cosmetic changes about interfaces

deepface/basemodels/ArcFace.py

@@ -1,5 +1,6 @@
 import os
 import gdown
+import numpy as np
 from deepface.commons import functions
 from deepface.commons.logger import Logger
 from deepface.models.FacialRecognition import FacialRecognition
@@ -43,7 +44,7 @@ else:
     )
 
 # pylint: disable=too-few-public-methods
-class ArcFace(FacialRecognition):
+class ArcFaceClient(FacialRecognition):
     """
     ArcFace model class
     """
@@ -52,6 +53,18 @@ class ArcFace(FacialRecognition):
         self.model = load_model()
         self.model_name = "ArcFace"
 
+    def find_embeddings(self, img: np.ndarray) -> list:
+        """
+        find embeddings with ArcFace model
+        Args:
+            img (np.ndarray): pre-loaded image in BGR
+        Returns
+            embeddings (list): multi-dimensional vector
+        """
+        # model.predict causes memory issue when it is called in a for loop
+        # embedding = model.predict(img, verbose=0)[0].tolist()
+        return self.model(img, training=False).numpy()[0].tolist()
+
 
 def load_model(
     url="https://github.com/serengil/deepface_models/releases/download/v1.0/arcface_weights.h5",

deepface/basemodels/DeepID.py

@@ -1,5 +1,6 @@
 import os
 import gdown
+import numpy as np
 from deepface.commons import functions
 from deepface.commons.logger import Logger
 from deepface.models.FacialRecognition import FacialRecognition
@@ -39,7 +40,7 @@ else:
 # -------------------------------------
 
 # pylint: disable=too-few-public-methods
-class DeepId(FacialRecognition):
+class DeepIdClient(FacialRecognition):
     """
     DeepId model class
     """
@@ -48,6 +49,18 @@ class DeepId(FacialRecognition):
         self.model = load_model()
         self.model_name = "DeepId"
 
+    def find_embeddings(self, img: np.ndarray) -> list:
+        """
+        find embeddings with DeepId model
+        Args:
+            img (np.ndarray): pre-loaded image in BGR
+        Returns
+            embeddings (list): multi-dimensional vector
+        """
+        # model.predict causes memory issue when it is called in a for loop
+        # embedding = model.predict(img, verbose=0)[0].tolist()
+        return self.model(img, training=False).numpy()[0].tolist()
+
 
 def load_model(
     url="https://github.com/serengil/deepface_models/releases/download/v1.0/deepid_keras_weights.h5",

deepface/basemodels/Dlib.py

@@ -11,7 +11,7 @@ logger = Logger(module="basemodels.DlibResNet")
 # pylint: disable=too-few-public-methods
 
 
-class Dlib(FacialRecognition):
+class DlibClient(FacialRecognition):
     """
     Dlib model class
     """
@@ -22,13 +22,31 @@ class Dlib(FacialRecognition):
 
     def find_embeddings(self, img: np.ndarray) -> list:
         """
-        Custom find embeddings function of Dlib different than FacialRecognition's one
+        find embeddings with Dlib model - different than regular models
         Args:
-            img (np.ndarray)
+            img (np.ndarray): pre-loaded image in BGR
-        Retunrs:
+        Returns
-            embeddings (list)
+            embeddings (list): multi-dimensional vector
         """
-        return self.model.predict(img)[0].tolist()
+        # return self.model.predict(img)[0].tolist()
+
+        # extract_faces returns 4 dimensional images
+        if len(img.shape) == 4:
+            img = img[0]
+
+        # bgr to rgb
+        img = img[:, :, ::-1]  # bgr to rgb
+
+        # img is in scale of [0, 1] but expected [0, 255]
+        if img.max() <= 1:
+            img = img * 255
+
+        img = img.astype(np.uint8)
+
+        img_representation = self.model.model.compute_face_descriptor(img)
+        img_representation = np.array(img_representation)
+        img_representation = np.expand_dims(img_representation, axis=0)
+        return img_representation[0].tolist()
 
 
 class DlibResNet:
@@ -69,38 +87,12 @@ class DlibResNet:
 
