mirror of
https://github.com/serengil/deepface.git
synced 2025-06-07 20:15:21 +00:00
implement multi-faces detections
This commit is contained in:
Pei-Yun Sun
parent
f36af9ffe7
commit
47733dc7a6
@ -103,8 +103,8 @@ def verify(img1_path, img2_path = '', model_name ='VGG-Face', distance_metric =
|
||||
input_shape = input_shape[1:3]
|
||||
|
||||
|
||||
img1 = functions.preprocess_face(img = img1_path, target_size = input_shape, enforce_detection = enforce_detection, detector_backend = detector_backend)
|
||||
img2 = functions.preprocess_face(img = img2_path, target_size = input_shape, enforce_detection = enforce_detection, detector_backend = detector_backend)
|
||||
img1 = functions.preprocess_face(img = img1_path, target_size = input_shape, enforce_detection = enforce_detection, detector_backend = detector_backend)['processed']
|
||||
img2 = functions.preprocess_face(img = img2_path, target_size = input_shape, enforce_detection = enforce_detection, detector_backend = detector_backend)['processed']
|
||||
|
||||
img1_representation = custom_model.predict(img1)[0,:]
|
||||
img2_representation = custom_model.predict(img2)[0,:]
|
||||
@ -271,8 +271,8 @@ def verify(img1_path, img2_path = '', model_name ='VGG-Face', distance_metric =
|
||||
#----------------------
|
||||
#crop and align faces
|
||||
|
||||
img1 = functions.preprocess_face(img=img1_path, target_size=(input_shape_y, input_shape_x), enforce_detection = enforce_detection, detector_backend = detector_backend)
|
||||
img2 = functions.preprocess_face(img=img2_path, target_size=(input_shape_y, input_shape_x), enforce_detection = enforce_detection, detector_backend = detector_backend)
|
||||
img1 = functions.preprocess_face(img=img1_path, target_size=(input_shape_y, input_shape_x), enforce_detection = enforce_detection, detector_backend = detector_backend)['processed']
|
||||
img2 = functions.preprocess_face(img=img2_path, target_size=(input_shape_y, input_shape_x), enforce_detection = enforce_detection, detector_backend = detector_backend)['processed']
|
||||
|
||||
#----------------------
|
||||
#find embeddings
|
||||
@ -358,7 +358,8 @@ def analyze(img_path, actions = [], models = {}, enforce_detection = True, detec
|
||||
|
||||
#if a specific target is not passed, then find them all
|
||||
if len(actions) == 0:
|
||||
actions= ['emotion', 'age', 'gender', 'race']
|
||||
# actions= ['emotion', 'age', 'gender', 'race']
|
||||
actions = ['emotion', 'age', 'gender']
|
||||
|
||||
#print("Actions to do: ", actions)
|
||||
|
||||
@ -403,120 +404,117 @@ def analyze(img_path, actions = [], models = {}, enforce_detection = True, detec
|
||||
for j in global_pbar:
|
||||
img_path = img_paths[j]
|
||||
|
||||
resp_obj = "{"
|
||||
|
||||
disable_option = False if len(actions) > 1 else True
|
||||
|
||||
pbar = tqdm(range(0,len(actions)), desc='Finding actions', disable = disable_option)
|
||||
|
||||
action_idx = 0
|
||||
img_224 = None # Set to prevent re-detection
|
||||
#for action in actions:
|
||||
for index in pbar:
|
||||
action = actions[index]
|
||||
pbar.set_description("Action: %s" % (action))
|
||||
# preprocess images
|
||||
emotion_imgs = functions.preprocess_face(img=img_path, target_size=(48, 48), grayscale=True, enforce_detection=enforce_detection, detector_backend=detector_backend)['processed']
|
||||
imgs_224 = functions.preprocess_face(img_path, target_size=(224, 224), grayscale=False, enforce_detection=enforce_detection) # just emotion model expects grayscale images
|
||||
orig_faces = imgs_224['original']
|
||||
imgs_224 = imgs_224['processed']
|
||||
|
||||
if action_idx > 0:
|
||||
resp_obj += ", "
|
||||
for i in range(len(imgs_224)):
|
||||
|
||||
if action == 'emotion':
|
||||
emotion_labels = ['angry', 'disgust', 'fear', 'happy', 'sad', 'surprise', 'neutral']
|
||||
img = functions.preprocess_face(img = img_path, target_size = (48, 48), grayscale = True, enforce_detection = enforce_detection, detector_backend = detector_backend)
|
||||
resp_obj = "{"
|
||||
action_idx = 0
|
||||
|
||||
emotion_predictions = emotion_model.predict(img)[0,:]
|
||||
#for action in actions:
|
||||
for index in pbar:
|
||||
action = actions[index]
|
||||
pbar.set_description("Action: %s" % (action))
|
||||
|
||||
sum_of_predictions = emotion_predictions.sum()
|
||||
if action_idx > 0:
|
||||
resp_obj += ", "
|
||||
|
||||
emotion_obj = "\"emotion\": {"
|
||||
for i in range(0, len(emotion_labels)):
|
||||
emotion_label = emotion_labels[i]
|
||||
emotion_prediction = 100 * emotion_predictions[i] / sum_of_predictions
|
||||
if action == 'emotion':
|
||||
emotion_labels = ['angry', 'disgust', 'fear', 'happy', 'sad', 'surprise', 'neutral']
|
||||
|
||||
if i > 0: emotion_obj += ", "
|
||||
emotion_predictions = emotion_model.predict(emotion_imgs[i])[0,:]
|
||||
|
||||
emotion_obj += "\"%s\": %s" % (emotion_label, emotion_prediction)
|
||||
sum_of_predictions = emotion_predictions.sum()
|
||||
|
||||
emotion_obj += "}"
|
||||
emotion_obj = "\"emotion\": {"
|
||||
for i in range(0, len(emotion_labels)):
|
||||
emotion_label = emotion_labels[i]
|
||||
emotion_prediction = 100 * emotion_predictions[i] / sum_of_predictions
|
||||
|
||||
emotion_obj += ", \"dominant_emotion\": \"%s\"" % (emotion_labels[np.argmax(emotion_predictions)])
|
||||
if i > 0: emotion_obj += ", "
|
||||
|
||||
resp_obj += emotion_obj
|
||||
emotion_obj += "\"%s\": %s" % (emotion_label, emotion_prediction)
|
||||
|
||||
elif action == 'age':
|
||||
if img_224 is None:
|
||||
img_224 = functions.preprocess_face(img_path, target_size = (224, 224), grayscale = False, enforce_detection = enforce_detection) #just emotion model expects grayscale images
|
||||
#print("age prediction")
|
||||
age_predictions = age_model.predict(img_224)[0,:]
|
||||
apparent_age = Age.findApparentAge(age_predictions)
|
||||
emotion_obj += "}"
|
||||
|
||||
resp_obj += "\"age\": %s" % (apparent_age)
|
||||
emotion_obj += ", \"dominant_emotion\": \"%s\"" % (emotion_labels[np.argmax(emotion_predictions)])
|
||||
|
||||
elif action == 'gender':
|
||||
