def __init__(self, FLAGS, mydb, is_save_mysql):
super().__init__()
with tf.Graph().as_default():
with tf.Session() as sess:
#加载预训练模型
facenet.load_model(FLAGS.model_path)
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=1.0)
sess = tf.Session(config=tf.ConfigProto(
gpu_options=gpu_options, log_device_placement=False))
#创建MTCNN模型,初始化pnet,rnet,onet网络，为摄像头获取的图片进行人脸对齐做准备
self.pnet, self.rnet, self.onet = detect_face.create_mtcnn(
sess, None)
#初始化UI界面
self.setupUi(self)
#打开摄像头
self.camera = cv2.VideoCapture(0)
#判断摄像头是否打开
self.is_camera_opened = False
# 定时器：30ms捕获一帧
self._timer = QtCore.QTimer(self)
self._timer.timeout.connect(self._queryFrame)
self._timer.setInterval(30)
self.FLAGS = FLAGS
self.mydb = mydb
# 是否保存到数据库
self.is_save_mysql = is_save_mysql
def __init__(self, minsize=20, factor=0.709, threshold=[0.8, 0.9, 0.9]):
with tf.device('/gpu:0'):
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(allow_growth=True)
sess = tf.Session(config=tf.ConfigProto(
gpu_options=gpu_options, log_device_placement=False))
with sess.as_default():
pnet, rnet, onet = detect_face.create_mtcnn(sess, 'align/')
self.pnet = pnet
self.rnet = rnet
self.onet = onet
self.minsize = minsize
self.factor = factor
self.threshold = threshold
def load_and_align_data(image_paths, image_size=160, margin=44):
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
print('Creating networks and loading parameters')
with tf.Graph().as_default():
sess = tf.Session()
with sess.as_default():
pnet, rnet, onet = detect_face.create_mtcnn(sess, None)
img_list = []
nrof_samples = len(image_paths)
success_paths = []
for img_path in image_paths:
img = misc.imread(img_path, mode='RGB')
img_size = np.asarray(img.shape)[0:2]
bounding_boxes, _ = detect_face.detect_face(img, minsize, pnet, rnet,
onet, threshold, factor)
if len(bounding_boxes) < 1:
print("no face found in {}".format(img_path))
continue
det = np.squeeze(bounding_boxes[0, 0:4])
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(det[0] - margin / 2, 0)
bb[1] = np.maximum(det[1] - margin / 2, 0)
bb[2] = np.minimum(det[2] + margin / 2, img_size[1])
bb[3] = np.minimum(det[3] + margin / 2, img_size[0])
cropped = img[bb[1]:bb[3], bb[0]:bb[2], :]
aligned = misc.imresize(cropped, (image_size, image_size),
interp='bilinear')
prewhitened = prewhiten(aligned)
img_list.append(prewhitened)
success_paths.append(img_path)
images = np.stack(img_list)
return success_paths, images
def __init__(self):
self.graph = tf.Graph()
with self.graph.as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.5)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
with sess.as_default():
self.pnet, self.rnet, self.onet = FaceDet.create_mtcnn(sess, None)
def __init__(self):
# some constants kept as default from facenet
self.minsize = 20
self.threshold = [0.6, 0.7, 0.7]
self.factor = 0.709
self.margin = 44
self.input_image_size = 160
self.max_dist = 0.75
self.sess = tf.Session()
# read pnet, rnet, onet models from align directory and files are det1.npy, det2.npy, det3.npy
self.pnet, self.rnet, self.onet = detect_face.create_mtcnn(
self.sess, 'align')
# read 20170512-110547 model file downloaded from https://drive.google.com/file/d/0B5MzpY9kBtDVZ2RpVDYwWmxoSUk
facenet.load_model('20170512-110547/20170512-110547.pb')
# Get input and output tensors
self.images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
self.embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
self.phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
self.embedding_size = self.embeddings.get_shape()[1]
self.face_dic = {}
def detect_face(img):
