Merge pull request #1397 from nriviera/yolo

[FEATURE]: adding yolov11 into face detection portfolio
serengil · Dec 11, 2024 · a402f09 · a402f09
2 parents e73bdb8 + 9abcbd3
commit a402f09
Show file tree

Hide file tree

Showing 12 changed files with 198 additions and 131 deletions.
diff --git a/README.md b/README.md
@@ -121,7 +121,7 @@ models = [
   "ArcFace", 
   "Dlib", 
   "SFace",
-  "GhostFaceNet",
+  "GhostFaceNet"
 ]
 
 #face verification
@@ -223,6 +223,9 @@ backends = [
   'retinaface', 
   'mediapipe',
   'yolov8',
+  'yolov11s',
+  'yolov11n',
+  'yolov11m',
   'yunet',
   'centerface',
 ]

diff --git a/deepface/DeepFace.py b/deepface/DeepFace.py
@@ -54,10 +54,10 @@ def build_model(model_name: str, task: str = "facial_recognition") -> Any:
     Args:
         model_name (str): model identifier
             - VGG-Face, Facenet, Facenet512, OpenFace, DeepFace, DeepID, Dlib,
-                ArcFace, SFace, GhostFaceNet for face recognition
+                ArcFace, SFace and GhostFaceNet for face recognition
             - Age, Gender, Emotion, Race for facial attributes
-            - opencv, mtcnn, ssd, dlib, retinaface, mediapipe, yolov8, yunet,
-                fastmtcnn or centerface for face detectors
+            - opencv, mtcnn, ssd, dlib, retinaface, mediapipe, yolov8, yolov11n,
+              yolov11s, yolov11m, yunet, fastmtcnn or centerface for face detectors
             - Fasnet for spoofing
         task (str): facial_recognition, facial_attribute, face_detector, spoofing
             default is facial_recognition
@@ -68,18 +68,18 @@ def build_model(model_name: str, task: str = "facial_recognition") -> Any:
 
 
 def verify(
-    img1_path: Union[str, np.ndarray, List[float]],
-    img2_path: Union[str, np.ndarray, List[float]],
-    model_name: str = "VGG-Face",
-    detector_backend: str = "opencv",
-    distance_metric: str = "cosine",
-    enforce_detection: bool = True,
-    align: bool = True,
-    expand_percentage: int = 0,
-    normalization: str = "base",
-    silent: bool = False,
-    threshold: Optional[float] = None,
-    anti_spoofing: bool = False,
+        img1_path: Union[str, np.ndarray, List[float]],
+        img2_path: Union[str, np.ndarray, List[float]],
+        model_name: str = "VGG-Face",
+        detector_backend: str = "opencv",
+        distance_metric: str = "cosine",
+        enforce_detection: bool = True,
+        align: bool = True,
+        expand_percentage: int = 0,
+        normalization: str = "base",
+        silent: bool = False,
+        threshold: Optional[float] = None,
+        anti_spoofing: bool = False,
 ) -> Dict[str, Any]:
     """
     Verify if an image pair represents the same person or different persons.
@@ -96,8 +96,8 @@ def verify(
             OpenFace, DeepFace, DeepID, Dlib, ArcFace, SFace and GhostFaceNet (default is VGG-Face).
 
         detector_backend (string): face detector backend. Options: 'opencv', 'retinaface',
-            'mtcnn', 'ssd', 'dlib', 'mediapipe', 'yolov8', 'centerface' or 'skip'
-            (default is opencv).
+            'mtcnn', 'ssd', 'dlib', 'mediapipe', 'yolov8', 'yolov11n', 'yolov11s', 'yolov11m',
+            'centerface' or 'skip' (default is opencv).
 
         distance_metric (string): Metric for measuring similarity. Options: 'cosine',
             'euclidean', 'euclidean_l2' (default is cosine).
@@ -164,14 +164,14 @@ def verify(
 
 
 def analyze(
-    img_path: Union[str, np.ndarray],
-    actions: Union[tuple, list] = ("emotion", "age", "gender", "race"),
-    enforce_detection: bool = True,
-    detector_backend: str = "opencv",
-    align: bool = True,
-    expand_percentage: int = 0,
-    silent: bool = False,
-    anti_spoofing: bool = False,
+        img_path: Union[str, np.ndarray],
+        actions: Union[tuple, list] = ("emotion", "age", "gender", "race"),
+        enforce_detection: bool = True,
+        detector_backend: str = "opencv",
+        align: bool = True,
+        expand_percentage: int = 0,
+        silent: bool = False,
+        anti_spoofing: bool = False,
 ) -> List[Dict[str, Any]]:
     """
     Analyze facial attributes such as age, gender, emotion, and race in the provided image.
@@ -187,8 +187,8 @@ def analyze(
             Set to False to avoid the exception for low-resolution images (default is True).
 