         # ---------------------
 
-        model = dlib.face_recognition_model_v1(weight_file)
+        self.model = dlib.face_recognition_model_v1(weight_file)
-        self.__model = model
 
         # ---------------------
 
         # return None  # classes must return None
 
-    def predict(self, img_aligned: np.ndarray) -> np.ndarray:
-
-        # functions.detectFace returns 4 dimensional images
-        if len(img_aligned.shape) == 4:
-            img_aligned = img_aligned[0]
-
-        # functions.detectFace returns bgr images
-        img_aligned = img_aligned[:, :, ::-1]  # bgr to rgb
-
-        # deepface.detectFace returns an array in scale of [0, 1]
-        # but dlib expects in scale of [0, 255]
-        if img_aligned.max() <= 1:
-            img_aligned = img_aligned * 255
-
-        img_aligned = img_aligned.astype(np.uint8)
-
-        model = self.__model
-
-        img_representation = model.compute_face_descriptor(img_aligned)
-
-        img_representation = np.array(img_representation)
-        img_representation = np.expand_dims(img_representation, axis=0)
-
-        return img_representation
-
 
 class DlibMetaData:
     def __init__(self):

deepface/basemodels/Facenet.py

@@ -1,5 +1,6 @@
 import os
 import gdown
+import numpy as np
 from deepface.commons import functions
 from deepface.commons.logger import Logger
 from deepface.models.FacialRecognition import FacialRecognition
@@ -43,7 +44,7 @@ else:
 # --------------------------------
 
 # pylint: disable=too-few-public-methods
-class FaceNet128d(FacialRecognition):
+class FaceNet128dClient(FacialRecognition):
     """
     FaceNet-128d model class
     """
@@ -52,8 +53,20 @@ class FaceNet128d(FacialRecognition):
         self.model = load_facenet128d_model()
         self.model_name = "FaceNet-128d"
 
+    def find_embeddings(self, img: np.ndarray) -> list:
+        """
+        find embeddings with FaceNet-128d model
+        Args:
+            img (np.ndarray): pre-loaded image in BGR
+        Returns
+            embeddings (list): multi-dimensional vector
+        """
+        # model.predict causes memory issue when it is called in a for loop
+        # embedding = model.predict(img, verbose=0)[0].tolist()
+        return self.model(img, training=False).numpy()[0].tolist()
 
-class FaceNet512d(FacialRecognition):
+
+class FaceNet512dClient(FacialRecognition):
     """
     FaceNet-1512d model class
     """
@@ -62,6 +75,18 @@ class FaceNet512d(FacialRecognition):
         self.model = load_facenet512d_model()
         self.model_name = "FaceNet-512d"
 
+    def find_embeddings(self, img: np.ndarray) -> list:
+        """
+        find embeddings with FaceNet-512d model
+        Args:
+            img (np.ndarray): pre-loaded image in BGR
+        Returns
+            embeddings (list): multi-dimensional vector
+        """
+        # model.predict causes memory issue when it is called in a for loop
+        # embedding = model.predict(img, verbose=0)[0].tolist()
+        return self.model(img, training=False).numpy()[0].tolist()
+
 
 def scaling(x, scale):
     return x * scale

deepface/basemodels/FbDeepFace.py

@@ -1,6 +1,7 @@
 import os
 import zipfile
 import gdown
+import numpy as np
 from deepface.commons import functions
 from deepface.commons.logger import Logger
 from deepface.models.FacialRecognition import FacialRecognition
@@ -36,7 +37,7 @@ else:
 
 # -------------------------------------
 # pylint: disable=line-too-long, too-few-public-methods
-class DeepFace(FacialRecognition):
+class DeepFaceClient(FacialRecognition):
     """
     Fb's DeepFace model class
     """
@@ -45,6 +46,18 @@ class DeepFace(FacialRecognition):
         self.model = load_model()
         self.model_name = "DeepFace"
 