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
margin = 32
image_size = 160
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.5)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
with sess.as_default():
pnet, rnet, onet = df.create_mtcnn(sess, None)
img_size = np.asarray(img.shape)[0:2]
bounding_boxes, _ = df.detect_face(img, minsize, pnet, rnet, onet,
threshold, factor)
det = np.squeeze(bounding_boxes[0, 0:4])
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(det[0] - margin / 2, 0)
bb[1] = np.maximum(det[1] - margin / 2, 0)
bb[2] = np.minimum(det[2] + margin / 2, img_size[1])
bb[3] = np.minimum(det[3] + margin / 2, img_size[0])
cropped = img[bb[1]:bb[3], bb[0]:bb[2], :]
aligned = misc.imresize(cropped, (image_size, image_size),
interp='bilinear')
face_token = str(uuid.uuid4())
output_filename = os.path.join(align_path, face_token + '.png')
misc.imsave(output_filename, aligned)
prewhitened = facenet.prewhiten(aligned)
aligned_image = prewhitened
aligned_pictures = [aligned_image]
return aligned_pictures
def initialize_mtcnn(gpu_memory_fraction):
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
with sess.as_default():
pnet, rnet, onet = detect_face.create_mtcnn(sess, None)
return pnet, rnet, onet
def process_celebrity(img):
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
print('Creating networks and loading parameters')
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=1.0)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
with sess.as_default():
pnet, rnet, onet = detect_face.create_mtcnn(sess, None)
img_size = np.asarray(img.shape)[0:2]
img_list = []
bounding_boxes, _ = detect_face.detect_face(img, minsize, pnet, rnet, onet,
threshold, factor)
count = len(bounding_boxes)
for i in range(count):
det = np.squeeze(bounding_boxes[i, 0:4])
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(det[0] - margin / 2, 0)
bb[1] = np.maximum(det[1] - margin / 2, 0)
bb[2] = np.minimum(det[2] + margin / 2, img_size[1])
bb[3] = np.minimum(det[3] + margin / 2, img_size[0])
cropped = img[bb[1]:bb[3], bb[0]:bb[2], :]
aligned = misc.imresize(cropped, (160, 160), interp='bilinear')
prewhitened = facenet.prewhiten(aligned)
# prewhitened = np.array(prewhitened).reshape(160, 160, 3)
img_list.append(prewhitened)
prewhitened = np.stack(img_list)
with tf.Session() as sess:
facenet.load_model(celeb_model)
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name(
"phase_train:0")
feed_dict = {
images_placeholder: prewhitened,
phase_train_placeholder: False
}
emb = sess.run(embeddings, feed_dict=feed_dict)
classifier_filename_exp = os.path.expanduser(classifier)
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile, encoding='latin1')
print('Loaded classifier model from file "%s"\n' %
classifier_filename_exp)
predictions = model.predict_proba(emb)
best_class_indices = np.argmax(predictions, axis=1)
best_class_probabilities = predictions[
np.arange(len(best_class_indices)), best_class_indices]
result_string = ""
for i in range(count):
result_string += class_names[best_class_indices[i]] + ', '
print(result_string)
return result_string
def _setup_mtcnn(self):
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(
gpu_options=gpu_options, log_device_placement=False))
with sess.as_default():
return detect_face.create_mtcnn(sess, None)
def __init__(self):
self.minsize = 20 # minimum size of face
self.threshold = [0.6, 0.7, 0.7] # three steps's threshold
self.factor = 0.709 # scale factor
with tf.Graph().as_default():
sess = tf.Session()
with sess.as_default():
self.pnet, self.rnet, self.onet = detect_face.create_mtcnn(
sess, None)
def __init__(self):
