu().numpy()  # shape (1, embedding_dim)
+
+    # 6 Predict class using Decision Tree
+    pred_label = clf.predict(scaler.transform(embedding))[0]
+
+
+    # --- Predict ---
+    # scaled_emb = scaler.transform(embedding)
+    # probs = clf.predict_proba(scaled_emb)
+    # pred_label = np.argmax(probs)
+    # confidence = probs[0, pred_label]
+
+
+
+    # 7 Optional: return class name (if available)
+    # If you have the dataset available:
+    # class_names = finalClassifierDset.classes
+    # return class_names[pred_label]
+    # class_names = ['Aayush', 'Aditya', 'Vikram']
+    # return class_names[pred_label] + " " + str(pred_label)
+    class_names = ['Aayush', 'Aditya', 'Vikram']
+    return f"{class_names[pred_label]} {pred_label}"
+
+
 # def get_face_class(img1):
+#     """
+#     img1: BGR image as numpy array (from cv2) OR path string accepted by detected_face.
+#     Returns: "Name label_index" or debug info.
+#     """
+#
 #     device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 #     BASE_DIR = os.path.dirname(os.path.abspath(__file__))
 #
-#     # 1 Load the Decision Tree classifier
-#     # clf_path = os.path.join(BASE_DIR, "decision_tree_model.sav")
+#     # 1) Load classifier + scaler
 #     clf_path = os.path.join(BASE_DIR, "logistic_regression_5.sav")
-#     clf = joblib.load(clf_path)
-#
 #     scaler_path = os.path.join(BASE_DIR, "standar_scaler.sav")
+#     clf = joblib.load(clf_path)
 #     scaler = joblib.load(scaler_path)
 #
-#     # 2 Load the Siamese feature extractor
+#     # 2) Load Siamese feature extractor
 #     myModel = Siamese().to(device)
 #     ckpt_path = os.path.join(BASE_DIR, "siamese_model.t7")
 #     ckpt = torch.load(ckpt_path, map_location=device)
 #     myModel.load_state_dict(ckpt['net_dict'])
 #     myModel.eval()
 #
-#     # 3 Face detection (if available)
-#     det_img1 = detected_face(img1)   # returns cropped face or 0 if not detected
+#     # 3) Face detection & crop
+#     det_img1 = detected_face(img1)   # your function: should return cropped face (preferably PIL.Image or np.uint8)
 #     if det_img1 == 0:
-#         # fallback: use original image
-#         det_img1 = Image.fromarray(cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY))
+#         # fallback: convert original to grayscale PIL
+#         if isinstance(img1, str):
+#             pil_img = Image.open(img1).convert("L")
+#         else:
+#             # img1 assumed BGR numpy (cv2)
+#             gray = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)
+#             pil_img = Image.fromarray(gray)
+#         det_img1 = pil_img
+#
+#     # Ensure det_img1 is a PIL Image in mode 'L' (single channel). Convert if needed.
+#     if isinstance(det_img1, np.ndarray):
+#         # if it's color BGR -> convert to gray
+#         if det_img1.ndim == 3 and det_img1.shape[2] == 3:
+#             det_img1 = cv2.cvtColor(det_img1, cv2.COLOR_BGR2GRAY)
+#         det_img1 = Image.fromarray(det_img1)
+#     det_img1 = det_img1.convert("L")  # enforce single-channel
 #
-#     # 4 Transform the face
-#     img_tensor = trnscm(det_img1).unsqueeze(0)
+#     # 4) Transform the face: trnscm must be the exact same transform used when creating embeddings
+#     img_tensor = trnscm(det_img1).unsqueeze(0)     # shape: (1, C, H, W)
+#     img_tensor = img_tensor.to(device)             # <--- IMPORTANT: move to device!
 #
-#     # 5 Extract embeddings
+#     # 5) Extract embeddings
 #     with torch.no_grad():
-#         embedding = myModel.forward_once(img_tensor)
-#         embedding = embedding.view(embedding.size(0), -1).cpu().numpy()  # shape (1, embedding_dim)
+#         embedding_t = myModel.forward_once(img_tensor)   # tensor on device
+#         embedding_t = embedding_t.view(embedding_t.size(0), -1)
+#         embedding = embedding_t.cpu().numpy()           # shape (1, embedding_dim)
 #
-#     # 6 Predict class using Decision Tree
-#     pred_label = clf.predict(scaler.transform(embedding))[0]
+#     # Debug prints (uncomment if needed)
+#     # print("embedding shape:", embedding.shape)
+#     # print("embedding min/max:", embedding.min(), embedding.max())
+#     # print("embedding mean/std:", embedding.mean(), embedding.std())
 #
+#     # 6) Check for NaNs / inf
+#     if np.isnan(embedding).any() or np.isinf(embedding).any():
+#         return "ERROR: embedding contains NaN or inf"
 #
-#     # --- Predict ---
-#     # scaled_emb = scaler.transform(embedding)
-#     # probs = clf.predict_proba(scaled_emb)
-#     # pred_label = np.argmax(probs)
-#     # confidence = probs[0, pred_label]
+#     # 7) Scale + predict
+#     try:
+#         scaled = scaler.transform(embedding)   # ensure scaler expects shape (1, D)
+#     except Exception as e:
+#         return f"Scaler transform error: {e}"
 #
+#     try:
+#         pred_label = clf.predict(scaled)[0]
+#     except Exception as e:
+#         return f"Classifier predict error: {e}"
 #
+#     # 8) Optional: probabilities (if classifier supports it)
+#     confidence = None
+#     if hasattr(clf, "predict_proba"):
+#         try:
+#             probs = clf.predict_proba(scaled)
+#             confidence = float(probs.max())
+#         except Exception:
+#             confidence = None
 #
-#     # 7 Optional: return class name (if available)
-#     # If you have the dataset available:
-#     # class_names = finalClassifierDset.classes
-#     # return class_names[pred_label]
-#     # class_names = ['Aayush', 'Aditya', 'Vikram']
-#     # return class_names[pred_label] + " " + str(pred_label)
-#     class_names = ['Aayush', 'Aditya', 'Vikram']
-#     return f"{class_names[pred_label]} {pred_label}"
-
-
-def get_face_class(img1):
-    """
-    img1: BGR image as numpy array (from cv2) OR path string accepted by detected_face.