if img_224 is None:
|
||||
img_224 = functions.preprocess_face(img = img_path, target_size = (224, 224), grayscale = False, enforce_detection = enforce_detection, detector_backend = detector_backend) #just emotion model expects grayscale images
|
||||
#print("gender prediction")
|
||||
resp_obj += emotion_obj
|
||||
|
||||
gender_prediction = gender_model.predict(img_224)[0,:]
|
||||
elif action == 'age':
|
||||
#print("age prediction")
|
||||
age_predictions = age_model.predict(imgs_224[i])[0,:]
|
||||
apparent_age = Age.findApparentAge(age_predictions)
|
||||
|
||||
if np.argmax(gender_prediction) == 0:
|
||||
gender = "Woman"
|
||||
elif np.argmax(gender_prediction) == 1:
|
||||
gender = "Man"
|
||||
resp_obj += "\"age\": %s" % (apparent_age)
|
||||
|
||||
resp_obj += "\"gender\": \"%s\"" % (gender)
|
||||
elif action == 'gender':
|
||||
#print("gender prediction")
|
||||
|
||||
elif action == 'race':
|
||||
if img_224 is None:
|
||||
img_224 = functions.preprocess_face(img = img_path, target_size = (224, 224), grayscale = False, enforce_detection = enforce_detection, detector_backend = detector_backend) #just emotion model expects grayscale images
|
||||
race_predictions = race_model.predict(img_224)[0,:]
|
||||
race_labels = ['asian', 'indian', 'black', 'white', 'middle eastern', 'latino hispanic']
|
||||
gender_prediction = gender_model.predict(imgs_224[i])[0,:]
|
||||
|
||||
sum_of_predictions = race_predictions.sum()
|
||||
if np.argmax(gender_prediction) == 0:
|
||||
gender = "Woman"
|
||||
elif np.argmax(gender_prediction) == 1:
|
||||
gender = "Man"
|
||||
|
||||
race_obj = "\"race\": {"
|
||||
for i in range(0, len(race_labels)):
|
||||
race_label = race_labels[i]
|
||||
race_prediction = 100 * race_predictions[i] / sum_of_predictions
|
||||
resp_obj += "\"gender\": \"%s\"" % (gender)
|
||||
|
||||
if i > 0: race_obj += ", "
|
||||
elif action == 'race':
|
||||
race_predictions = race_model.predict(imgs_224[i])[0,:]
|
||||
race_labels = ['asian', 'indian', 'black', 'white', 'middle eastern', 'latino hispanic']
|
||||
|
||||
race_obj += "\"%s\": %s" % (race_label, race_prediction)
|
||||
sum_of_predictions = race_predictions.sum()
|
||||
|
||||
race_obj += "}"
|
||||
race_obj += ", \"dominant_race\": \"%s\"" % (race_labels[np.argmax(race_predictions)])
|
||||
race_obj = "\"race\": {"
|
||||
for i in range(0, len(race_labels)):
|
||||
race_label = race_labels[i]
|
||||
race_prediction = 100 * race_predictions[i] / sum_of_predictions
|
||||
|
||||
resp_obj += race_obj
|
||||
if i > 0: race_obj += ", "
|
||||
|
||||
action_idx = action_idx + 1
|
||||
race_obj += "\"%s\": %s" % (race_label, race_prediction)
|
||||
|
||||
resp_obj += "}"
|
||||
race_obj += "}"
|
||||
race_obj += ", \"dominant_race\": \"%s\"" % (race_labels[np.argmax(race_predictions)])
|
||||
|
||||
resp_obj = json.loads(resp_obj)
|
||||
resp_obj += race_obj
|
||||
|
||||
action_idx = action_idx + 1
|
||||
|
||||
resp_obj += "}"
|
||||
|
||||
resp_obj = json.loads(resp_obj)
|
||||
|
||||
if bulkProcess == True:
|
||||
resp_objects.append(resp_obj)
|
||||
else:
|
||||
return resp_obj
|
||||
|
||||
if bulkProcess == True:
|
||||
resp_obj = "{"
|
||||
# resp_obj = "{"
|
||||
#
|
||||
# for i in range(0, len(resp_objects)):
|
||||
# resp_item = json.dumps(resp_objects[i])
|
||||
#
|
||||
# if i > 0:
|
||||
# resp_obj += ", "
|
||||
#
|
||||
# resp_obj += "\"instance_"+str(i+1)+"\": "+resp_item
|
||||
# resp_obj += "}"
|
||||
# resp_obj = json.loads(resp_obj)
|
||||
# return resp_obj
|
||||
return resp_objects, orig_faces
|
||||
|
||||
for i in range(0, len(resp_objects)):
|
||||
resp_item = json.dumps(resp_objects[i])
|
||||
|
||||
if i > 0:
|
||||
resp_obj += ", "
|
||||
|
||||
resp_obj += "\"instance_"+str(i+1)+"\": "+resp_item
|
||||
resp_obj += "}"
|
||||
resp_obj = json.loads(resp_obj)
|
||||
return resp_obj
|
||||
#return resp_objects
|
||||
|
||||
|
||||
def detectFace(img_path, detector_backend = 'opencv'):
|
||||
img = functions.preprocess_face(img = img_path, detector_backend = detector_backend)[0] #preprocess_face returns (1, 224, 224, 3)
|
||||
return img[:, :, ::-1] #bgr to rgb
|
||||
def detectFace(img_path, detector_backend='opencv'):
|
||||
imgs = functions.preprocess_face(img=img_path, detector_backend=detector_backend)['processed'] #preprocess_face returns (1, 224, 224, 3)
|
||||
for i in range(len(imgs)):
|
||||
imgs[i] = imgs[i][0][:, :, ::-1] #bgr to rgb
|
||||
return imgs
|
||||
|
||||
def find(img_path, db_path, model_name ='VGG-Face', distance_metric = 'cosine', model = None, enforce_detection = True, detector_backend = 'opencv'):
|
||||
|
||||
@ -538,22 +536,22 @@ def find(img_path, db_path, model_name ='VGG-Face', distance_metric = 'cosine',
|
||||
|
||||
if model == None:
|
||||
if model_name == 'VGG-Face':
|
||||
print("Using VGG-Face model backend and", distance_metric,"distance.")
|
||||
print("Using VGG-Face model backend and", distance_metric, "distance.")
|
||||
model = VGGFace.loadModel()
|
||||
elif model_name == 'OpenFace':
|
||||
print("Using OpenFace model backend", distance_metric,"distance.")
|
||||
print("Using OpenFace model backend", distance_metric, "distance.")
|
||||
model = OpenFace.loadModel()
|
||||
elif model_name == 'Facenet':
|
||||
print("Using Facenet model backend", distance_metric,"distance.")
|
||||
print("Using Facenet model backend", distance_metric, "distance.")
|
||||
model = Facenet.loadModel()
|
||||
elif model_name == 'DeepFace':
|
||||
print("Using FB DeepFace model backend", distance_metric,"distance.")
|
||||
print("Using FB DeepFace model backend", distance_metric, "distance.")
|
||||
model = FbDeepFace.loadModel()
|
||||
elif model_name == 'DeepID':
|
||||
print("Using DeepID model backend", distance_metric,"distance.")
|
||||
print("Using DeepID model backend", distance_metric, "distance.")
|
||||
model = DeepID.loadModel()
|
||||
elif model_name == 'Dlib':
|
||||
print("Using Dlib ResNet model backend", distance_metric,"distance.")
|
||||
print("Using Dlib ResNet model backend", distance_metric, "distance.")