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=GPU_MEMORY_FRACTION)
sess = tf.Session(config=tf.ConfigProto(
gpu_options=gpu_options, log_device_placement=False))
with sess.as_default():
self.pnet, self.rnet, self.onet = detect_face.create_mtcnn(
sess, None)
def load_detect_face_model(device='auto'):
with tf.Graph().as_default():
if 'cpu' in device:
config = tf.ConfigProto(device_count={'GPU': 0})
sess = tf.Session(config=config)
else:
sess = tf.Session()
with sess.as_default():
pnet, rnet, onet = df.create_mtcnn(sess, None)
return (pnet, rnet, onet)
def __init__(self):
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.85)
self.sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
with self.sess.as_default():
self.pnet, self.rnet, self.onet = detect_face.create_mtcnn(self.sess, None)
self.minsize = 20 # minimum size of face
self.threshold = [ 0.6, 0.7, 0.7 ] # three steps's threshold
self.factor = 0.709 # scale factor
def __init__(self):
self.minsize = 30 # minimum size of face
self.threshold = [0.6, 0.7, 0.7] # three steps's threshold
self.factor = 0.709 # scale factor
print('Creating networks and loading parameters')
with tf.Graph().as_default():
# gpu_memory_fraction = 1.0
# gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=gpu_memory_fraction)
# sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
sess = tf.Session()
with sess.as_default():
self.pnet, self.rnet, self.onet = detect_face.create_mtcnn(sess, None)
def main(args):
# MTCNN
with tf.Graph().as_default():
sess = tf.Session()
with sess.as_default():
pnet, rnet, onet = detect_face.create_mtcnn(sess, None)
threshold = [0.6, 0.7, 0.7]
factor = 0.709
# Output dirs creation
if not os.path.exists(args.output_dir):
os.makedirs(args.output_dir)
images = []
for path in sorted(os.listdir(args.input_dir)):
if not os.path.exists(os.path.join(args.output_dir, path)):
os.mkdir(os.path.join(args.output_dir, path))
for name in sorted(os.listdir(os.path.join(args.input_dir, path))):
images.append(os.path.join(path, name))
# Alignment procedure
for path in tqdm(images):
img = io.imread(os.path.join(args.input_dir, path))
if img.ndim == 2:
img = to_rgb(img)
img = img[:, :, 0:3]
_minsize = min(min(img.shape[0] // 5, img.shape[1] // 5), 80)
bounding_boxes, points = detect_face.detect_face(
img, _minsize, pnet, rnet, onet, threshold, factor)
if bounding_boxes.size > 0:
bindex = -1
nrof_faces = bounding_boxes.shape[0]
if nrof_faces > 0:
det = bounding_boxes[:, 0:4]
img_size = np.asarray(img.shape)[0:2]
bindex = 0
if nrof_faces > 1:
bounding_box_size = (det[:, 2] - det[:, 0]) * (det[:, 3] -
det[:, 1])
img_center = img_size / 2
offsets = np.vstack([
(det[:, 0] + det[:, 2]) / 2 - img_center[1],
(det[:, 1] + det[:, 3]) / 2 - img_center[0]
])
offset_dist_squared = np.sum(np.power(offsets, 2.0), 0)
bindex = np.argmax(bounding_box_size -
offset_dist_squared * 2.0)
points = points[:, bindex]
landmark = points.reshape((2, 5)).T
warped = preprocess(img, landmark)
io.imsave(os.path.join(args.output_dir, path), warped)
else:
print(path + ' was skipped')
def sortface(path):
minsize = 3 # 脸部最小的大小
threshold = [0.65, 0.7, 0.7] # 三个步骤的阈值
factor = 0.709 # 用于在图像中检测的人脸大小的缩放金字塔的因子
# 分配给 tensorflow 的 gpu 的显存大小: GPU 实际显存 * 0.7
gpu_memory_fraction = 0.7
# 创建 tensorflow 网络并加载参数
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
with sess.as_default():
pnet, rnet, onet = detect_face.create_mtcnn(sess, None)
def eyes(im):
img = misc.imread(im)
bounding_boxes, face_points = detect_face.detect_face(img, minsize, pnet, rnet, onet, threshold, factor)
if bounding_boxes.shape[0] == 0:
return -1
