github/deepface
1
1
Fork 0
mirror of https://github.com/serengil/deepface.git synced 2025-06-06 19:45:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #911 from serengil/feat-task-0712-some-improvements

Browse Source 
Feat task 0712 some improvements
This commit is contained in:
Sefik Ilkin Serengil 2023-12-08 22:21:21 +00:00 committed by GitHub
commit 5696d27e84
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
10 changed files with 167 additions and 94 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/tests.yml vendored
View File

@ -1,4 +1,4 @@
name: Tests
name: Tests and Linting
on:
push:

44
deepface/DeepFace.py
View File

@ -30,6 +30,8 @@ from deepface.extendedmodels import Age, Gender, Race, Emotion
from deepface.commons import functions, realtime, distance as dst
from deepface.commons.logger import Logger
# pylint: disable=no-else-raise
logger = Logger(module="DeepFace")
# -----------------------------------
@ -465,8 +467,16 @@ def find(
file_name = f"representations_{model_name}.pkl"
file_name = file_name.replace("-", "_").lower()
if path.exists(db_path + "/" + file_name):
df_cols = [
"identity",
f"{model_name}_representation",
"target_x",
"target_y",
"target_w",
"target_h",
]
if path.exists(db_path + "/" + file_name):
if not silent:
logger.warn(
f"Representations for images in {db_path} folder were previously stored"
@ -477,6 +487,12 @@ def find(
with open(f"{db_path}/{file_name}", "rb") as f:
representations = pickle.load(f)
if len(representations) > 0 and len(representations[0]) != len(df_cols):
raise ValueError(
f"Seems existing {db_path}/{file_name} is out-of-the-date."
"Delete it and re-run."
)
if not silent:
logger.info(f"There are {len(representations)} representations found in {file_name}")
@ -523,7 +539,7 @@ def find(
align=align,
)
for img_content, _, _ in img_objs:
for img_content, img_region, _ in img_objs:
embedding_obj = represent(
img_path=img_content,
model_name=model_name,
@ -538,6 +554,10 @@ def find(
instance = []
instance.append(employee)
instance.append(img_representation)
instance.append(img_region["x"])
instance.append(img_region["y"])
instance.append(img_region["w"])
instance.append(img_region["h"])
representations.append(instance)
# -------------------------------
@ -553,10 +573,13 @@ def find(
# ----------------------------
# now, we got representations for facial database
df = pd.DataFrame(representations, columns=["identity", f"{model_name}_representation"])
df = pd.DataFrame(
representations,
columns=df_cols,
)
# img path might have more than once face
target_objs = functions.extract_faces(
source_objs = functions.extract_faces(
img=img_path,
target_size=target_size,
detector_backend=detector_backend,
@ -567,9 +590,9 @@ def find(
resp_obj = []
for target_img, target_region, _ in target_objs:
for source_img, source_region, _ in source_objs:
target_embedding_obj = represent(
img_path=target_img,
img_path=source_img,
model_name=model_name,
enforce_detection=enforce_detection,
detector_backend="skip",
@ -580,10 +603,10 @@ def find(
target_representation = target_embedding_obj[0]["embedding"]
result_df = df.copy() # df will be filtered in each img
result_df["source_x"] = target_region["x"]
result_df["source_y"] = target_region["y"]
result_df["source_w"] = target_region["w"]
result_df["source_h"] = target_region["h"]
result_df["source_x"] = source_region["x"]
result_df["source_y"] = source_region["y"]
result_df["source_w"] = source_region["w"]
result_df["source_h"] = source_region["h"]
distances = []
for index, instance in df.iterrows():
@ -815,6 +838,7 @@ def extract_faces(
"""
resp_objs = []
img_objs = functions.extract_faces(
img=img_path,
target_size=target_size,

