Remove unwanted changes, and add comments.

.vscode/settings.json

@@ -9,7 +9,5 @@
   "python.formatting.provider": "black",
   "python.formatting.blackArgs": ["--line-length=100"],
   "editor.fontWeight": "normal",
-  "python.analysis.extraPaths": ["./deepface"],
+  "python.analysis.extraPaths": ["./deepface"]
-  "stylelint.autoFixOnSave": false,
-  "standard.autoFixOnSave": false
 }

README.md

@@ -194,7 +194,7 @@ Age model got ± 4.65 MAE; gender model got 97.44% accuracy, 96.29% precision an
 
 **Face Detectors** - [`Demo`](https://youtu.be/GZ2p2hj2H5k)
 
-Face detection and alignment are important early stages of a modern face recognition pipeline. Experiments show that just alignment increases the face recognition accuracy almost 1%. [`OpenCV`](https://sefiks.com/2020/02/23/face-alignment-for-face-recognition-in-python-within-opencv/), [`SSD`](https://sefiks.com/2020/08/25/deep-face-detection-with-opencv-in-python/), [`Dlib`](https://sefiks.com/2020/07/11/face-recognition-with-dlib-in-python/),  [`MTCNN`](https://sefiks.com/2020/09/09/deep-face-detection-with-mtcnn-in-python/), [`RetinaFace`](https://sefiks.com/2021/04/27/deep-face-detection-with-retinaface-in-python/) and [`MediaPipe`](https://sefiks.com/2022/01/14/deep-face-detection-with-mediapipe/) detectors are wrapped in deepface.
+Face detection and alignment are important early stages of a modern face recognition pipeline. Experiments show that just alignment increases the face recognition accuracy almost 1%. [`OpenCV`](https://sefiks.com/2020/02/23/face-alignment-for-face-recognition-in-python-within-opencv/), [`SSD`](https://sefiks.com/2020/08/25/deep-face-detection-with-opencv-in-python/), [`Dlib`](https://sefiks.com/2020/07/11/face-recognition-with-dlib-in-python/),  [`MTCNN`](https://sefiks.com/2020/09/09/deep-face-detection-with-mtcnn-in-python/), [`RetinaFace`](https://sefiks.com/2021/04/27/deep-face-detection-with-retinaface-in-python/), [`MediaPipe`](https://sefiks.com/2022/01/14/deep-face-detection-with-mediapipe/) and [`YOLOv8 Face`](https://github.com/derronqi/yolov8-face) detectors are wrapped in deepface.
 
 <p align="center"><img src="https://raw.githubusercontent.com/serengil/deepface/master/icon/detector-portfolio-v3.jpg" width="95%" height="95%"></p>
 
@@ -207,7 +207,8 @@ backends = [
   'dlib', 
   'mtcnn', 
   'retinaface', 
-  'mediapipe'
+  'mediapipe',
+  'yolov8n',
 ]
 
 #face verification

deepface/DeepFace.py

@@ -41,6 +41,7 @@ if tf_version == 2:
 
 
 def build_model(model_name):
+
     """
     This function builds a deepface model
     Parameters:
@@ -95,6 +96,7 @@ def verify(
     align=True,
     normalization="base",
 ):
+
     """
     This function verifies an image pair is same person or different persons. In the background,
     verification function represents facial images as vectors and then calculates the similarity
@@ -116,7 +118,7 @@ def verify(
             This might be convenient for low resolution images.
 
             detector_backend (string): set face detector backend to opencv, retinaface, mtcnn, ssd,
-            dlib or mediapipe
+            dlib, mediapipe or yolov8n.
 
             align (boolean): alignment according to the eye positions.
 
@@ -233,8 +235,9 @@ def analyze(
     align=True,
     silent=False,
 ):
+
     """
-    This function analyze facial attributes including age, gender, emotion and race.
+    This function analyzes facial attributes including age, gender, emotion and race.
     In the background, analysis function builds convolutional neural network models to
     classify age, gender, emotion and race of the input image.
 
@@ -251,7 +254,7 @@ def analyze(
             resolution images.
 
             detector_backend (string): set face detector backend to opencv, retinaface, mtcnn, ssd,
-            dlib or mediapipe.
+            dlib, mediapipe or yolov8n.
 
             align (boolean): alignment according to the eye positions.
 
@@ -297,16 +300,6 @@ def analyze(
         actions = (actions,)
 
     actions = list(actions)
-
-    if not actions:
-        raise ValueError("`actions` must be a list of strings.")
-
-    for action in actions:
-        if action not in ("emotion", "age", "gender", "race"):
-            raise ValueError(
-                f"Invalid action passed ({action})). "
-                "Valid actions are `emotion`, `age`, `gender`, `race`."
-            )
     # ---------------------------------
     # build models
     models = {}
@@ -405,6 +398,7 @@ def find(
     normalization="base",
     silent=False,
 ):
+
     """
     This function applies verification several times and find the identities in a database
 
@@ -427,10 +421,10 @@ def find(
             resolution images.
 
             detector_backend (string): set face detector backend to opencv, retinaface, mtcnn, ssd,
-            dlib or mediapipe
+            dlib, mediapipe or yolov8n.
 
             align (boolean): alignment according to the eye positions.
-
+            
             normalization (string): normalize the input image before feeding to model
 
             silent (boolean): disable some logging and progress bars
@@ -454,6 +448,7 @@ def find(
     file_name = file_name.replace("-", "_").lower()
 
     if path.exists(db_path + "/" + file_name):
+
         if not silent:
             print(
                 f"WARNING: Representations for images in {db_path} folder were previously stored"
@@ -621,6 +616,7 @@ def represent(
     align=True,
     normalization="base",
 ):
+
     """
     This function represents facial images as vectors. The function uses convolutional neural
     networks models to generate vector embeddings.
@@ -638,7 +634,7 @@ def represent(
             This might be convenient for low resolution images.
 
             detector_backend (string): set face detector backend to opencv, retinaface, mtcnn, ssd,
-            dlib or mediapipe
+            dlib, mediapipe or yolov8n.
 
             align (boolean): alignment according to the eye positions.
 