eye_dis = abs(face_points[0] - face_points[1])
eye_mid = (face_points[0] + face_points[1])/2
score1 = abs(face_points[2]-eye_mid)/eye_dis
return round(score1[0], 2)
def lap(im):
img = cv2.imread(im)
score2 = cv2.Laplacian(img, cv2.CV_64F).var()
return score2//50
face_score1 = []
face_score2 = []
face_dirs = os.listdir(path)
face_dirs = [path+i for i in face_dirs]
for face in face_dirs:
print(face)
s1 = eyes(face)
face_score1.append(s1)
if s1 >= 0:
face_score2.append(lap(face))
else:
face_score2.append(0)
data = {'a': face_dirs, 'b': face_score1, 'c': face_score2}
data = pd.DataFrame(data)
data = data.sort_values(['b', 'c'], ascending=[True, False])
# data = data.sort_values('c', ascending=False)
dir = data['a'].values.tolist()
return dir
def initialize_mtcnn(gpu_memory_fraction,
rect_minsize=100,
mtcnn_thresholds=[0.6, 0.7, 0.7],
scale_factor=0.709):
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.5)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
with sess.as_default():
pnet, rnet, onet = create_mtcnn(sess, None)
minsize = rect_minsize
threshold = mtcnn_thresholds
factor = scale_factor
return pnet, rnet, onet, minsize, threshold, factor
def __init__(self, joint_align=True):
self.joint_align = joint_align
self.minsize = 20
self.threshold = [0.6, 0.9, 0.9]
self.threshold = [0.6, 0.7, 0.9]
self.threshold = [0.6, 0.7, 0.7]
self.threshold = [0.6, 0.7, 0.8]
self.factor = 0.6
self.factor = 0.8
self.factor = 0.709
self.graph = tf.Graph()
self.sess = tf.Session(graph=self.graph)
with self.graph.as_default():
self.pnet, self.rnet, self.onet = detect_face.create_mtcnn(self.sess, None)
def detection_face(img):
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
print('Creating networks and loading parameters')
with tf.Graph().as_default():
# gpu_memory_fraction = 1.0
# gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=gpu_memory_fraction)
# sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
sess = tf.Session()
with sess.as_default():
pnet, rnet, onet = detect_face.create_mtcnn(sess, None)
bounding_boxes, points = detect_face.detect_face(img, minsize, pnet, rnet,
onet, threshold, factor)
return bounding_boxes, points
def __init__(self):
# minimum size of face所认为的图片中需要识别的人脸的最小尺寸，minsize越大，生成的“金字塔”层数越少，resize和pnet的计算量越小。
self.minsize = 30 # 需要识别的人脸的最小尺寸，minsize越大，生成的“金字塔”层数越少，resize和pnet的计算量越小。
self.threshold = [0.6, 0.7, 0.7] # three steps's threshold阈值
self.factor = 0.709 # scale factor生成图片金字塔时使用的缩放因子即每次对边缩放的倍数
print('Creating networks and loading parameters')
with tf.Graph().as_default():
# # gpu_memory_fraction = 1.0
# # gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=gpu_memory_fraction)
# # sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
sess = tf.Session()
with sess.as_default():
# 在使用mtcnn模型时必须先调用detect_facec的creat_mtcnn方法导入网络结构，
self.pnet, self.rnet, self.onet = detect_face.create_mtcnn(
sess, None)
def get_face_img(img_paths):
# input a list of paths of images
# return
# (1) close-ups of faces
# (2) source
# (3) locations
face_closeups = list()
face_source = list()
face_locations = list()
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.25)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
with sess.as_default():
pnet, rnet, onet = detect_face.create_mtcnn(sess, None)
for path in img_paths:
img = img_read(path)
bounding_boxes, _ = detect_face.detect_face(
img, minsize, pnet, rnet, onet, threshold, factor)
nrof_faces = bounding_boxes.shape[0]
if nrof_faces > 0:
det = bounding_boxes[:, 0:4]
img_size = np.asarray(img.shape)[0:2]
for det_no in range(nrof_faces):
each_det = np.squeeze(det[det_no])