         detector_backend (string): face detector backend. Options: 'opencv', 'retinaface',
-            'mtcnn', 'ssd', 'dlib', 'mediapipe', 'yolov8', 'centerface' or 'skip'
-            (default is opencv).
+            'mtcnn', 'ssd', 'dlib', 'mediapipe', 'yolov8', 'yolov11n',  'yolov11s', 'yolov11m',
+            'centerface' or 'skip' (default is opencv).
 
         distance_metric (string): Metric for measuring similarity. Options: 'cosine',
             'euclidean', 'euclidean_l2' (default is cosine).
@@ -263,20 +263,20 @@ def analyze(
 
 
 def find(
-    img_path: Union[str, np.ndarray],
-    db_path: str,
-    model_name: str = "VGG-Face",
-    distance_metric: str = "cosine",
-    enforce_detection: bool = True,
-    detector_backend: str = "opencv",
-    align: bool = True,
-    expand_percentage: int = 0,
-    threshold: Optional[float] = None,
-    normalization: str = "base",
-    silent: bool = False,
-    refresh_database: bool = True,
-    anti_spoofing: bool = False,
-    batched: bool = False,
+        img_path: Union[str, np.ndarray],
+        db_path: str,
+        model_name: str = "VGG-Face",
+        distance_metric: str = "cosine",
+        enforce_detection: bool = True,
+        detector_backend: str = "opencv",
+        align: bool = True,
+        expand_percentage: int = 0,
+        threshold: Optional[float] = None,
+        normalization: str = "base",
+        silent: bool = False,
+        refresh_database: bool = True,
+        anti_spoofing: bool = False,
+        batched: bool = False,
 ) -> Union[List[pd.DataFrame], List[List[Dict[str, Any]]]]:
     """
     Identify individuals in a database
@@ -298,8 +298,8 @@ def find(
             Set to False to avoid the exception for low-resolution images (default is True).
 
         detector_backend (string): face detector backend. Options: 'opencv', 'retinaface',
-            'mtcnn', 'ssd', 'dlib', 'mediapipe', 'yolov8', 'centerface' or 'skip'
-            (default is opencv).
+            'mtcnn', 'ssd', 'dlib', 'mediapipe', 'yolov8', 'yolov11n', 'yolov11s', 'yolov11m',
+            'centerface' or 'skip' (default is opencv).
 
         align (boolean): Perform alignment based on the eye positions (default is True).
 
@@ -369,15 +369,15 @@ def find(
 
 
 def represent(
-    img_path: Union[str, np.ndarray],
-    model_name: str = "VGG-Face",
-    enforce_detection: bool = True,
-    detector_backend: str = "opencv",
-    align: bool = True,
-    expand_percentage: int = 0,
-    normalization: str = "base",
-    anti_spoofing: bool = False,
-    max_faces: Optional[int] = None,
+        img_path: Union[str, np.ndarray],
+        model_name: str = "VGG-Face",
+        enforce_detection: bool = True,
+        detector_backend: str = "opencv",
+        align: bool = True,
+        expand_percentage: int = 0,
+        normalization: str = "base",
+        anti_spoofing: bool = False,
+        max_faces: Optional[int] = None,
 ) -> List[Dict[str, Any]]:
     """
     Represent facial images as multi-dimensional vector embeddings.
@@ -396,8 +396,8 @@ def represent(
             (default is True).
 
         detector_backend (string): face detector backend. Options: 'opencv', 'retinaface',
-            'mtcnn', 'ssd', 'dlib', 'mediapipe', 'yolov8', 'centerface' or 'skip'
-            (default is opencv).
+            'mtcnn', 'ssd', 'dlib', 'mediapipe', 'yolov8', 'yolov11n', 'yolov11s', 'yolov11m',
+            'centerface' or 'skip' (default is opencv).
 
         align (boolean): Perform alignment based on the eye positions (default is True).
 
@@ -441,15 +441,15 @@ def represent(
 
 
 def stream(
-    db_path: str = "",
-    model_name: str = "VGG-Face",
-    detector_backend: str = "opencv",
-    distance_metric: str = "cosine",
-    enable_face_analysis: bool = True,
-    source: Any = 0,
-    time_threshold: int = 5,
-    frame_threshold: int = 5,
-    anti_spoofing: bool = False,
+        db_path: str = "",
+        model_name: str = "VGG-Face",
+        detector_backend: str = "opencv",
+        distance_metric: str = "cosine",
+        enable_face_analysis: bool = True,
+        source: Any = 0,
+        time_threshold: int = 5,
+        frame_threshold: int = 5,
+        anti_spoofing: bool = False,
 ) -> None:
     """
     Run real time face recognition and facial attribute analysis
@@ -462,8 +462,8 @@ def stream(
             OpenFace, DeepFace, DeepID, Dlib, ArcFace, SFace and GhostFaceNet (default is VGG-Face).
 
         detector_backend (string): face detector backend. Options: 'opencv', 'retinaface',
-            'mtcnn', 'ssd', 'dlib', 'mediapipe', 'yolov8', 'centerface' or 'skip'
-            (default is opencv).
+            'mtcnn', 'ssd', 'dlib', 'mediapipe', 'yolov8', 'yolov11n', 'yolov11s', 'yolov11m',
+            'centerface' or 'skip' (default is opencv).
 