|
||||
from deepface.basemodels.DlibResNet import DlibResNet #this is not a must because it is very huge
|
||||
model = DlibResNet()
|
||||
elif model_name == 'Ensemble':
|
||||
@ -659,7 +657,7 @@ def find(img_path, db_path, model_name ='VGG-Face', distance_metric = 'cosine',
|
||||
|
||||
input_shape_x = input_shape[0]; input_shape_y = input_shape[1]
|
||||
|
||||
img = functions.preprocess_face(img = employee, target_size = (input_shape_y, input_shape_x), enforce_detection = enforce_detection, detector_backend = detector_backend)
|
||||
img = functions.preprocess_face(img = employee, target_size = (input_shape_y, input_shape_x), enforce_detection = enforce_detection, detector_backend = detector_backend)['processed']
|
||||
representation = model.predict(img)[0,:]
|
||||
|
||||
instance = []
|
||||
@ -685,7 +683,7 @@ def find(img_path, db_path, model_name ='VGG-Face', distance_metric = 'cosine',
|
||||
|
||||
input_shape_x = input_shape[0]; input_shape_y = input_shape[1]
|
||||
|
||||
img = functions.preprocess_face(img = employee, target_size = (input_shape_y, input_shape_x), enforce_detection = enforce_detection, detector_backend = detector_backend)
|
||||
img = functions.preprocess_face(img = employee, target_size = (input_shape_y, input_shape_x), enforce_detection = enforce_detection, detector_backend = detector_backend)['processed']
|
||||
representation = ensemble_model.predict(img)[0,:]
|
||||
instance.append(representation)
|
||||
|
||||
@ -730,7 +728,7 @@ def find(img_path, db_path, model_name ='VGG-Face', distance_metric = 'cosine',
|
||||
else:
|
||||
input_shape = input_shape[1:3]
|
||||
|
||||
img = functions.preprocess_face(img = img_path, target_size = input_shape, enforce_detection = enforce_detection, detector_backend = detector_backend)
|
||||
img = functions.preprocess_face(img = img_path, target_size = input_shape, enforce_detection = enforce_detection, detector_backend = detector_backend)['processed']
|
||||
target_representation = ensemble_model.predict(img)[0,:]
|
||||
|
||||
for k in metric_names:
|
||||
@ -822,7 +820,7 @@ def find(img_path, db_path, model_name ='VGG-Face', distance_metric = 'cosine',
|
||||
|
||||
input_shape_x = input_shape[0]; input_shape_y = input_shape[1]
|
||||
|
||||
img = functions.preprocess_face(img = img_path, target_size = (input_shape_y, input_shape_x), enforce_detection = enforce_detection, detector_backend = detector_backend)
|
||||
img = functions.preprocess_face(img = img_path, target_size = (input_shape_y, input_shape_x), enforce_detection = enforce_detection, detector_backend = detector_backend)['processed']
|
||||
target_representation = model.predict(img)[0,:]
|
||||
|
||||
distances = []
|
||||
|
||||
@ -18,548 +18,581 @@ import tensorflow as tf
|
||||
import keras
|
||||
import bz2
|
||||
from deepface.commons import distance
|
||||
from mtcnn import MTCNN #0.1.0
|
||||
from mtcnn import MTCNN # 0.1.0
|
||||
|
||||
|
||||
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
|
||||
encoded_data = uri.split(',')[1]
|
||||
nparr = np.fromstring(base64.b64decode(encoded_data), np.uint8)
|
||||
img = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
|
||||
return img
|
||||
|
||||
|
||||
def initializeFolder():
|
||||
home = str(Path.home())
|
||||
|
||||
home = str(Path.home())
|
||||
if not os.path.exists(home + "/.deepface"):
|
||||
os.mkdir(home + "/.deepface")
|
||||
print("Directory ", home, "/.deepface created")
|
||||
|
||||
if not os.path.exists(home+"/.deepface"):
|
||||
os.mkdir(home+"/.deepface")
|
||||
print("Directory ",home,"/.deepface created")
|
||||
if not os.path.exists(home + "/.deepface/weights"):
|
||||
os.mkdir(home + "/.deepface/weights")
|
||||
print("Directory ", home, "/.deepface/weights created")
|
||||
|
||||
if not os.path.exists(home+"/.deepface/weights"):
|
||||
os.mkdir(home+"/.deepface/weights")
|
||||
print("Directory ",home,"/.deepface/weights created")
|
||||
|
||||
def findThreshold(model_name, distance_metric):
|
||||
threshold = 0.40
|
||||
|
||||
threshold = 0.40
|
||||
if model_name == 'VGG-Face':
|
||||
if distance_metric == 'cosine':
|
||||
threshold = 0.40
|
||||
elif distance_metric == 'euclidean':
|
||||
threshold = 0.55
|
||||
elif distance_metric == 'euclidean_l2':
|
||||
threshold = 0.75
|
||||
|
||||
if model_name == 'VGG-Face':
|
||||
if distance_metric == 'cosine':
|
||||
threshold = 0.40
|
||||
elif distance_metric == 'euclidean':
|
||||
threshold = 0.55
|
||||
elif distance_metric == 'euclidean_l2':
|
||||
threshold = 0.75
|
||||
elif model_name == 'OpenFace':
|
||||
if distance_metric == 'cosine':
|
||||
threshold = 0.10
|
||||
elif distance_metric == 'euclidean':
|
||||
threshold = 0.55
|
||||
elif distance_metric == 'euclidean_l2':
|
||||
threshold = 0.55
|
||||
|
||||
elif model_name == 'OpenFace':
|
||||
if distance_metric == 'cosine':
|
||||
threshold = 0.10
|
||||
elif distance_metric == 'euclidean':
|
||||
threshold = 0.55
|
||||
elif distance_metric == 'euclidean_l2':
|
||||
threshold = 0.55
|
||||
elif model_name == 'Facenet':
|
||||
if distance_metric == 'cosine':
|
||||
threshold = 0.40
|
||||
elif distance_metric == 'euclidean':
|
||||
threshold = 10
|
||||
elif distance_metric == 'euclidean_l2':
|
||||
threshold = 0.80
|
||||
|
||||
elif model_name == 'Facenet':
|
||||
if distance_metric == 'cosine':
|
||||
threshold = 0.40
|
||||
elif distance_metric == 'euclidean':
|
||||
threshold = 10
|
||||
elif distance_metric == 'euclidean_l2':
|
||||
threshold = 0.80
|
||||
elif model_name == 'DeepFace':
|
||||
if distance_metric == 'cosine':
|
||||
threshold = 0.23
|
||||
elif distance_metric == 'euclidean':
|
||||
threshold = 64
|
||||
elif distance_metric == 'euclidean_l2':
|
||||
threshold = 0.64
|
||||
|
||||
elif model_name == 'DeepFace':
|
||||
if distance_metric == 'cosine':
|
||||
threshold = 0.23
|
||||
elif distance_metric == 'euclidean':
|
||||
threshold = 64
|
||||
elif distance_metric == 'euclidean_l2':
|
||||
threshold = 0.64
|
||||
elif model_name == 'DeepID':
|
||||
if distance_metric == 'cosine':
|
||||
threshold = 0.015
|
||||
elif distance_metric == 'euclidean':
|
||||
threshold = 45
|
||||
elif distance_metric == 'euclidean_l2':
|
||||
threshold = 0.17
|
||||
|
||||
elif model_name == 'DeepID':
|
||||
if distance_metric == 'cosine':
|
||||
threshold = 0.015
|
||||