-    Returns: "Name label_index" or debug info.
-    """
-
-    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
-    BASE_DIR = os.path.dirname(os.path.abspath(__file__))
-
-    # 1) Load classifier + scaler
-    clf_path = os.path.join(BASE_DIR, "logistic_regression_5.sav")
-    scaler_path = os.path.join(BASE_DIR, "standar_scaler.sav")
-    clf = joblib.load(clf_path)
-    scaler = joblib.load(scaler_path)
-
-    # 2) Load Siamese feature extractor
-    myModel = Siamese().to(device)
-    ckpt_path = os.path.join(BASE_DIR, "siamese_model.t7")
-    ckpt = torch.load(ckpt_path, map_location=device)
-    myModel.load_state_dict(ckpt['net_dict'])
-    myModel.eval()
-
-    # 3) Face detection & crop
-    det_img1 = detected_face(img1)   # your function: should return cropped face (preferably PIL.Image or np.uint8)
-    if det_img1 == 0:
-        # fallback: convert original to grayscale PIL
-        if isinstance(img1, str):
-            pil_img = Image.open(img1).convert("L")
-        else:
-            # img1 assumed BGR numpy (cv2)
-            gray = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)
-            pil_img = Image.fromarray(gray)
-        det_img1 = pil_img
-
-    # Ensure det_img1 is a PIL Image in mode 'L' (single channel). Convert if needed.
-    if isinstance(det_img1, np.ndarray):
-        # if it's color BGR -> convert to gray
-        if det_img1.ndim == 3 and det_img1.shape[2] == 3:
-            det_img1 = cv2.cvtColor(det_img1, cv2.COLOR_BGR2GRAY)
-        det_img1 = Image.fromarray(det_img1)
-    det_img1 = det_img1.convert("L")  # enforce single-channel
-
-    # 4) Transform the face: trnscm must be the exact same transform used when creating embeddings
-    img_tensor = trnscm(det_img1).unsqueeze(0)     # shape: (1, C, H, W)
-    img_tensor = img_tensor.to(device)             # <--- IMPORTANT: move to device!
-
-    # 5) Extract embeddings
-    with torch.no_grad():
-        embedding_t = myModel.forward_once(img_tensor)   # tensor on device
-        embedding_t = embedding_t.view(embedding_t.size(0), -1)
-        embedding = embedding_t.cpu().numpy()           # shape (1, embedding_dim)
-
-    # Debug prints (uncomment if needed)
-    # print("embedding shape:", embedding.shape)
-    # print("embedding min/max:", embedding.min(), embedding.max())
-    # print("embedding mean/std:", embedding.mean(), embedding.std())
-
-    # 6) Check for NaNs / inf
-    if np.isnan(embedding).any() or np.isinf(embedding).any():
-        return "ERROR: embedding contains NaN or inf"
-
-    # 7) Scale + predict
-    try:
-        scaled = scaler.transform(embedding)   # ensure scaler expects shape (1, D)
-    except Exception as e:
-        return f"Scaler transform error: {e}"
-
-    try:
-        pred_label = clf.predict(scaled)[0]
-    except Exception as e:
-        return f"Classifier predict error: {e}"
-
-    # 8) Optional: probabilities (if classifier supports it)
-    confidence = None
-    if hasattr(clf, "predict_proba"):
-        try:
-            probs = clf.predict_proba(scaled)
-            confidence = float(probs.max())
-        except Exception:
-            confidence = None
-
-    # 9) Map to class names
-    class_names = ['Aayush', 'Aditya', 'Vikram']  # replace with your saved names or load from file
-    name = class_names[pred_label] if pred_label < len(class_names) else str(pred_label)
-
-    if confidence is not None:
-        return f"{name} {pred_label} (conf={confidence:.3f})"
-    else:
-        return f"{name} {pred_label}"
+#     # 9) Map to class names
+#     class_names = ['Aayush', 'Aditya', 'Vikram']  # replace with your saved names or load from file
+#     name = class_names[pred_label] if pred_label < len(class_names) else str(pred_label)
+#
+#     if confidence is not None:
+#         return f"{name} {pred_label} (conf={confidence:.3f})"
+#     else:
+#         return f"{name} {pred_label}"