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(each_det[0] - args_margin / 2,
0) # left Bound
bb[1] = np.maximum(each_det[1] - args_margin / 2,
0) # upper Bound
bb[2] = np.minimum(each_det[2] + args_margin / 2,
img_size[1]) # right Bound
bb[3] = np.minimum(each_det[3] + args_margin / 2,
img_size[0]) # lower Bound
cropped = img[bb[1]:bb[3], bb[0]:bb[2], :]
scaled = misc.imresize(cropped,
(args_image_size, args_image_size),
interp='bilinear')
face_closeups.append(scaled)
face_source.append(path)
face_locations.append(bb)
return face_closeups, face_source, face_locations
def convert_to_embedding(self, single=False, img_path=None):
extracted = []
npy=''
with tf.Graph().as_default():
with tf.Session() as sess:
self.sess = sess
# Load the model
facenet.load_model(self.model_dir)
pnet, rnet, onet = detect_face.create_mtcnn(sess, npy)
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
margin = 32
frame_interval = 3
batch_size = 1000
image_size = 160
input_image_size = 160
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name("input:0")
self.images_placeholder = tf.image.resize_images(images_placeholder,(self.image_size, self.image_size))
self.embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
self.phase_train_placeholder = tf.get_default_graph().get_tensor_by_name("phase_train:0")
self.embedding_size = self.embeddings.get_shape()[1]
if not single:
for filename in os.listdir(self.data_path):
img = cv2.imread(self.data_path+"/"+filename, 1)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
#cv2.imshow('img', img)
#cv2.waitKey(0)
bounding_boxes, points = self.alignMTCNN.get_bounding_boxes(image=img)
bounding_boxes,points = detect_face.detect_face(img, minsize, pnet, rnet, onet, threshold, factor)
#detector = MTCNN()
#image = cv2.imread()
#result = detector.detect_faces(img)
#bounding_box = result[0]['box']
#keypoints = result[0]['keypoints']
faces = self.get_faces(img, bounding_boxes, points, filename)
extracted.append(faces)
with open('extracted_embeddings.pickle','wb') as f:
pickle.dump(extracted,f)
return None
else:
img = cv2.imread(img_path, 1)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
bounding_boxes, points = self.alignMTCNN.get_bounding_boxes(image=img)
faces = self.get_faces(img, bounding_boxes, points, img_path)
return faces
def main():
frame_interval = 3 # Number of frames after which to run face detection
model_path = '/home/zxk/AI/tensorflow-yolov3/checkpoint/yolov3.ckpt'
# detector=YoLoService(model_path)
sess = tf.Session()
pnet, rnet, onet = create_mtcnn(sess, None)
frame_count = 0
video_capture = cv2.VideoCapture(
'/home/zxk/AI/y2mate.com - _c0raDbZpV9s_360p.mp4')
# face_recognition = face.Recognition()
while True:
# Capture frame-by-frame
ret, frame = video_capture.read()
if not ret: break
frame_count += 1
if frame_count % 1 == 0:
# frame=cv2.rotate(frame,cv2.ROTATE_90_CLOCKWISE)
frameorgin = frame
H, W, _ = frameorgin.shape
frame = cv2.resize(frame, (640, 480),
interpolation=cv2.INTER_LINEAR)
# objects=detector.predict(frame)
total_boxes, _ = detect_face(frame[:, :, ::-1], 30, pnet, rnet,
onet, [0.6, 0.6, 0.7], 0.7)
objects = {
'boxes': total_boxes,
'labels': [1] * len(total_boxes),
'scores': [1] * len(total_boxes)
}
# cropPeople(frameorgin,objects,frame_count,'out')
add_overlays(frame, objects, 1)
cv2.imshow('Video', frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
print(frame_count, ret)
# When everything is done, release the capture
video_capture.release()
cv2.destroyAllWindows()
def __init__(self):
'''load mtcnn and facenet model
load all needed parameters from sys_config.py