+    def find_embeddings(self, img: np.ndarray) -> list:
+        """
+        find embeddings with OpenFace model
+        Args:
+            img (np.ndarray): pre-loaded image in BGR
+        Returns
+            embeddings (list): multi-dimensional vector
+        """
+        # model.predict causes memory issue when it is called in a for loop
+        # embedding = model.predict(img, verbose=0)[0].tolist()
+        return self.model(img, training=False).numpy()[0].tolist()
+
 
 def load_model(
     url="https://github.com/swghosh/DeepFace/releases/download/weights-vggface2-2d-aligned/VGGFace2_DeepFace_weights_val-0.9034.h5.zip",

deepface/basemodels/OpenFace.py

@@ -1,6 +1,7 @@
 import os
 import gdown
 import tensorflow as tf
+import numpy as np
 from deepface.commons import functions
 from deepface.commons.logger import Logger
 from deepface.models.FacialRecognition import FacialRecognition
@@ -26,7 +27,7 @@ else:
 # ---------------------------------------
 
 # pylint: disable=too-few-public-methods
-class OpenFace(FacialRecognition):
+class OpenFaceClient(FacialRecognition):
     """
     OpenFace model class
     """
@@ -35,6 +36,18 @@ class OpenFace(FacialRecognition):
         self.model = load_model()
         self.model_name = "OpenFace"
 
+    def find_embeddings(self, img: np.ndarray) -> list:
+        """
+        find embeddings with OpenFace model
+        Args:
+            img (np.ndarray): pre-loaded image in BGR
+        Returns
+            embeddings (list): multi-dimensional vector
+        """
+        # model.predict causes memory issue when it is called in a for loop
+        # embedding = model.predict(img, verbose=0)[0].tolist()
+        return self.model(img, training=False).numpy()[0].tolist()
+
 
 def load_model(
     url="https://github.com/serengil/deepface_models/releases/download/v1.0/openface_weights.h5",

deepface/basemodels/SFace.py

@@ -14,7 +14,7 @@ logger = Logger(module="basemodels.SFace")
 # pylint: disable=line-too-long, too-few-public-methods
 
 
-class SFace(FacialRecognition):
+class SFaceClient(FacialRecognition):
     """
     SFace model class
     """
@@ -25,13 +25,20 @@ class SFace(FacialRecognition):
 
     def find_embeddings(self, img: np.ndarray) -> list:
         """
-        Custom find embeddings function of SFace different than FacialRecognition's one
+        find embeddings with SFace model - different than regular models
         Args:
-            img (np.ndarray)
+            img (np.ndarray): pre-loaded image in BGR
-        Retunrs:
+        Returns
-            embeddings (list)
+            embeddings (list): multi-dimensional vector
         """
-        return self.model.predict(img)[0].tolist()
+        # return self.model.predict(img)[0].tolist()
+
+        # revert the image to original format and preprocess using the model
+        input_blob = (img[0] * 255).astype(np.uint8)
+
+        embeddings = self.model.model.feature(input_blob)
+
+        return embeddings[0].tolist()
 
 
 def load_model(
@@ -74,17 +81,6 @@ class SFaceWrapper:
 
         self.layers = [_Layer()]
 
-    def predict(self, image: np.ndarray) -> np.ndarray:
-        # Preprocess
-        input_blob = (image[0] * 255).astype(
-            np.uint8
-        )  # revert the image to original format and preprocess using the model
-
-        # Forward
-        embeddings = self.model.feature(input_blob)
-
-        return embeddings
-
 
 class _Layer:
     input_shape = (None, 112, 112, 3)

deepface/basemodels/VGGFace.py

@@ -1,5 +1,6 @@
 import os
 import gdown
+import numpy as np
 from deepface.commons import functions
 from deepface.commons.logger import Logger
 from deepface.models.FacialRecognition import FacialRecognition
@@ -37,7 +38,7 @@ else:
 # ---------------------------------------
 
 # pylint: disable=too-few-public-methods
-class VggFace(FacialRecognition):
+class VggFaceClient(FacialRecognition):
     """
     VGG-Face model class
     """
@@ -46,6 +47,18 @@ class VggFace(FacialRecognition):
         self.model = load_model()
         self.model_name = "VGG-Face"
 