         distance_metric (string): Metric for measuring similarity. Options: 'cosine',
             'euclidean', 'euclidean_l2' (default is cosine).
@@ -499,15 +499,15 @@ def stream(
 
 
 def extract_faces(
-    img_path: Union[str, np.ndarray],
-    detector_backend: str = "opencv",
-    enforce_detection: bool = True,
-    align: bool = True,
-    expand_percentage: int = 0,
-    grayscale: bool = False,
-    color_face: str = "rgb",
-    normalize_face: bool = True,
-    anti_spoofing: bool = False,
+        img_path: Union[str, np.ndarray],
+        detector_backend: str = "opencv",
+        enforce_detection: bool = True,
+        align: bool = True,
+        expand_percentage: int = 0,
+        grayscale: bool = False,
+        color_face: str = "rgb",
+        normalize_face: bool = True,
+        anti_spoofing: bool = False,
 ) -> List[Dict[str, Any]]:
     """
     Extract faces from a given image
@@ -517,8 +517,8 @@ def extract_faces(
             as a string, numpy array (BGR), or base64 encoded images.
 
         detector_backend (string): face detector backend. Options: 'opencv', 'retinaface',
-            'mtcnn', 'ssd', 'dlib', 'mediapipe', 'yolov8', 'centerface' or 'skip'
-            (default is opencv).
+            'mtcnn', 'ssd', 'dlib', 'mediapipe', 'yolov8', 'yolov11n', 'yolov11s', 'yolov11m',
+            'centerface' or 'skip' (default is opencv).
 
         enforce_detection (boolean): If no face is detected in an image, raise an exception.
             Set to False to avoid the exception for low-resolution images (default is True).
@@ -584,11 +584,11 @@ def cli() -> None:
 
 
 def detectFace(
-    img_path: Union[str, np.ndarray],
-    target_size: tuple = (224, 224),
-    detector_backend: str = "opencv",
-    enforce_detection: bool = True,
-    align: bool = True,
+        img_path: Union[str, np.ndarray],
+        target_size: tuple = (224, 224),
+        detector_backend: str = "opencv",
+        enforce_detection: bool = True,
+        align: bool = True,
 ) -> Union[np.ndarray, None]:
     """
     Deprecated face detection function. Use extract_faces for same functionality.
@@ -601,8 +601,8 @@ def detectFace(
             added to resize the image (default is (224, 224)).
 
         detector_backend (string): face detector backend. Options: 'opencv', 'retinaface',
-            'mtcnn', 'ssd', 'dlib', 'mediapipe', 'yolov8', 'centerface' or 'skip'
-            (default is opencv).
+            'mtcnn', 'ssd', 'dlib', 'mediapipe', 'yolov8', 'yolov11n', 'yolov11s', 'yolov11m',
+            'centerface' or 'skip' (default is opencv).
 
         enforce_detection (boolean): If no face is detected in an image, raise an exception.
             Set to False to avoid the exception for low-resolution images (default is True).

diff --git a/deepface/commons/weight_utils.py b/deepface/commons/weight_utils.py
@@ -128,8 +128,9 @@ def download_all_models_in_one_shot() -> None:
         WEIGHTS_URL as SSD_WEIGHTS,
     )
     from deepface.models.face_detection.Yolo import (
-        WEIGHT_URL as YOLOV8_WEIGHTS,
-        WEIGHT_NAME as YOLOV8_WEIGHT_NAME,
+        WEIGHT_URLS as YOLO_WEIGHTS,
+        WEIGHT_NAMES as YOLO_WEIGHT_NAMES,
+        YoloModel
     )
     from deepface.models.face_detection.YuNet import WEIGHTS_URL as YUNET_WEIGHTS
     from deepface.models.face_detection.Dlib import WEIGHTS_URL as DLIB_FD_WEIGHTS
@@ -162,8 +163,20 @@ def download_all_models_in_one_shot() -> None:
         SSD_MODEL,
         SSD_WEIGHTS,
         {
-            "filename": YOLOV8_WEIGHT_NAME,
-            "url": YOLOV8_WEIGHTS,
+            "filename": YOLO_WEIGHT_NAMES[YoloModel.V8N.value],
+            "url": YOLO_WEIGHTS[YoloModel.V8N.value],
+        },
+        {
+            "filename": YOLO_WEIGHT_NAMES[YoloModel.V11N.value],
+            "url": YOLO_WEIGHTS[YoloModel.V11N.value],
+        },
+        {
+            "filename": YOLO_WEIGHT_NAMES[YoloModel.V11S.value],
+            "url": YOLO_WEIGHTS[YoloModel.V11S.value],
+        },
+        {
+            "filename": YOLO_WEIGHT_NAMES[YoloModel.V11M.value],
+            "url": YOLO_WEIGHTS[YoloModel.V11M.value],
         },
         YUNET_WEIGHTS,
         DLIB_FD_WEIGHTS,