preload the models and save correspond session
'''
self.facenet_weight_dir = sys_config.facenet_weight_dir
self.face_minsize = sys_config.face_minsize
self.image_size = sys_config.image_size
self.margin = sys_config.margin
self.three_threshold = sys_config.three_threshold
self.factor = sys_config.factor
self.distance_threshold = sys_config.distance_threshold
print('Creating networks and loading parameters')
with tf.Graph().as_default():
# setting not fully occupied memory, allocated on demand
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)
with sess.as_default():
# load mtcnn model(do face detection and align)
self.pnet, self.rnet, self.onet = detect_face.create_mtcnn(
sess, None)
# load the facenet model(do face recognition)
facenet.load_model(self.facenet_weight_dir)
# Get input and output tensors
self.images_placeholder = tf.get_default_graph(
).get_tensor_by_name("input:0")
self.embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
self.phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
# save session
self.facenet_session = sess
# load target people feature embeddings
template_embeddings_file = sys_config.template_face_embeddings_file
if os.path.exists(template_embeddings_file):
self.template_face_embeddings = np.load(
template_embeddings_file)
print("init finish")
def load_nets(**kwargs):
global pnets
global rnet
global onet
use_tf = PARAMS['use_tf']
if use_tf:
model_path = PARAMS['tf_path']
import tensorflow as tf
sess = tf.Session()
pnets, rnet, onet = detect_face.create_mtcnn(sess, model_path)
else:
plugin = kwargs.get('plugin')
model_dir = PARAMS.get('align_model_dir')
LOG.info('Load PNET')
pnets_proxy = []
for r in ko.parse_resolutions(PARAMS['resolutions']):
p = ko.PNetHandler(plugin, r[0], r[1])
pnets_proxy.append(p.proxy())
LOG.info('Load RNET')
net = ie.IENetwork.from_ir(*net_filenames(model_dir, 'rnet'))
rnet_proxy = OpenVINONet(plugin, net)
LOG.info('Load ONET')
net = ie.IENetwork.from_ir(*net_filenames(model_dir, 'onet'))
onet_proxy = OpenVINONet(plugin, net)
onet_input_name = list(net.inputs.keys())[0]
onet_batch_size = net.inputs[onet_input_name][0]
LOG.info('ONET_BATCH_SIZE = {}'.format(onet_batch_size))
pnets, rnet, onet = detect_face.create_openvino_mtcnn(
pnets_proxy, rnet_proxy, onet_proxy, onet_batch_size)
LOG.info('Load classifier')
with open(PARAMS['classifier'], 'rb') as f:
global model
global class_names
opts = {'file': f}
if six.PY3:
opts['encoding'] = 'latin1'
(model, class_names) = pickle.load(**opts)
def __init__(self):
#minsize ：最小可检测图像
self.minsize = 20
#threshold：人脸框阈值
self.threshold = [0.6, 0.7, 0.7]
#factor ：生成图像金字塔时候的缩放系数
self.factor = 0.709
print('MTCNN人脸检测与定位正在运行>>>\n')
#调用create_mtcnn-API，利用TensorFlow搭建神经网络
with tf.Graph().as_default():
sess = tf.Session()
with sess.as_default():
self.pnet, self.rnet, self.onet = detect_face.create_mtcnn(
sess, None) #参数解包，依次赋值给左侧，第二个参数默认值为None
def load_and_align_data(image_path, image_size, margin, gpu_memory_fraction):
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
print('Creating networks and loading parameters')
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
with sess.as_default():
pnet, rnet, onet = detect_face.create_mtcnn(sess, None)
img_list = []
img = misc.imread(os.path.expanduser(image_path), mode='RGB')
print("os.path.expanduser(image_path)")
print(os.path.expanduser(image_path))
img_size = np.asarray(img.shape)[0:2]
bounding_boxes, _ = detect_face.detect_face(img, minsize, pnet, rnet, onet,
threshold, factor)
if len(bounding_boxes) < 1:
#image_paths.remove(image)
print("can't detect face, remove ", image_path)