elif distance_metric == 'euclidean':
|
||||
threshold = 45
|
||||
elif distance_metric == 'euclidean_l2':
|
||||
threshold = 0.17
|
||||
elif model_name == 'Dlib':
|
||||
if distance_metric == 'cosine':
|
||||
threshold = 0.07
|
||||
elif distance_metric == 'euclidean':
|
||||
threshold = 0.60
|
||||
elif distance_metric == 'euclidean_l2':
|
||||
threshold = 0.60
|
||||
|
||||
elif model_name == 'Dlib':
|
||||
if distance_metric == 'cosine':
|
||||
threshold = 0.07
|
||||
elif distance_metric == 'euclidean':
|
||||
threshold = 0.60
|
||||
elif distance_metric == 'euclidean_l2':
|
||||
threshold = 0.60
|
||||
return threshold
|
||||
|
||||
return threshold
|
||||
|
||||
def get_opencv_path():
|
||||
opencv_home = cv2.__file__
|
||||
folders = opencv_home.split(os.path.sep)[0:-1]
|
||||
opencv_home = cv2.__file__
|
||||
folders = opencv_home.split(os.path.sep)[0:-1]
|
||||
|
||||
path = folders[0]
|
||||
for folder in folders[1:]:
|
||||
path = path + "/" + folder
|
||||
path = folders[0]
|
||||
for folder in folders[1:]:
|
||||
path = path + "/" + folder
|
||||
|
||||
return path + "/data/"
|
||||
|
||||
return path+"/data/"
|
||||
|
||||
def load_image(img):
|
||||
exact_image = False
|
||||
if type(img).__module__ == np.__name__:
|
||||
exact_image = True
|
||||
|
||||
exact_image = False
|
||||
if type(img).__module__ == np.__name__:
|
||||
exact_image = True
|
||||
base64_img = False
|
||||
if len(img) > 11 and img[0:11] == "data:image/":
|
||||
base64_img = True
|
||||
|
||||
base64_img = False
|
||||
if len(img) > 11 and img[0:11] == "data:image/":
|
||||
base64_img = True
|
||||
# ---------------------------
|
||||
|
||||
#---------------------------
|
||||
if base64_img == True:
|
||||
img = loadBase64Img(img)
|
||||
|
||||
if base64_img == True:
|
||||
img = loadBase64Img(img)
|
||||
elif exact_image != True: # image path passed as input
|
||||
if os.path.isfile(img) != True:
|
||||
raise ValueError("Confirm that ", img, " exists")
|
||||
|
||||
elif exact_image != True: #image path passed as input
|
||||
if os.path.isfile(img) != True:
|
||||
raise ValueError("Confirm that ",img," exists")
|
||||
img = cv2.imread(img)
|
||||
|
||||
img = cv2.imread(img)
|
||||
return img
|
||||
|
||||
return img
|
||||
|
||||
def detect_face(img, detector_backend = 'opencv', grayscale = False, enforce_detection = True):
|
||||
def detect_face(img, detector_backend='opencv', grayscale=False, enforce_detection=True):
|
||||
home = str(Path.home())
|
||||
|
||||
home = str(Path.home())
|
||||
if detector_backend == 'opencv':
|
||||
|
||||
if detector_backend == 'opencv':
|
||||
# get opencv configuration up first
|
||||
opencv_path = get_opencv_path()
|
||||
face_detector_path = opencv_path + "haarcascade_frontalface_default.xml"
|
||||
|
||||
#get opencv configuration up first
|
||||
opencv_path = get_opencv_path()
|
||||
face_detector_path = opencv_path+"haarcascade_frontalface_default.xml"
|
||||
if os.path.isfile(face_detector_path) != True:
|
||||
raise ValueError("Confirm that opencv is installed on your environment! Expected path ", face_detector_path,
|
||||
" violated.")
|
||||
|
||||
if os.path.isfile(face_detector_path) != True:
|
||||
raise ValueError("Confirm that opencv is installed on your environment! Expected path ",face_detector_path," violated.")
|
||||
face_detector = cv2.CascadeClassifier(face_detector_path)
|
||||
|
||||
face_detector = cv2.CascadeClassifier(face_detector_path)
|
||||
# --------------------------
|
||||
|
||||
#--------------------------
|
||||
faces = []
|
||||
|
||||
faces = []
|
||||
try:
|
||||
faces = face_detector.detectMultiScale(img, 1.3, 5)
|
||||
except:
|
||||
pass
|
||||
|
||||
try:
|
||||
faces = face_detector.detectMultiScale(img, 1.3, 5)
|
||||
except:
|
||||
pass
|
||||
if len(faces) > 0:
|
||||
detected_faces = []
|
||||
for face in faces:
|
||||
print(face)
|
||||
x, y, w, h = face
|
||||
detected_face = img[int(y):int(y + h), int(x):int(x + w)]
|
||||
detected_faces.append(detected_face)
|
||||
return detected_faces
|
||||
|
||||
if len(faces) > 0:
|
||||
x,y,w,h = faces[0] #focus on the 1st face found in the image
|
||||
detected_face = img[int(y):int(y+h), int(x):int(x+w)]
|
||||
return detected_face
|
||||
else: # if no face detected
|
||||
|
||||
else: #if no face detected
|
||||
if enforce_detection != True:
|
||||
return img
|
||||
|
||||
if enforce_detection != True:
|
||||
return img
|
||||
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.")
|
||||
|
||||
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.")
|
||||
elif detector_backend == 'ssd':
|
||||
|
||||
elif detector_backend == 'ssd':
|
||||
# ---------------------------
|
||||
# check required ssd model exists in the home/.deepface/weights folder
|
||||
|
||||
#---------------------------
|
||||
#check required ssd model exists in the home/.deepface/weights folder
|
||||
# model structure
|
||||
if os.path.isfile(home + '/.deepface/weights/deploy.prototxt') != True:
|
||||
print("deploy.prototxt will be downloaded...")
|
||||
|
||||
#model structure
|
||||
if os.path.isfile(home+'/.deepface/weights/deploy.prototxt') != True:
|
||||
url = "https://github.com/opencv/opencv/raw/3.4.0/samples/dnn/face_detector/deploy.prototxt"
|
||||
|
||||
print("deploy.prototxt will be downloaded...")
|
||||
output = home + '/.deepface/weights/deploy.prototxt'
|
||||
|
||||
url = "https://github.com/opencv/opencv/raw/3.4.0/samples/dnn/face_detector/deploy.prototxt"
|
||||
gdown.download(url, output, quiet=False)
|
||||
|
||||
output = home+'/.deepface/weights/deploy.prototxt'
|
||||
# pre-trained weights
|
||||
if os.path.isfile(home + '/.deepface/weights/res10_300x300_ssd_iter_140000.caffemodel') != True:
|
||||
print("res10_300x300_ssd_iter_140000.caffemodel will be downloaded...")
|
||||
|
||||
gdown.download(url, output, quiet=False)
|
||||
url = "https://github.com/opencv/opencv_3rdparty/raw/dnn_samples_face_detector_20170830/res10_300x300_ssd_iter_140000.caffemodel"
|
||||
|
||||
output = home + '/.deepface/weights/res10_300x300_ssd_iter_140000.caffemodel'
|
||||
|
||||
#pre-trained weights
|
||||
if os.path.isfile(home+'/.deepface/weights/res10_300x300_ssd_iter_140000.caffemodel') != True:
|
||||
gdown.download(url, output, quiet=False)
|
||||
|
||||
print("res10_300x300_ssd_iter_140000.caffemodel will be downloaded...")