127
deepface/commons/functions.py
View File

@ -16,6 +16,8 @@ from deepface.commons.logger import Logger
logger = Logger(module="commons.functions")
# pylint: disable=no-else-raise
# --------------------------------------------------
# configurations of dependencies
@ -73,49 +75,52 @@ def loadBase64Img(uri):
"""
encoded_data = uri.split(",")[1]
nparr = np.fromstring(base64.b64decode(encoded_data), np.uint8)
img = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
return img
img_bgr = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
# img_rgb = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2RGB)
return img_bgr
def load_image(img):
"""Load image from path, url, base64 or numpy array.
"""
Load image from path, url, base64 or numpy array.
Args:
img: a path, url, base64 or numpy array.
Raises:
ValueError: if the image path does not exist.
Returns:
numpy array: the loaded image.
image (numpy array): the loaded image in BGR format
image name (str): image name itself
"""
# The image is already a numpy array
if type(img).__module__ == np.__name__:
return img
return img, None
# The image is a base64 string
if img.startswith("data:image/"):
return loadBase64Img(img)
return loadBase64Img(img), None
# The image is a url
if img.startswith("http"):
return np.array(Image.open(requests.get(img, stream=True, timeout=60).raw).convert("RGB"))[
:, :, ::-1
]
return (
np.array(Image.open(requests.get(img, stream=True, timeout=60).raw).convert("BGR"))[
:, :, ::-1
],
# return url as image name
img,
)
# The image is a path
if os.path.isfile(img) is not True:
raise ValueError(f"Confirm that {img} exists")
# For reading images with unicode names
with open(img, "rb") as img_f:
chunk = img_f.read()
chunk_arr = np.frombuffer(chunk, dtype=np.uint8)
img = cv2.imdecode(chunk_arr, cv2.IMREAD_COLOR)
return img
# image must be a file on the system then
# This causes troubles when reading files with non english names
# return cv2.imread(img)
# image name must have english characters
if img.isascii() is False:
raise ValueError(f"Input image must not have non-english characters - {img}")
img_obj_bgr = cv2.imread(img)
# img_obj_rgb = cv2.cvtColor(img_obj_bgr, cv2.COLOR_BGR2RGB)
return img_obj_bgr, img
# --------------------------------------------------
@ -152,7 +157,7 @@ def extract_faces(
extracted_faces = []
# img might be path, base64 or numpy array. Convert it to numpy whatever it is.
img = load_image(img)
img, img_name = load_image(img)
img_region = [0, 0, img.shape[1], img.shape[0]]
if detector_backend == "skip":
@ -163,10 +168,17 @@ def extract_faces(
# in case of no face found
if len(face_objs) == 0 and enforce_detection is True:
raise ValueError(
"Face could not be detected. Please confirm that the picture is a face photo "
+ "or consider to set enforce_detection param to False."
)
if img_name is not None:
raise ValueError(
f"Face could not be detected in {img_name}."
"Please confirm that the picture is a face photo "
"or consider to set enforce_detection param to False."
)
else:
raise ValueError(
"Face could not be detected. Please confirm that the picture is a face photo "
"or consider to set enforce_detection param to False."
)
if len(face_objs) == 0 and enforce_detection is False:
face_objs = [(img, img_region, 0)]
@ -177,39 +189,38 @@ def extract_faces(
current_img = cv2.cvtColor(current_img, cv2.COLOR_BGR2GRAY)
# resize and padding
if current_img.shape[0] > 0 and current_img.shape[1] > 0:
factor_0 = target_size[0] / current_img.shape[0]
factor_1 = target_size[1] / current_img.shape[1]
factor = min(factor_0, factor_1)
factor_0 = target_size[0] / current_img.shape[0]
factor_1 = target_size[1] / current_img.shape[1]
factor = min(factor_0, factor_1)
dsize = (
int(current_img.shape[1] * factor),
int(current_img.shape[0] * factor),
dsize = (
int(current_img.shape[1] * factor),
int(current_img.shape[0] * factor),
)
current_img = cv2.resize(current_img, dsize)
diff_0 = target_size[0] - current_img.shape[0]
diff_1 = target_size[1] - current_img.shape[1]
if grayscale is False:
# Put the base image in the middle of the padded image
current_img = np.pad(
current_img,
(
(diff_0 // 2, diff_0 - diff_0 // 2),
(diff_1 // 2, diff_1 - diff_1 // 2),
(0, 0),
),
"constant",
)
else:
current_img = np.pad(
current_img,
(
(diff_0 // 2, diff_0 - diff_0 // 2),
(diff_1 // 2, diff_1 - diff_1 // 2),
),
"constant",
)
current_img = cv2.resize(current_img, dsize)
diff_0 = target_size[0] - current_img.shape[0]
diff_1 = target_size[1] - current_img.shape[1]
if grayscale is False:
# Put the base image in the middle of the padded image
current_img = np.pad(
current_img,
(
(diff_0 // 2, diff_0 - diff_0 // 2),
(diff_1 // 2, diff_1 - diff_1 // 2),
(0, 0),
),
"constant",
)
else:
current_img = np.pad(
current_img,
(
(diff_0 // 2, diff_0 - diff_0 // 2),
(diff_1 // 2, diff_1 - diff_1 // 2),
),
"constant",
)
# double check: if target image is not still the same size with target.
if current_img.shape[0:2] != target_size:

5
deepface/commons/logger.py
View File

@ -1,5 +1,6 @@
import os
import logging
from datetime import datetime
# pylint: disable=broad-except
class Logger:
@ -17,7 +18,7 @@ class Logger:
def info(self, message):
if self.log_level <= logging.INFO:
self.dump_log(message)
self.dump_log(f"{message}")
def debug(self, message):
if self.log_level <= logging.DEBUG:
@ -36,4 +37,4 @@ class Logger:
self.dump_log(f"💥 {message}")
def dump_log(self, message):
print(message)
print(f"{str(datetime.now())[2:-7]} - {message}")

19
deepface/detectors/DlibWrapper.py
View File

@ -6,11 +6,19 @@ from deepface.commons.logger import Logger
logger = Logger(module="detectors.DlibWrapper")
def build_model():
home = functions.get_deepface_home()
import dlib # this requirement is not a must that's why imported here
# this is not a must dependency. do not import it in the global level.
try:
import dlib
except ModuleNotFoundError as e:
raise ImportError(
"Dlib is an optional detector, ensure the library is installed."
"Please install using 'pip install dlib' "
) from e
# check required file exists in the home/.deepface/weights folder
if os.path.isfile(home + "/.deepface/weights/shape_predictor_5_face_landmarks.dat") != True:
@ -40,7 +48,14 @@ def build_model():
def detect_face(detector, img, align=True):
import dlib # this requirement is not a must that's why imported here
# this is not a must dependency. do not import it in the global level.
try:
import dlib
except ModuleNotFoundError as e:
raise ImportError(
"Dlib is an optional detector, ensure the library is installed."
"Please install using 'pip install dlib' "
) from e
resp = []

29
deepface/detectors/FastMtcnnWrapper.py
View File

@ -4,23 +4,27 @@ from deepface.detectors import FaceDetector
# Link -> https://github.com/timesler/facenet-pytorch
# Examples https://www.kaggle.com/timesler/guide-to-mtcnn-in-facenet-pytorch
def build_model():
# Optional dependency
# this is not a must dependency. do not import it in the global level.
try:
from facenet_pytorch import MTCNN as fast_mtcnn
except ModuleNotFoundError as e:
raise ImportError("This is an optional detector, ensure the library is installed. \
Please install using 'pip install facenet-pytorch' ") from e
raise ImportError(
"FastMtcnn is an optional detector, ensure the library is installed."
"Please install using 'pip install facenet-pytorch' "
) from e
face_detector = fast_mtcnn(image_size=160,
thresholds=[0.6, 0.7, 0.7], # MTCNN thresholds
post_process=True,
device='cpu',
select_largest=False, # return result in descending order
)
face_detector = fast_mtcnn(
image_size=160,
thresholds=[0.6, 0.7, 0.7], # MTCNN thresholds
post_process=True,
device="cpu",
select_largest=False, # return result in descending order
)
return face_detector
def xyxy_to_xywh(xyxy):
"""
Convert xyxy format to xywh format.
@ -30,6 +34,7 @@ def xyxy_to_xywh(xyxy):
h = xyxy[3] - y + 1
return [x, y, w, h]
def detect_face(face_detector, img, align=True):
resp = []
@ -38,7 +43,9 @@ def detect_face(face_detector, img, align=True):
img_region = [0, 0, img.shape[1], img.shape[0]]
img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) # mtcnn expects RGB but OpenCV read BGR
detections = face_detector.detect(img_rgb, landmarks=True) # returns boundingbox, prob, landmark
detections = face_detector.detect(
img_rgb, landmarks=True
) # returns boundingbox, prob, landmark
if len(detections[0]) > 0:
for detection in zip(*detections):

