Feat task 0510 developments

deepface/commons/weight_utils.py

@@ -19,6 +19,40 @@
 
 logger = Logger()
 
+# pylint: disable=line-too-long
+WEIGHTS = {
+    "facial_recognition": {
+        "VGG-Face": "https://github.com/serengil/deepface_models/releases/download/v1.0/vgg_face_weights.h5",
+        "Facenet": "https://github.com/serengil/deepface_models/releases/download/v1.0/facenet_weights.h5",
+        "Facenet512": "https://github.com/serengil/deepface_models/releases/download/v1.0/facenet512_weights.h5",
+        "OpenFace": "https://github.com/serengil/deepface_models/releases/download/v1.0/openface_weights.h5",
+        "FbDeepFace": "https://github.com/swghosh/DeepFace/releases/download/weights-vggface2-2d-aligned/VGGFace2_DeepFace_weights_val-0.9034.h5.zip",
+        "ArcFace": "https://github.com/serengil/deepface_models/releases/download/v1.0/arcface_weights.h5",
+        "DeepID": "https://github.com/serengil/deepface_models/releases/download/v1.0/deepid_keras_weights.h5",
+        "SFace": "https://github.com/opencv/opencv_zoo/raw/main/models/face_recognition_sface/face_recognition_sface_2021dec.onnx",
+        "GhostFaceNet": "https://github.com/HamadYA/GhostFaceNets/releases/download/v1.2/GhostFaceNet_W1.3_S1_ArcFace.h5",
+        "Dlib": "http://dlib.net/files/dlib_face_recognition_resnet_model_v1.dat.bz2",
+    },
+    "demography": {
+        "Age": "https://github.com/serengil/deepface_models/releases/download/v1.0/age_model_weights.h5",
+        "Gender": "https://github.com/serengil/deepface_models/releases/download/v1.0/gender_model_weights.h5",
+        "Emotion": "https://github.com/serengil/deepface_models/releases/download/v1.0/facial_expression_model_weights.h5",
+        "Race": "https://github.com/serengil/deepface_models/releases/download/v1.0/race_model_single_batch.h5",
+    },
+    "detection": {
+        "ssd_model": "https://github.com/opencv/opencv/raw/3.4.0/samples/dnn/face_detector/deploy.prototxt",
+        "ssd_weights": "https://github.com/opencv/opencv_3rdparty/raw/dnn_samples_face_detector_20170830/res10_300x300_ssd_iter_140000.caffemodel",
+        "yolo": "https://drive.google.com/uc?id=1qcr9DbgsX3ryrz2uU8w4Xm3cOrRywXqb",
+        "yunet": "https://github.com/opencv/opencv_zoo/raw/main/models/face_detection_yunet/face_detection_yunet_2023mar.onnx",
+        "dlib": "http://dlib.net/files/shape_predictor_5_face_landmarks.dat.bz2",
+        "centerface": "https://github.com/Star-Clouds/CenterFace/raw/master/models/onnx/centerface.onnx",
+    },
+    "spoofing": {
+        "MiniFASNetV2": "https://github.com/minivision-ai/Silent-Face-Anti-Spoofing/raw/master/resources/anti_spoof_models/2.7_80x80_MiniFASNetV2.pth",
+        "MiniFASNetV1SE": "https://github.com/minivision-ai/Silent-Face-Anti-Spoofing/raw/master/resources/anti_spoof_models/4_0_0_80x80_MiniFASNetV1SE.pth",
+    },
+}
+
 ALLOWED_COMPRESS_TYPES = ["zip", "bz2"]
 
 
@@ -95,3 +129,20 @@ def load_model_weights(model: Sequential, weight_file: str) -> Sequential:
             "and copying it to the target folder."
         ) from err
     return model
+
+
+def retrieve_model_source(model_name: str, task: str) -> str:
+    """
+    Find the source url of a given model name
+    Args:
+        model_name (str): given model name
+    Returns:
+        weight_url (str): source url of the given model
+    """
+    if task not in ["facial_recognition", "detection", "demography", "spoofing"]:
+        raise ValueError(f"unimplemented task - {task}")
+
+    source_url = WEIGHTS.get(task, {}).get(model_name)
+    if source_url is None:
+        raise ValueError(f"Source url cannot be found for given model {task}-{model_name}")
+    return source_url

deepface/models/Detector.py

@@ -6,7 +6,7 @@
 # Notice that all facial detector models must be inherited from this class
 
 
-# pylint: disable=unnecessary-pass, too-few-public-methods
+# pylint: disable=unnecessary-pass, too-few-public-methods, too-many-instance-attributes
 class Detector(ABC):
     @abstractmethod
     def detect_faces(self, img: np.ndarray) -> List["FacialAreaRegion"]:
@@ -45,13 +45,17 @@ class FacialAreaRegion:
         confidence (float, optional): Confidence score associated with the face detection.
             Default is None.
     """
+
     x: int
     y: int
     w: int
     h: int
     left_eye: Optional[Tuple[int, int]] = None
     right_eye: Optional[Tuple[int, int]] = None
     confidence: Optional[float] = None
+    nose: Optional[Tuple[int, int]] = None
+    mouth_right: Optional[Tuple[int, int]] = None
+    mouth_left: Optional[Tuple[int, int]] = None
 