+    def find_embeddings(self, img: np.ndarray) -> list:
+        """
+        find embeddings with VGG-Face model
+        Args:
+            img (np.ndarray): pre-loaded image in BGR
+        Returns
+            embeddings (list): multi-dimensional vector
+        """
+        # model.predict causes memory issue when it is called in a for loop
+        # embedding = model.predict(img, verbose=0)[0].tolist()
+        return self.model(img, training=False).numpy()[0].tolist()
+
 
 def base_model() -> Sequential:
     """

deepface/detectors/DetectorWrapper.py

@@ -2,15 +2,15 @@ from typing import Any
 import numpy as np
 from deepface.models.Detector import Detector
 from deepface.detectors import (
-    OpenCvWrapper,
+    FastMtCnn,
-    SsdWrapper,
+    MediaPipe,
-    DlibWrapper,
+    MtCnn,
-    MtcnnWrapper,
+    OpenCv,
-    RetinaFaceWrapper,
+    Dlib,
-    MediapipeWrapper,
+    RetinaFace,
-    YoloWrapper,
+    Ssd,
-    YunetWrapper,
+    Yolo,
-    FastMtcnnWrapper,
+    YuNet,
 )
 
 
@@ -25,15 +25,15 @@ def build_model(detector_backend: str) -> Any:
     global face_detector_obj  # singleton design pattern
 
     backends = {
-        "opencv": OpenCvWrapper.OpenCv,
+        "opencv": OpenCv.OpenCvClient,
-        "mtcnn": MtcnnWrapper.MtCnn,
+        "mtcnn": MtCnn.MtCnnClient,
-        "ssd": SsdWrapper.Ssd,
+        "ssd": Ssd.SsdClient,
-        "dlib": DlibWrapper.Dlib,
+        "dlib": Dlib.DlibClient,
-        "retinaface": RetinaFaceWrapper.RetinaFace,
+        "retinaface": RetinaFace.RetinaFaceClient,
-        "mediapipe": MediapipeWrapper.MediaPipe,
+        "mediapipe": MediaPipe.MediaPipeClient,
-        "yolov8": YoloWrapper.Yolo,
+        "yolov8": Yolo.YoloClient,
-        "yunet": YunetWrapper.YuNet,
+        "yunet": YuNet.YuNetClient,
-        "fastmtcnn": FastMtcnnWrapper.FastMtCnn,
+        "fastmtcnn": FastMtCnn.FastMtCnnClient,
     }
 
     if not "face_detector_obj" in globals():

deepface/detectors/Dlib.py

@@ -9,7 +9,7 @@ from deepface.commons.logger import Logger
 logger = Logger(module="detectors.DlibWrapper")
 
 
-class Dlib(Detector):
+class DlibClient(Detector):
     def __init__(self):
         self.model = self.build_model()
 

deepface/detectors/FastMtCnn.py

@@ -7,7 +7,7 @@ from deepface.models.Detector import Detector
 # Examples https://www.kaggle.com/timesler/guide-to-mtcnn-in-facenet-pytorch
 
 
-class FastMtCnn(Detector):
+class FastMtCnnClient(Detector):
     def __init__(self):
         self.model = self.build_model()
 

deepface/detectors/MediaPipe.py

@@ -5,7 +5,7 @@ from deepface.models.Detector import Detector
 # Link - https://google.github.io/mediapipe/solutions/face_detection
 
 
-class MediaPipe(Detector):
+class MediaPipeClient(Detector):
     def __init__(self):
         self.model = self.build_model()
 

deepface/detectors/MtCnn.py

@@ -4,7 +4,7 @@ from mtcnn import MTCNN
 from deepface.models.Detector import Detector
 
 
-class MtCnn(Detector):
+class MtCnnClient(Detector):
     """
     Class to cover common face detection functionalitiy for MtCnn backend
     """

deepface/detectors/OpenCv.py

@@ -5,7 +5,7 @@ import numpy as np
 from deepface.models.Detector import Detector
 