9
deepface/detectors/MediapipeWrapper.py
View File

@ -4,7 +4,14 @@ from deepface.detectors import FaceDetector
def build_model():
import mediapipe as mp # this is not a must dependency. do not import it in the global level.
# this is not a must dependency. do not import it in the global level.
try:
import mediapipe as mp
except ModuleNotFoundError as e:
raise ImportError(
"MediaPipe is an optional detector, ensure the library is installed."
"Please install using 'pip install mediapipe' "
) from e
mp_face_detection = mp.solutions.face_detection
face_detection = mp_face_detection.FaceDetection(min_detection_confidence=0.7)

20
deepface/detectors/YoloWrapper.py
View File

@ -20,9 +20,16 @@ def build_model():
import os
# Import the Ultralytics YOLO model
from ultralytics import YOLO
try:
from ultralytics import YOLO
except ModuleNotFoundError as e:
raise ImportError(
"Yolo is an optional detector, ensure the library is installed. \
Please install using 'pip install ultralytics' "
) from e
from deepface.commons.functions import get_deepface_home
weight_path = f"{get_deepface_home()}{PATH}"
# Download the model's weights if they don't exist
@ -38,8 +45,7 @@ def detect_face(face_detector, img, align=False):
resp = []
# Detect faces
results = face_detector.predict(
img, verbose=False, show=False, conf=0.25)[0]
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:
@ -48,7 +54,7 @@ def detect_face(face_detector, img, align=False):
confidence = result.boxes.conf.tolist()[0]
x, y, w, h = int(x - w / 2), int(y - h / 2), int(w), int(h)
detected_face = img[y: y + h, x: x + w].copy()
detected_face = img[y : y + h, x : x + w].copy()
if align:
# Tuple of x,y and confidence for left eye
@ -57,8 +63,10 @@ def detect_face(face_detector, img, align=False):
right_eye = result.keypoints.xy[0][1], result.keypoints.conf[0][1]
# Check the landmarks confidence before alignment
if (left_eye[1] > LANDMARKS_CONFIDENCE_THRESHOLD and
right_eye[1] > LANDMARKS_CONFIDENCE_THRESHOLD):
if (
left_eye[1] > LANDMARKS_CONFIDENCE_THRESHOLD
and right_eye[1] > LANDMARKS_CONFIDENCE_THRESHOLD
):
detected_face = FaceDetector.alignment_procedure(
detected_face, left_eye[0].cpu(), right_eye[0].cpu()
)

2
setup.py
View File

@ -8,7 +8,7 @@ with open("requirements.txt", "r", encoding="utf-8") as f:
setuptools.setup(
name="deepface",
version="0.0.79",
version="0.0.80",
author="Sefik Ilkin Serengil",
author_email="serengil@gmail.com",
description="A Lightweight Face Recognition and Facial Attribute Analysis Framework (Age, Gender, Emotion, Race) for Python",

4
tests/unit_tests.py
View File

@ -9,7 +9,7 @@ from deepface.commons.logger import Logger
logger = Logger()
# pylint: disable=consider-iterating-dictionary
# pylint: disable=consider-iterating-dictionary,broad-except
logger.info("-----------------------------------------")
@ -45,7 +45,7 @@ def evaluate(condition):
# ------------------------------------------------
detectors = ["opencv", "mtcnn"]
models = ["VGG-Face", "Facenet", "ArcFace"]
models = ["VGG-Face", "Facenet", "Facenet512", "ArcFace"]
metrics = ["cosine", "euclidean", "euclidean_l2"]
dataset = [