 
 @dataclass
@@ -63,7 +67,8 @@ class DetectedFace:
         img (np.ndarray): detected face image as numpy array
         facial_area (FacialAreaRegion): detected face's metadata (e.g. bounding box)
         confidence (float): confidence score for face detection
-        """
+    """
+
     img: np.ndarray
     facial_area: FacialAreaRegion
     confidence: float

deepface/models/face_detection/RetinaFace.py

@@ -42,10 +42,19 @@ def detect_faces(self, img: np.ndarray) -> List[FacialAreaRegion]:
             # retinaface sets left and right eyes with respect to the person
             left_eye = identity["landmarks"]["left_eye"]
             right_eye = identity["landmarks"]["right_eye"]
+            nose = identity["landmarks"].get("nose")
+            mouth_right = identity["landmarks"].get("mouth_right")
+            mouth_left = identity["landmarks"].get("mouth_left")
 
             # eyes are list of float, need to cast them tuple of int
             left_eye = tuple(int(i) for i in left_eye)
             right_eye = tuple(int(i) for i in right_eye)
+            if nose is not None:
+                nose = tuple(int(i) for i in nose)
+            if mouth_right is not None:
+                mouth_right = tuple(int(i) for i in mouth_right)
+            if mouth_left is not None:
+                mouth_left = tuple(int(i) for i in mouth_left)
 
             confidence = identity["score"]
 
@@ -57,6 +66,9 @@ def detect_faces(self, img: np.ndarray) -> List[FacialAreaRegion]:
                 left_eye=left_eye,
                 right_eye=right_eye,
                 confidence=confidence,
+                nose=nose,
+                mouth_left=mouth_left,
+                mouth_right=mouth_right,
             )
 
             resp.append(facial_area)

deepface/models/facial_recognition/VGGFace.py

@@ -140,9 +140,7 @@ def load_model(
         file_name="vgg_face_weights.h5", source_url=url
     )
 
-    model = weight_utils.load_model_weights(
-        model=model, weight_file=weight_file
-    )
+    model = weight_utils.load_model_weights(model=model, weight_file=weight_file)
 
     # 2622d dimensional model
     # vgg_face_descriptor = Model(inputs=model.layers[0].input, outputs=model.layers[-2].output)
@@ -151,7 +149,6 @@ def load_model(
     # - softmax causes underfitting
     # - added normalization layer to avoid underfitting with euclidean
     # as described here: https://github.com/serengil/deepface/issues/944
-    base_model_output = Sequential()
     base_model_output = Flatten()(model.layers[-5].output)
     # keras backend's l2 normalization layer troubles some gpu users (e.g. issue 957, 966)
     # base_model_output = Lambda(lambda x: K.l2_normalize(x, axis=1), name="norm_layer")(

deepface/modules/detection.py

@@ -148,16 +148,26 @@ def extract_faces(
         w = min(width - x - 1, int(current_region.w))
         h = min(height - y - 1, int(current_region.h))
 
+        facial_area = {
+            "x": x,
+            "y": y,
+            "w": w,
+            "h": h,
+            "left_eye": current_region.left_eye,
+            "right_eye": current_region.right_eye,
+        }
+
+        # optional nose, mouth_left and mouth_right fields are coming just for retinaface
+        if current_region.nose is not None:
+            facial_area["nose"] = current_region.nose
+        if current_region.mouth_left is not None:
+            facial_area["mouth_left"] = current_region.mouth_left
+        if current_region.mouth_right is not None:
+            facial_area["mouth_right"] = current_region.mouth_right
+
         resp_obj = {
             "face": current_img,
-            "facial_area": {
-                "x": x,
-                "y": y,
-                "w": w,
-                "h": h,
-                "left_eye": current_region.left_eye,
-                "right_eye": current_region.right_eye,
-            },
+            "facial_area": facial_area,
             "confidence": round(float(current_region.confidence or 0), 2),
         }
 
@@ -272,6 +282,9 @@ def expand_and_align_face(
     left_eye = facial_area.left_eye
     right_eye = facial_area.right_eye
     confidence = facial_area.confidence
+    nose = facial_area.nose
+    mouth_left = facial_area.mouth_left
+    mouth_right = facial_area.mouth_right
 
     if expand_percentage > 0:
         # Expand the facial region height and width by the provided percentage
@@ -305,11 +318,26 @@ def expand_and_align_face(
             left_eye = (left_eye[0] - width_border, left_eye[1] - height_border)
         if right_eye is not None:
             right_eye = (right_eye[0] - width_border, right_eye[1] - height_border)
+        if nose is not None:
+            nose = (nose[0] - width_border, nose[1] - height_border)
+        if mouth_left is not None:
+            mouth_left = (mouth_left[0] - width_border, mouth_left[1] - height_border)
+        if mouth_right is not None:
+            mouth_right = (mouth_right[0] - width_border, mouth_right[1] - height_border)
 
     return DetectedFace(
         img=detected_face,
         facial_area=FacialAreaRegion(
-            x=x, y=y, h=h, w=w, confidence=confidence, left_eye=left_eye, right_eye=right_eye
+            x=x,
+            y=y,
+            h=h,
+            w=w,
+            confidence=confidence,
+            left_eye=left_eye,
+            right_eye=right_eye,
+            nose=nose,
+            mouth_left=mouth_left,
+            mouth_right=mouth_right,
         ),
         confidence=confidence,
     )