@@ -714,6 +710,7 @@ def stream(
     time_threshold=5,
     frame_threshold=5,
 ):
+
     """
     This function applies real time face recognition and facial attribute analysis
 
@@ -723,7 +720,7 @@ def stream(
             model_name (string): VGG-Face, Facenet, Facenet512, OpenFace, DeepFace, DeepID, Dlib,
             ArcFace, SFace
 
-            detector_backend (string): opencv, retinaface, mtcnn, ssd, dlib or mediapipe
+            detector_backend (string): opencv, retinaface, mtcnn, ssd, dlib, mediapipe or yolov8n.
 
             distance_metric (string): cosine, euclidean, euclidean_l2
 
@@ -768,6 +765,7 @@ def extract_faces(
     align=True,
     grayscale=False,
 ):
+
     """
     This function applies pre-processing stages of a face recognition pipeline
     including detection and alignment
@@ -832,7 +830,7 @@ def detectFace(
 ):
     """
     Deprecated function. Use extract_faces for same functionality.
-
+    
     This function applies pre-processing stages of a face recognition pipeline
     including detection and alignment
 
@@ -857,7 +855,7 @@ def detectFace(
 
     Returns:
             detected and aligned face as numpy array
-
+            
     """
     print("⚠️ Function detectFace is deprecated. Use extract_faces instead.")
     face_objs = extract_faces(

deepface/detectors/FaceDetector.py

@@ -47,6 +47,9 @@ def detect_face(face_detector, detector_backend, img, align=True):
 
     if len(obj) > 0:
         face, region, confidence = obj[0]  # discard multiple faces
+
+    # If no face detected, return, set face to None,
+    # image region to full image, confidence to 0
     else:  # len(obj) == 0
         face = None
         region = [0, 0, img.shape[1], img.shape[0]]

deepface/detectors/OpenCvWrapper.py

@@ -44,6 +44,7 @@ def detect_face(detector, img, align=True):
     detected_face = None
     img_region = [0, 0, img.shape[1], img.shape[0]]
 
+    # Initialize faces and scores to empty lists
     faces = []
     scores = []
     try:
@@ -53,12 +54,16 @@ def detect_face(detector, img, align=True):
         faces, _, scores = detector["face_detector"].detectMultiScale3(
             img, 1.1, 10, outputRejectLevels=True
         )
+
+    # except alone is too broad and will catch keyboard interrupts
+    # Exception should be changed to something more specific in the future
     except Exception:  # pylint: disable=broad-except
-        # except alone is too broad and will catch keyboard interrupts
         import traceback
 
         print(traceback.format_exc())
-
+    
+    # For each face and associated score, append face,
+    # bounding box, and score to resp
     for (x, y, w, h), confidence in zip(faces, scores):
         detected_face = img[int(y) : int(y + h), int(x) : int(x + w)]
 

deepface/detectors/Yolov8faceWrapper.py

@@ -1,13 +1,16 @@
 from deepface.detectors import FaceDetector
 
+# Models names and paths
 PATHS = {
     "yolov8-lite-t": "/.deepface/weights/yolov8-lite-t.pt",
     "yolov8-lite-s": "/.deepface/weights/yolov8-lite-s.pt",
     "yolov8n": "/.deepface/weights/yolov8n-face.pt",
 }
 
+# Google Drive base URL
 BASE_URL = "https://drive.google.com/uc?id="
 
+# Models' Google Drive IDs
 IDS = {
     "yolov8-lite-t": "1vFMGW8xtRVo9bfC9yJVWWGY7vVxbLh94",
     "yolov8-lite-s": "1ckpBT8KfwURTvTm5pa-cMC89A0V5jbaq",
@@ -19,20 +22,24 @@ def build_model(model: str):
     """Function factory for YOLO models"""
     from deepface.commons.functions import get_deepface_home
 
+    # Get model's weights path and Google Drive URL
     func_weights_path = f"{get_deepface_home()}{PATHS[model]}"
     func_url = f"{BASE_URL}{IDS[model]}"
 
+    # Define function to build the model
     def _build_model(weights_path: str = func_weights_path, url: str = func_url):
         import gdown
         import os
 
+        # Import the Ultralytics YOLO model
         from ultralytics import YOLO
 
+        # Download the model's weights if they don't exist
         if not os.path.isfile(weights_path):
             gdown.download(url, weights_path, quiet=False)
             print(f"Downloaded YOLO model {os.path.basename(PATHS[model])}")
 
-        # return face_detector
+        # Return face_detector
         return YOLO(weights_path)
 
     return _build_model
@@ -41,9 +48,12 @@ def build_model(model: str):
 def detect_face(face_detector, img, align=False):
     resp = []
 
+    # Detect faces
     results = face_detector.predict(img, verbose=False, show=False, conf=0.25)[0]
 
+    # For each face, extract the bounding box, the landmarks and confidence
     for result in results:
+        # Extract the bounding box and the confidence
         x, y, w, h = result.boxes.xywh.tolist()[0]
         confidence = result.boxes.conf.tolist()[0]