|
||||
# ---------------------------
|
||||
|
||||
url = "https://github.com/opencv/opencv_3rdparty/raw/dnn_samples_face_detector_20170830/res10_300x300_ssd_iter_140000.caffemodel"
|
||||
ssd_detector = cv2.dnn.readNetFromCaffe(
|
||||
home + "/.deepface/weights/deploy.prototxt",
|
||||
home + "/.deepface/weights/res10_300x300_ssd_iter_140000.caffemodel"
|
||||
)
|
||||
|
||||
output = home+'/.deepface/weights/res10_300x300_ssd_iter_140000.caffemodel'
|
||||
ssd_labels = ["img_id", "is_face", "confidence", "left", "top", "right", "bottom"]
|
||||
|
||||
gdown.download(url, output, quiet=False)
|
||||
target_size = (300, 300)
|
||||
|
||||
#---------------------------
|
||||
base_img = img.copy() # we will restore base_img to img later
|
||||
|
||||
ssd_detector = cv2.dnn.readNetFromCaffe(
|
||||
home+"/.deepface/weights/deploy.prototxt",
|
||||
home+"/.deepface/weights/res10_300x300_ssd_iter_140000.caffemodel"
|
||||
)
|
||||
original_size = img.shape
|
||||
|
||||
ssd_labels = ["img_id", "is_face", "confidence", "left", "top", "right", "bottom"]
|
||||
img = cv2.resize(img, target_size)
|
||||
|
||||
target_size = (300, 300)
|
||||
aspect_ratio_x = (original_size[1] / target_size[1])
|
||||
aspect_ratio_y = (original_size[0] / target_size[0])
|
||||
|
||||
base_img = img.copy() #we will restore base_img to img later
|
||||
imageBlob = cv2.dnn.blobFromImage(image=img)
|
||||
|
||||
original_size = img.shape
|
||||
ssd_detector.setInput(imageBlob)
|
||||
detections = ssd_detector.forward()
|
||||
|
||||
img = cv2.resize(img, target_size)
|
||||
detections_df = pd.DataFrame(detections[0][0], columns=ssd_labels)
|
||||
|
||||
aspect_ratio_x = (original_size[1] / target_size[1])
|
||||
aspect_ratio_y = (original_size[0] / target_size[0])
|
||||
detections_df = detections_df[detections_df['is_face'] == 1] # 0: background, 1: face
|
||||
detections_df = detections_df[detections_df['confidence'] >= 0.90]
|
||||
|
||||
imageBlob = cv2.dnn.blobFromImage(image = img)
|
||||
detections_df['left'] = (detections_df['left'] * 300).astype(int)
|
||||
detections_df['bottom'] = (detections_df['bottom'] * 300).astype(int)
|
||||
detections_df['right'] = (detections_df['right'] * 300).astype(int)
|
||||
detections_df['top'] = (detections_df['top'] * 300).astype(int)
|
||||
|
||||
ssd_detector.setInput(imageBlob)
|
||||
detections = ssd_detector.forward()
|
||||
if detections_df.shape[0] > 0:
|
||||
|
||||
detections_df = pd.DataFrame(detections[0][0], columns = ssd_labels)
|
||||
# TODO: sort detections_df
|
||||
|
||||
detections_df = detections_df[detections_df['is_face'] == 1] #0: background, 1: face
|
||||
detections_df = detections_df[detections_df['confidence'] >= 0.90]
|
||||
# get the first face in the image
|
||||
instance = detections_df.iloc[0]
|
||||
|
||||
detections_df['left'] = (detections_df['left'] * 300).astype(int)
|
||||
detections_df['bottom'] = (detections_df['bottom'] * 300).astype(int)
|
||||
detections_df['right'] = (detections_df['right'] * 300).astype(int)
|
||||
detections_df['top'] = (detections_df['top'] * 300).astype(int)
|
||||
left = instance["left"]
|
||||
right = instance["right"]
|
||||
bottom = instance["bottom"]
|
||||
top = instance["top"]
|
||||
|
||||
if detections_df.shape[0] > 0:
|
||||
detected_face = base_img[int(top * aspect_ratio_y):int(bottom * aspect_ratio_y),
|
||||
int(left * aspect_ratio_x):int(right * aspect_ratio_x)]
|
||||
|
||||
#TODO: sort detections_df
|
||||
return detected_face
|
||||
|
||||
#get the first face in the image
|
||||
instance = detections_df.iloc[0]
|
||||
else: # if no face detected
|
||||
|
||||
left = instance["left"]
|
||||
right = instance["right"]
|
||||
bottom = instance["bottom"]
|
||||
top = instance["top"]
|
||||
if enforce_detection != True:
|
||||
img = base_img.copy()
|
||||
return img
|
||||
|
||||
detected_face = base_img[int(top*aspect_ratio_y):int(bottom*aspect_ratio_y), int(left*aspect_ratio_x):int(right*aspect_ratio_x)]
|
||||
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.")
|
||||
|
||||
return detected_face
|
||||
elif detector_backend == 'dlib':
|
||||
import \
|
||||
dlib # this is not a must library within deepface. that's why, I didn't put this import to a global level. version: 19.20.0
|
||||
|
||||
else: #if no face detected
|
||||
detector = dlib.get_frontal_face_detector()
|
||||
|
||||
if enforce_detection != True:
|
||||
img = base_img.copy()
|
||||
return img
|
||||
detections = detector(img, 1)
|
||||
|
||||
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(detections) > 0:
|
||||
|
||||
elif detector_backend == 'dlib':
|
||||
import dlib #this is not a must library within deepface. that's why, I didn't put this import to a global level. version: 19.20.0
|
||||
for idx, d in enumerate(detections):
|
||||
left = d.left();
|
||||
right = d.right()
|
||||
top = d.top();
|
||||
bottom = d.bottom()
|
||||
|
||||
detector = dlib.get_frontal_face_detector()
|
||||
detected_face = img[top:bottom, left:right]
|
||||
|
||||
detections = detector(img, 1)
|
||||
return detected_face
|
||||
|
||||
if len(detections) > 0:
|
||||
else: # if no face detected
|
||||
|
||||
for idx, d in enumerate(detections):
|
||||
left = d.left(); right = d.right()
|
||||
top = d.top(); bottom = d.bottom()
|
||||
if enforce_detection != True:
|
||||
return img
|
||||
|
||||
detected_face = img[top:bottom, left:right]
|
||||
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.")
|
||||
|
||||
return detected_face
|
||||
elif detector_backend == 'mtcnn':
|
||||
|
||||
else: #if no face detected
|
||||
mtcnn_detector = MTCNN()
|
||||
|
||||
if enforce_detection != True:
|
||||
return img
|
||||
detections = mtcnn_detector.detect_faces(img)
|
||||
|
||||
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(detections) > 0:
|
||||
detected_faces = []
|
||||
for detection in detections:
|
||||
x, y, w, h = detection["box"]
|
||||
detected_face = img[int(y):int(y + h), int(x):int(x + w)]
|
||||
detected_faces.append(detected_face)
|
||||
return detected_faces
|
||||
|
||||
elif detector_backend == 'mtcnn':
|
||||
else: # if no face detected
|
||||
if enforce_detection != True:
|
||||
return img
|
||||
|
||||
mtcnn_detector = MTCNN()
|
||||
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.")
|
||||
|
||||
detections = mtcnn_detector.detect_faces(img)
|
||||
else:
|
||||
detectors = ['opencv', 'ssd', 'dlib', 'mtcnn']
|
||||
raise ValueError("Valid backends are ", detectors, " but you passed ", detector_backend)
|
||||
|
||||
if len(detections) > 0:
|
||||
detection = detections[0]
|
||||
x, y, w, h = detection["box"]
|
||||
detected_face = img[int(y):int(y+h), int(x):int(x+w)]
|
||||
return detected_face
|
||||
return 0
|
||||
|
||||
else: #if no face detected
|
||||
if enforce_detection != True:
|
||||
return img
|
||||
|
||||
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.")