 
-class OpenCv(Detector):
+class OpenCvClient(Detector):
     """
     Class to cover common face detection functionalitiy for OpenCv backend
     """

deepface/detectors/RetinaFace.py

@@ -4,7 +4,7 @@ from retinaface.commons import postprocess
 from deepface.models.Detector import Detector
 
 
-class RetinaFace(Detector):
+class RetinaFaceClient(Detector):
     def __init__(self):
         self.model = rf.build_model()
 

deepface/detectors/Ssd.py

@@ -3,7 +3,7 @@ import gdown
 import cv2
 import pandas as pd
 import numpy as np
-from deepface.detectors import OpenCvWrapper
+from deepface.detectors import OpenCv
 from deepface.commons import functions
 from deepface.models.Detector import Detector
 from deepface.commons.logger import Logger
@@ -13,7 +13,7 @@ logger = Logger(module="detectors.SsdWrapper")
 # pylint: disable=line-too-long
 
 
-class Ssd(Detector):
+class SsdClient(Detector):
     def __init__(self):
         self.model = self.build_model()
 
@@ -65,7 +65,7 @@ class Ssd(Detector):
 
         detector = {}
         detector["face_detector"] = face_detector
-        detector["opencv_module"] = OpenCvWrapper.OpenCv()
+        detector["opencv_module"] = OpenCv.OpenCvClient()
 
         return detector
 
@@ -134,7 +134,7 @@ class Ssd(Detector):
                 confidence = instance["confidence"]
 
                 if align:
-                    opencv_module: OpenCvWrapper.OpenCv = self.model["opencv_module"]
+                    opencv_module: OpenCv.OpenCv = self.model["opencv_module"]
                     left_eye, right_eye = opencv_module.find_eyes(detected_face)
                     detected_face = self.align_face(
                         img=detected_face, left_eye=left_eye, right_eye=right_eye

deepface/detectors/Yolo.py

@@ -16,7 +16,7 @@ WEIGHT_URL = "https://drive.google.com/uc?id=1qcr9DbgsX3ryrz2uU8w4Xm3cOrRywXqb"
 LANDMARKS_CONFIDENCE_THRESHOLD = 0.5
 
 
-class Yolo(Detector):
+class YoloClient(Detector):
     def __init__(self):
         self.model = self.build_model()
 

deepface/detectors/YuNet.py

@@ -10,7 +10,7 @@ from deepface.models.Detector import Detector
 logger = Logger(module="detectors.YunetWrapper")
 
 
-class YuNet(Detector):
+class YuNetClient(Detector):
     def __init__(self):
         self.model = self.build_model()
 

deepface/extendedmodels/Age.py

@@ -23,7 +23,7 @@ else:
 # ----------------------------------------
 
 # pylint: disable=too-few-public-methods
-class ApparentAge(Demography):
+class ApparentAgeClient(Demography):
     """
     Age model class
     """

deepface/extendedmodels/Emotion.py

@@ -33,7 +33,7 @@ else:
 labels = ["angry", "disgust", "fear", "happy", "sad", "surprise", "neutral"]
 
 # pylint: disable=too-few-public-methods
-class FacialExpression(Demography):
+class EmotionClient(Demography):
     """
     Emotion model class
     """

deepface/extendedmodels/Gender.py

@@ -26,7 +26,7 @@ else:
 labels = ["Woman", "Man"]
 
 # pylint: disable=too-few-public-methods
-class Gender(Demography):
+class GenderClient(Demography):
     """
     Gender model class
     """

deepface/extendedmodels/Race.py

@@ -25,7 +25,7 @@ else:
 labels = ["asian", "indian", "black", "white", "middle eastern", "latino hispanic"]
 
 # pylint: disable=too-few-public-methods
-class Race(Demography):
+class RaceClient(Demography):
     """
     Race model class
     """

deepface/models/Detector.py

@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import Union
+from typing import Union, Optional
 import numpy as np
 from PIL import Image
 