else:
for bounding_box in bounding_boxes:
print("bounding_box")
print(bounding_box)
det = np.squeeze(bounding_box)
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(det[0] - margin / 2, 0)
bb[1] = np.maximum(det[1] - margin / 2, 0)
bb[2] = np.minimum(det[2] + margin / 2, img_size[1])
bb[3] = np.minimum(det[3] + margin / 2, img_size[0])
cropped = img[bb[1]:bb[3], bb[0]:bb[2], :]
aligned = misc.imresize(cropped, (image_size, image_size),
interp='bilinear')
prewhitened = facenet.prewhiten(aligned)
img_list.append(prewhitened)
#print("img_list")
#print(img_list)
return img_list, bounding_boxes
def initialise(self, filename):
# some constants kept as default from facenet
global pnet, rnet, onet, threshold, factor, minsize, margin, sess, images_placeholder, phase_train_placeholder, embedding_size, embeddings
sess = tf.Session()
# read pnet, rnet, onet models from align directory and files are det1.npy, det2.npy, det3.npy
pnet, rnet, onet = detect_face.create_mtcnn(sess, 'align')
# read 20170512-110547 model file downloaded from https://drive.google.com/file/d/0B5MzpY9kBtDVZ2RpVDYwWmxoSUk
facenet.load_model("20170512-110547/20170512-110547.pb")
# Get input and output tensors
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name("embeddings:0")
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name(
"phase_train:0")
embedding_size = embeddings.get_shape()[1]
obj = Recognition
obj.printResults(self, filename)
def detection_face(img):
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
print('Creating networks and loading parameters')
with tf.Graph().as_default():
# gpu_memory_fraction = 1.0
# gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=gpu_memory_fraction)
# sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False))
sess = tf.Session()
with sess.as_default():
pnet, rnet, onet = detect_face.create_mtcnn(sess, None)
bboxes, landmarks = detect_face.detect_face(img, minsize, pnet, rnet, onet, threshold, factor)
landmarks = np.transpose(landmarks)
bboxes = bboxes.astype(int)
bboxes = [b[:4] for b in bboxes]
landmarks_list=[]
for landmark in landmarks:
face_landmarks = [[landmark[j], landmark[j + 5]] for j in range(5)]
landmarks_list.append(face_landmarks)
return bboxes,landmarks_list
def main(args):
sess = tf.Session()
pnet, rnet, onet = detect_face.create_mtcnn(sess, None)
threshold = [ 0.6, 0.7, 0.7 ]
factor = 0.709
img = io.imread(args.image)
_minsize = min(min(img.shape[0]//5, img.shape[1]//5),80)
bounding_boxes, points = detect_face.detect_face(img, _minsize, pnet, rnet, onet, threshold, factor)
assert bounding_boxes.size>0
points = points[:, 0]
landmark = points.reshape((2,5)).T
warped = preprocess(img, landmark)
io.imsave(args.image[:-4]+'_aligned.png',warped)
if args.mask:
if args.logo is None:
logo_mask = np.ones((1,400,900,3),dtype=np.float32)
else:
logo_mask = np.where(io.imread(args.logo)/255.< 0.5, 1., 0.)
logo_mask = np.expand_dims(logo_mask, axis=0)
logo = tf.placeholder(tf.float32,shape=[1,400,900,3])
param = tf.placeholder(tf.float32,shape=[1,1])
ph = tf.placeholder(tf.float32,shape=[1,1])
result = projector(param,ph,logo)
face_input = tf.placeholder(tf.float32,shape=[1,600,600,3])
theta = tf.placeholder(tf.float32,shape=[1,6])
prepared = stn(result,theta)
united = prepared[:,300:,150:750]+face_input*(1-prepared[:,300:,150:750])
img_with_mask = sess.run(united,feed_dict={ph:[[args.ph]],logo:logo_mask,param:[[args.param]],\
face_input:np.expand_dims(warped/255.,0),\
theta:1./args.scale*np.array([[1.,0.,-args.x/450.,0.,1.,-args.y/450.]])})[0]
io.imsave(args.image[:-4]+'_mask.png',img_with_mask)