|
||||
|
||||
else:
|
||||
detectors = ['opencv', 'ssd', 'dlib', 'mtcnn']
|
||||
raise ValueError("Valid backends are ", detectors," but you passed ", detector_backend)
|
||||
|
||||
return 0
|
||||
|
||||
def alignment_procedure(img, left_eye, right_eye):
|
||||
# this function aligns given face in img based on left and right eye coordinates
|
||||
|
||||
#this function aligns given face in img based on left and right eye coordinates
|
||||
left_eye_x, left_eye_y = left_eye
|
||||
right_eye_x, right_eye_y = right_eye
|
||||
|
||||
left_eye_x, left_eye_y = left_eye
|
||||
right_eye_x, right_eye_y = right_eye
|
||||
# -----------------------
|
||||
# find rotation direction
|
||||
|
||||
#-----------------------
|
||||
#find rotation direction
|
||||
if left_eye_y > right_eye_y:
|
||||
point_3rd = (right_eye_x, left_eye_y)
|
||||
direction = -1 # rotate same direction to clock
|
||||
else:
|
||||
point_3rd = (left_eye_x, right_eye_y)
|
||||
direction = 1 # rotate inverse direction of clock
|
||||
|
||||
if left_eye_y > right_eye_y:
|
||||
point_3rd = (right_eye_x, left_eye_y)
|
||||
direction = -1 #rotate same direction to clock
|
||||
else:
|
||||
point_3rd = (left_eye_x, right_eye_y)
|
||||
direction = 1 #rotate inverse direction of clock
|
||||
# -----------------------
|
||||
# find length of triangle edges
|
||||
|
||||
#-----------------------
|
||||
#find length of triangle edges
|
||||
a = distance.findEuclideanDistance(np.array(left_eye), np.array(point_3rd))
|
||||
b = distance.findEuclideanDistance(np.array(right_eye), np.array(point_3rd))
|
||||
c = distance.findEuclideanDistance(np.array(right_eye), np.array(left_eye))
|
||||
|
||||
a = distance.findEuclideanDistance(np.array(left_eye), np.array(point_3rd))
|
||||
b = distance.findEuclideanDistance(np.array(right_eye), np.array(point_3rd))
|
||||
c = distance.findEuclideanDistance(np.array(right_eye), np.array(left_eye))
|
||||
# -----------------------
|
||||
|
||||
#-----------------------
|
||||
# apply cosine rule
|
||||
|
||||
#apply cosine rule
|
||||
if b != 0 and c != 0: # this multiplication causes division by zero in cos_a calculation
|
||||
|
||||
if b != 0 and c != 0: #this multiplication causes division by zero in cos_a calculation
|
||||
cos_a = (b * b + c * c - a * a) / (2 * b * c)
|
||||
angle = np.arccos(cos_a) # angle in radian
|
||||
angle = (angle * 180) / math.pi # radian to degree
|
||||
|
||||
cos_a = (b*b + c*c - a*a)/(2*b*c)
|
||||
angle = np.arccos(cos_a) #angle in radian
|
||||
angle = (angle * 180) / math.pi #radian to degree
|
||||
# -----------------------
|
||||
# rotate base image
|
||||
|
||||
#-----------------------
|
||||
#rotate base image
|
||||
if direction == -1:
|
||||
angle = 90 - angle
|
||||
|
||||
if direction == -1:
|
||||
angle = 90 - angle
|
||||
img = Image.fromarray(img)
|
||||
img = np.array(img.rotate(direction * angle))
|
||||
|
||||
img = Image.fromarray(img)
|
||||
img = np.array(img.rotate(direction * angle))
|
||||
# -----------------------
|
||||
|
||||
#-----------------------
|
||||
return img # return img anyway
|
||||
|
||||
return img #return img anyway
|
||||
|
||||
def align_face(img, detector_backend = 'opencv'):
|
||||
def align_face(img, detector_backend='opencv'):
|
||||
home = str(Path.home())
|
||||
|
||||
home = str(Path.home())
|
||||
if (detector_backend == 'opencv') or (detector_backend == 'ssd'):
|
||||
|
||||
if (detector_backend == 'opencv') or (detector_backend == 'ssd'):
|
||||
opencv_path = get_opencv_path()
|
||||
eye_detector_path = opencv_path + "haarcascade_eye.xml"
|
||||
eye_detector = cv2.CascadeClassifier(eye_detector_path)
|
||||
|
||||
opencv_path = get_opencv_path()
|
||||
eye_detector_path = opencv_path+"haarcascade_eye.xml"
|
||||
eye_detector = cv2.CascadeClassifier(eye_detector_path)
|
||||
detected_face_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # eye detector expects gray scale image
|
||||
|
||||
detected_face_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) #eye detector expects gray scale image
|
||||
eyes = eye_detector.detectMultiScale(detected_face_gray)
|
||||
|
||||
eyes = eye_detector.detectMultiScale(detected_face_gray)
|
||||
if len(eyes) >= 2:
|
||||
|
||||
if len(eyes) >= 2:
|
||||
# find the largest 2 eye
|
||||
|
||||
#find the largest 2 eye
|
||||
base_eyes = eyes[:, 2]
|
||||
|
||||
base_eyes = eyes[:, 2]
|
||||
items = []
|
||||
for i in range(0, len(base_eyes)):
|
||||
item = (base_eyes[i], i)
|
||||
items.append(item)
|
||||
|
||||
items = []
|
||||
for i in range(0, len(base_eyes)):
|
||||
item = (base_eyes[i], i)
|
||||
items.append(item)
|
||||
df = pd.DataFrame(items, columns=["length", "idx"]).sort_values(by=['length'], ascending=False)
|
||||
|
||||
df = pd.DataFrame(items, columns = ["length", "idx"]).sort_values(by=['length'], ascending=False)
|
||||
eyes = eyes[df.idx.values[0:2]] # eyes variable stores the largest 2 eye
|
||||
|
||||
eyes = eyes[df.idx.values[0:2]] #eyes variable stores the largest 2 eye
|
||||
# -----------------------
|
||||
# decide left and right eye
|
||||
|
||||
#-----------------------
|
||||
#decide left and right eye
|
||||
eye_1 = eyes[0];
|
||||
eye_2 = eyes[1]
|
||||
|
||||
eye_1 = eyes[0]; eye_2 = eyes[1]
|
||||
if eye_1[0] < eye_2[0]:
|
||||
left_eye = eye_1;
|
||||
right_eye = eye_2
|
||||
else:
|
||||
left_eye = eye_2;
|
||||
right_eye = eye_1
|
||||
|
||||
if eye_1[0] < eye_2[0]:
|
||||
left_eye = eye_1; right_eye = eye_2
|
||||
else:
|
||||
left_eye = eye_2; right_eye = eye_1
|
||||
# -----------------------
|
||||
# find center of eyes
|