@@ -12,7 +12,10 @@ class Detector(ABC):
         pass
 
     def align_face(
-        self, img: np.ndarray, left_eye: Union[list, tuple], right_eye: Union[list, tuple]
+        self,
+        img: np.ndarray,
+        left_eye: Optional[Union[list, tuple]] = None,
+        right_eye: Optional[Union[list, tuple]] = None,
     ) -> np.ndarray:
         """
         Align a given image horizantally with respect to their left and right eye locations

deepface/models/FacialRecognition.py

@@ -1,4 +1,4 @@
-from abc import ABC
+from abc import ABC, abstractmethod
 from typing import Any, Union
 import numpy as np
 from deepface.commons import functions
@@ -16,13 +16,6 @@ class FacialRecognition(ABC):
     model: Union[Model, Any]
     model_name: str
 
+    @abstractmethod
     def find_embeddings(self, img: np.ndarray) -> list:
-        if not isinstance(self.model, Model):
+        pass
-            raise ValueError(
-                "If a facial recognition model is not type of (tf.)keras.models.Model,"
-                "Then its find_embeddings method must be implemented its own module."
-                f"However {self.model_name}'s model type is {type(self.model)}"
-            )
-        # model.predict causes memory issue when it is called in a for loop
-        # embedding = model.predict(img, verbose=0)[0].tolist()
-        return self.model(img, training=False).numpy()[0].tolist()

deepface/modules/modeling.py

@@ -5,12 +5,12 @@ from typing import Any
 from deepface.basemodels import (
     VGGFace,
     OpenFace,
-    Facenet,
     FbDeepFace,
     DeepID,
-    DlibResNet,
     ArcFace,
     SFace,
+    Dlib,
+    FaceNet,
 )
 from deepface.extendedmodels import Age, Gender, Race, Emotion
 
@@ -31,19 +31,19 @@ def build_model(model_name: str) -> Any:
     global model_obj
 
     models = {
-        "VGG-Face": VGGFace.VggFace,
+        "VGG-Face": VGGFace.VggFaceClient,
-        "OpenFace": OpenFace.OpenFace,
+        "OpenFace": OpenFace.OpenFaceClient,
-        "Facenet": Facenet.FaceNet128d,
+        "Facenet": FaceNet.FaceNet128dClient,
-        "Facenet512": Facenet.FaceNet512d,
+        "Facenet512": FaceNet.FaceNet512dClient,
-        "DeepFace": FbDeepFace.DeepFace,
+        "DeepFace": FbDeepFace.DeepFaceClient,
-        "DeepID": DeepID.DeepId,
+        "DeepID": DeepID.DeepIdClient,
-        "Dlib": DlibResNet.Dlib,
+        "Dlib": Dlib.DlibClient,
-        "ArcFace": ArcFace.ArcFace,
+        "ArcFace": ArcFace.ArcFaceClient,
-        "SFace": SFace.SFace,
+        "SFace": SFace.SFaceClient,
-        "Emotion": Emotion.FacialExpression,
+        "Emotion": Emotion.EmotionClient,
-        "Age": Age.ApparentAge,
+        "Age": Age.ApparentAgeClient,
-        "Gender": Gender.Gender,
+        "Gender": Gender.GenderClient,
-        "Race": Race.Race,
+        "Race": Race.RaceClient,
     }
 
     if not "model_obj" in globals():

tests/visual-test.py

@@ -14,11 +14,12 @@ model_names = [
     "Facenet512",
     "OpenFace",
     "DeepFace",
-    "DeepID",
+    # "DeepID",
     "Dlib",
     "ArcFace",
     "SFace",
 ]
+
 detector_backends = ["opencv", "ssd", "dlib", "mtcnn", "retinaface"]
 
 
@@ -44,10 +45,11 @@ dfs = DeepFace.find(
 for df in dfs:
     logger.info(df)
 
+
 # extract faces
 for detector_backend in detector_backends:
     face_objs = DeepFace.extract_faces(
-        img_path="dataset/img1.jpg", detector_backend=detector_backend
+        img_path="dataset/img11.jpg", detector_backend=detector_backend
     )
     for face_obj in face_objs:
         face = face_obj["face"]