||||
|
||||
#-----------------------
|
||||
#find center of eyes
|
||||
left_eye = (int(left_eye[0] + (left_eye[2] / 2)), int(left_eye[1] + (left_eye[3] / 2)))
|
||||
right_eye = (int(right_eye[0] + (right_eye[2] / 2)), int(right_eye[1] + (right_eye[3] / 2)))
|
||||
|
||||
left_eye = (int(left_eye[0] + (left_eye[2] / 2)), int(left_eye[1] + (left_eye[3] / 2)))
|
||||
right_eye = (int(right_eye[0] + (right_eye[2]/2)), int(right_eye[1] + (right_eye[3]/2)))
|
||||
img = alignment_procedure(img, left_eye, right_eye)
|
||||
|
||||
img = alignment_procedure(img, left_eye, right_eye)
|
||||
return img # return img anyway
|
||||
|
||||
return img #return img anyway
|
||||
elif detector_backend == 'dlib':
|
||||
|
||||
elif detector_backend == 'dlib':
|
||||
# check required file exists in the home/.deepface/weights folder
|
||||
|
||||
#check required file exists in the home/.deepface/weights folder
|
||||
if os.path.isfile(home + '/.deepface/weights/shape_predictor_5_face_landmarks.dat') != True:
|
||||
print("shape_predictor_5_face_landmarks.dat.bz2 is going to be downloaded")
|
||||
|
||||
if os.path.isfile(home+'/.deepface/weights/shape_predictor_5_face_landmarks.dat') != True:
|
||||
url = "http://dlib.net/files/shape_predictor_5_face_landmarks.dat.bz2"
|
||||
output = home + '/.deepface/weights/' + url.split("/")[-1]
|
||||
|
||||
print("shape_predictor_5_face_landmarks.dat.bz2 is going to be downloaded")
|
||||
gdown.download(url, output, quiet=False)
|
||||
|
||||
url = "http://dlib.net/files/shape_predictor_5_face_landmarks.dat.bz2"
|
||||
output = home+'/.deepface/weights/'+url.split("/")[-1]
|
||||
zipfile = bz2.BZ2File(output)
|
||||
data = zipfile.read()
|
||||
newfilepath = output[:-4] # discard .bz2 extension
|
||||
open(newfilepath, 'wb').write(data)
|
||||
|
||||
gdown.download(url, output, quiet=False)
|
||||
# ------------------------------
|
||||
|
||||
zipfile = bz2.BZ2File(output)
|
||||
data = zipfile.read()
|
||||
newfilepath = output[:-4] #discard .bz2 extension
|
||||
open(newfilepath, 'wb').write(data)
|
||||
import dlib # this is not a must dependency in deepface
|
||||
|
||||
#------------------------------
|
||||
detector = dlib.get_frontal_face_detector()
|
||||
sp = dlib.shape_predictor(home + "/.deepface/weights/shape_predictor_5_face_landmarks.dat")
|
||||
|
||||
import dlib #this is not a must dependency in deepface
|
||||
detections = detector(img, 1)
|
||||
|
||||
detector = dlib.get_frontal_face_detector()
|
||||
sp = dlib.shape_predictor(home+"/.deepface/weights/shape_predictor_5_face_landmarks.dat")
|
||||
if len(detections) > 0:
|
||||
detected_face = detections[0]
|
||||
img_shape = sp(img, detected_face)
|
||||
img = dlib.get_face_chip(img, img_shape, size=img.shape[0])
|
||||
|
||||
detections = detector(img, 1)
|
||||
return img # return img anyway
|
||||
|
||||
if len(detections) > 0:
|
||||
detected_face = detections[0]
|
||||
img_shape = sp(img, detected_face)
|
||||
img = dlib.get_face_chip(img, img_shape, size = img.shape[0])
|
||||
elif detector_backend == 'mtcnn':
|
||||
|
||||
return img #return img anyway
|
||||
mtcnn_detector = MTCNN()
|
||||
detections = mtcnn_detector.detect_faces(img)
|
||||
|
||||
elif detector_backend == 'mtcnn':
|
||||
if len(detections) > 0:
|
||||
detection = detections[0]
|
||||
|
||||
mtcnn_detector = MTCNN()
|
||||
detections = mtcnn_detector.detect_faces(img)
|
||||
keypoints = detection["keypoints"]
|
||||
left_eye = keypoints["left_eye"]
|
||||
right_eye = keypoints["right_eye"]
|
||||
|
||||
if len(detections) > 0:
|
||||
detection = detections[0]
|
||||
img = alignment_procedure(img, left_eye, right_eye)
|
||||
|
||||
keypoints = detection["keypoints"]
|
||||
left_eye = keypoints["left_eye"]
|
||||
right_eye = keypoints["right_eye"]
|
||||
return img # return img anyway
|
||||
|
||||
img = alignment_procedure(img, left_eye, right_eye)
|
||||
|
||||
return img #return img anyway
|
||||
def preprocess_face(img, target_size=(224, 224), grayscale=False, enforce_detection=True, detector_backend='opencv'):
|
||||
# img might be path, base64 or numpy array. Convert it to numpy whatever it is.
|
||||
img = load_image(img)
|
||||
base_img = img.copy()
|
||||
|
||||
def preprocess_face(img, target_size=(224, 224), grayscale = False, enforce_detection = True, detector_backend = 'opencv'):
|
||||
imgs = detect_face(img=img, detector_backend=detector_backend, grayscale=grayscale,
|
||||
enforce_detection=enforce_detection)
|
||||
|
||||
#img might be path, base64 or numpy array. Convert it to numpy whatever it is.
|
||||
img = load_image(img)
|
||||
base_img = img.copy()
|
||||
# --------------------------
|
||||
|
||||
img = detect_face(img = img, detector_backend = detector_backend, grayscale = grayscale, enforce_detection = enforce_detection)
|
||||
for i in range(len(imgs)):
|
||||
|
||||
#--------------------------
|
||||
img = imgs[i]
|
||||
|
||||
if img.shape[0] > 0 and img.shape[1] > 0:
|
||||
img = align_face(img = img, detector_backend = detector_backend)
|
||||
else:
|
||||
if img.shape[0] > 0 and img.shape[1] > 0:
|
||||
imgs[i] = align_face(img=img, detector_backend=detector_backend)
|
||||
else:
|
||||
|
||||
if enforce_detection == True:
|
||||
raise ValueError("Detected face shape is ", img.shape,". Consider to set enforce_detection argument to False.")
|
||||
else: #restore base image
|
||||
img = base_img.copy()
|
||||
if enforce_detection == True:
|
||||
raise ValueError("Detected face shape is ", img.shape,
|
||||
". Consider to set enforce_detection argument to False.")
|
||||
else: # restore base image
|
||||
imgs[i] = base_img.copy()
|
||||
|
||||
#--------------------------
|
||||
# --------------------------
|
||||
|
||||
#post-processing
|
||||
if grayscale == True:
|
||||
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
|
||||
# post-processing
|
||||
|
||||
img = cv2.resize(img, target_size)
|
||||
img_pixels = image.img_to_array(img)
|
||||
img_pixels = np.expand_dims(img_pixels, axis = 0)
|
||||
img_pixels /= 255 #normalize input in [0, 1]
|
||||
pixels = []
|
||||
|
||||
for img in imgs:
|
||||
|
||||
if grayscale == True:
|
||||
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
|
||||
|
||||
img = cv2.resize(img, target_size)
|
||||
img_pixels = image.img_to_array(img)
|
||||
img_pixels = np.expand_dims(img_pixels, axis=0)
|
||||
img_pixels /= 255 # normalize input in [0, 1]
|
||||
|
||||
pixels.append(img_pixels)
|
||||
|
||||
return {'processed': pixels, 'original': imgs}
|
||||
|
||||
return img_pixels
|
||||
|
||||
def allocateMemory():
|
||||
# find allocated memories
|
||||
gpu_indexes = []
|
||||
memory_usage_percentages = [];
|
||||
available_memories = [];
|
||||
total_memories = [];
|
||||
utilizations = []
|
||||
power_usages = [];
|
||||
power_capacities = []
|
||||
|
||||
#find allocated memories
|
||||
gpu_indexes = []
|
||||
memory_usage_percentages = []; available_memories = []; total_memories = []; utilizations = []
|
||||
power_usages = []; power_capacities = []
|
||||
try:
|
||||
result = subprocess.check_output(['nvidia-smi'])
|
||||
|
||||
try:
|
||||
result = subprocess.check_output(['nvidia-smi'])
|
||||
dashboard = result.decode("utf-8").split("=|")
|
||||
|
||||
dashboard = result.decode("utf-8").split("=|")
|
||||
dashboard = dashboard[1].split("\n")
|
||||
|
||||
dashboard = dashboard[1].split("\n")
|
||||
gpu_idx = 0
|
||||
for line in dashboard:
|
||||
if ("MiB" in line):
|
||||
power_info = line.split("|")[1]
|
||||
power_capacity = int(power_info.split("/")[-1].replace("W", ""))
|
||||
power_usage = int((power_info.split("/")[-2]).strip().split(" ")[-1].replace("W", ""))
|
||||
|
||||
gpu_idx = 0
|
||||
for line in dashboard:
|
||||
if ("MiB" in line):
|
||||
power_info = line.split("|")[1]
|
||||
power_capacity = int(power_info.split("/")[-1].replace("W", ""))
|
||||
power_usage = int((power_info.split("/")[-2]).strip().split(" ")[-1].replace("W", ""))
|
||||
power_usages.append(power_usage)
|
||||
power_capacities.append(power_capacity)
|
||||
|
||||
power_usages.append(power_usage)
|
||||
power_capacities.append(power_capacity)
|
||||
# ----------------------------
|
||||
|
||||
#----------------------------
|
||||
memory_info = line.split("|")[2].replace("MiB", "").split("/")
|
||||
utilization_info = int(line.split("|")[3].split("%")[0])
|
||||
|
||||
memory_info = line.split("|")[2].replace("MiB","").split("/")
|
||||
utilization_info = int(line.split("|")[3].split("%")[0])
|
||||
allocated = int(memory_info[0])
|
||||
total_memory = int(memory_info[1])
|
||||
available_memory = total_memory - allocated
|
||||
|
||||
allocated = int(memory_info[0])
|
||||
total_memory = int(memory_info[1])
|
||||
available_memory = total_memory - allocated
|
||||
total_memories.append(total_memory)
|
||||
available_memories.append(available_memory)
|
||||
memory_usage_percentages.append(round(100 * int(allocated) / int(total_memory), 4))
|
||||
utilizations.append(utilization_info)
|
||||
gpu_indexes.append(gpu_idx)
|
||||
|
||||
total_memories.append(total_memory)
|
||||
available_memories.append(available_memory)
|
||||
memory_usage_percentages.append(round(100*int(allocated)/int(total_memory), 4))
|
||||
utilizations.append(utilization_info)
|
||||
gpu_indexes.append(gpu_idx)
|
||||
gpu_idx = gpu_idx + 1
|
||||
|
||||
gpu_idx = gpu_idx + 1
|
||||
gpu_count = gpu_idx * 1
|
||||
|
||||
gpu_count = gpu_idx * 1
|
||||
except Exception as err:
|
||||
gpu_count = 0
|
||||
# print(str(err))
|
||||
|
||||
except Exception as err:
|
||||
gpu_count = 0
|
||||
#print(str(err))
|
||||
# ------------------------------
|
||||
|
||||
#------------------------------
|
||||
df = pd.DataFrame(gpu_indexes, columns=["gpu_index"])
|
||||
df["total_memories_in_mb"] = total_memories
|
||||
df["available_memories_in_mb"] = available_memories
|
||||
df["memory_usage_percentage"] = memory_usage_percentages
|
||||
df["utilizations"] = utilizations
|
||||
df["power_usages_in_watts"] = power_usages
|
||||
df["power_capacities_in_watts"] = power_capacities
|
||||
|
||||
df = pd.DataFrame(gpu_indexes, columns = ["gpu_index"])
|
||||
df["total_memories_in_mb"] = total_memories
|
||||
df["available_memories_in_mb"] = available_memories
|
||||
df["memory_usage_percentage"] = memory_usage_percentages
|
||||
df["utilizations"] = utilizations
|
||||
df["power_usages_in_watts"] = power_usages
|
||||
df["power_capacities_in_watts"] = power_capacities
|
||||
df = df.sort_values(by=["available_memories_in_mb"], ascending=False).reset_index(drop=True)
|
||||
|
||||
df = df.sort_values(by = ["available_memories_in_mb"], ascending = False).reset_index(drop = True)
|
||||
# ------------------------------
|
||||
|
||||
#------------------------------
|
||||
required_memory = 10000 # All deepface models require 9016 MiB
|
||||
|
||||
required_memory = 10000 #All deepface models require 9016 MiB
|
||||
if df.shape[0] > 0: # has gpu
|
||||
if df.iloc[0].available_memories_in_mb > required_memory:
|
||||
my_gpu = str(int(df.iloc[0].gpu_index))
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = my_gpu
|
||||
|
||||
if df.shape[0] > 0: #has gpu
|
||||
if df.iloc[0].available_memories_in_mb > required_memory:
|
||||
my_gpu = str(int(df.iloc[0].gpu_index))
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = my_gpu
|
||||
# ------------------------------
|
||||
# tf allocates all memory by default
|
||||
# this block avoids greedy approach
|
||||
|
||||
#------------------------------
|
||||
#tf allocates all memory by default
|
||||
#this block avoids greedy approach
|
||||
config = tf.ConfigProto()
|
||||
config.gpu_options.allow_growth = True
|
||||
session = tf.Session(config=config)
|
||||
keras.backend.set_session(session)
|
||||
|
||||
config = tf.ConfigProto()
|
||||
config.gpu_options.allow_growth = True
|
||||
session = tf.Session(config=config)
|
||||
keras.backend.set_session(session)
|
||||
|
||||
print("DeepFace will run on GPU (gpu_", my_gpu,")")
|
||||
else:
|
||||
#this case has gpu but no enough memory to allocate
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = "" #run it on cpu
|
||||
print("Even though the system has GPUs, there is no enough space in memory to allocate.")
|
||||
print("DeepFace will run on CPU")
|
||||
else:
|
||||
print("DeepFace will run on CPU")
|
||||
print("DeepFace will run on GPU (gpu_", my_gpu, ")")
|
||||
else:
|
||||
# this case has gpu but no enough memory to allocate
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = "" # run it on cpu
|
||||
print("Even though the system has GPUs, there is no enough space in memory to allocate.")
|
||||
print("DeepFace will run on CPU")
|
||||
else:
|
||||
print("DeepFace will run on CPU")
|
||||
|
||||
441
my_deepface.ipynb
Normal file
441
my_deepface.ipynb
Normal file
File diff suppressed because one or more lines are too long
BIN
test_imgs/.DS_Store
vendored
Normal file
BIN
test_imgs/.DS_Store
vendored
Normal file
Binary file not shown.
BIN
test_imgs/test1.jpg
Normal file
BIN
test_imgs/test1.jpg
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 285 KiB |
BIN
test_imgs/test2.jpeg
Normal file
BIN
test_imgs/test2.jpeg
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 3.8 KiB |
BIN
test_imgs/test3.jpg
Normal file
BIN
test_imgs/test3.jpg
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 29 KiB |
Loading…
x
Reference in New Issue
Block a user