def Run(target):
assert target in ['rnet', 'onet']
model_path = GetModelPaths()
batch_size = [2048, 256, 16]
thresh = [0.4, 0.05, 0.7]
min_face_size = 24
detectors = [None, None, None]
detectors[0] = FcnDetector(P_Net, model_path[0])
if target == 'onet':
detectors[1] = Detector(R_Net, 24, batch_size[1], model_path[1])
data = read_annotation()
if cfg.debug:
data['bboxes'] = data['bboxes'][:20]
data['images'] = data['images'][:20]
test_data = TestLoader(data['images'])
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=min_face_size,
stride=2,
threshold=thresh)
detections, _ = mtcnn_detector.detect_face(test_data)
save_file = join(cfg.path_output_files, 'detections_%s.pkl' % target)
with open(save_file, 'wb') as f:
pickle.dump(detections, f, 1)
save_hard_example(target, data, save_file)
def t_net(prefix, epoch,
batch_size, test_mode="PNet",
thresh=[0.6, 0.6, 0.7], min_face_size=25,
stride=2, slide_window=False, shuffle=False, vis=False):
detectors = [None, None, None]
print("Test model: ", test_mode)
#PNet-echo
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
print(model_path[0])
# load pnet model
if slide_window:
PNet = Detector(P_Net, 12, batch_size[0], model_path[0])
else:
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
# load rnet model
if test_mode in ["RNet", "ONet"]:
print("==================================", test_mode)
RNet = Detector(R_Net, 24, batch_size[1], model_path[1])
detectors[1] = RNet
# load onet model
if test_mode == "ONet":
print("==================================", test_mode)
ONet = Detector(O_Net, 48, batch_size[2], model_path[2])
detectors[2] = ONet
basedir = '.'
#anno_file
filename = './wider_face_train_bbx_gt.txt'
#read annatation(type:dict)
data = read_annotation(basedir,filename)
mtcnn_detector = MtcnnDetector(detectors=detectors, min_face_size=min_face_size,
stride=stride, threshold=thresh, slide_window=slide_window)
print("==================================")
# 注意是在“test”模式下
# imdb = IMDB("wider", image_set, root_path, dataset_path, 'test')
# gt_imdb = imdb.gt_imdb()
test_data = TestLoader(data['images'])
#list
detections,_ = mtcnn_detector.detect_face(test_data)
save_net = 'RNet'
if test_mode == "PNet":
save_net = "RNet"
elif test_mode == "RNet":
save_net = "ONet"
#save detect result
save_path = os.path.join(data_dir, save_net)
print save_path
if not os.path.exists(save_path):
os.mkdir(save_path)
save_file = os.path.join(save_path, "detections.pkl")
with open(save_file, 'wb') as f:
pickle.dump(detections, f,1)
print("%s测试完成开始OHEM" % image_size)
save_hard_example(image_size, data, save_path)
def t_net(prefix, epoch,
batch_size, test_mode="PNet",
thresh=[0.6, 0.6, 0.7], min_face_size=25,
stride=2, slide_window=False, shuffle=False, vis=False):
detectors = [None, None, None]
print("Test model: ", test_mode)
#PNet-echo
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
print(model_path[0])
# load pnet model
if slide_window:
PNet = Detector(P_Net, 12, batch_size[0], model_path[0])
else:
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
# load rnet model
if test_mode in ["RNet", "ONet"]:
print("==================================", test_mode)
RNet = Detector(R_Net, 24, batch_size[1], model_path[1])
detectors[1] = RNet
# load onet model
if test_mode == "ONet":
print("==================================", test_mode)
ONet = Detector(O_Net, 48, batch_size[2], model_path[2])
detectors[2] = ONet
basedir = '.'
#anno_file
filename = './wider_face_train_bbx_gt.txt'
#read annatation(type:dict)
data = read_annotation(basedir,filename)
mtcnn_detector = MtcnnDetector(detectors=detectors, min_face_size=min_face_size,
stride=stride, threshold=thresh, slide_window=slide_window)
print("==================================")
# 注意是在“test”模式下
# imdb = IMDB("wider", image_set, root_path, dataset_path, 'test')
# gt_imdb = imdb.gt_imdb()
test_data = TestLoader(data['images'][:100])
#list
detections,_ = mtcnn_detector.detect_face(test_data)
save_net = 'RNet'
if test_mode == "PNet":
save_net = "RNet"
elif test_mode == "RNet":
save_net = "ONet"
#save detect result
save_path = os.path.join(data_dir, save_net)
print save_path
if not os.path.exists(save_path):
os.mkdir(save_path)
save_file = os.path.join(save_path, "detections.pkl")
with open(save_file, 'wb') as f:
pickle.dump(detections, f,1)
print("%s测试完成开始OHEM" % image_size)
save_hard_example(image_size, data, save_path)
def t_net(prefix,
epoch,
data_dir,
batch_size,
PNet_factory,
RNet_factory,
test_mode="PNet",
thresh=[0.6, 0.6, 0.7],
min_face_size=25,
stride=2,
slide_window=False,
shuffle=False,
vis=False):
# load detectors
detectors = [None, None, None]
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
# load pnet model
if slide_window:
PNet = Detector(PNet_factory, 12, batch_size[0], model_path[0])
else:
PNet = FcnDetector(PNet_factory, model_path[0])
detectors[0] = PNet
# load rnet model
if test_mode == "RNet":
RNet = Detector(RNet_factory, 24, batch_size[1], model_path[1])
detectors[1] = RNet
# Get detections
basedir = '.'
filename = './wider_face_train_bbx_gt.txt'
data = read_annotation(basedir, filename)
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=min_face_size,
stride=stride,
threshold=thresh,
slide_window=slide_window)
test_data = TestLoader(data['images'])
print("Getting detections for {} images.".format(test_data.size))
detections, _ = mtcnn_detector.detect_face(test_data)
# Save detections
if test_mode == "PNet":
save_net = "RNet"
elif test_mode == "RNet":
save_net = "ONet"
save_path = os.path.join(data_dir, save_net)
if not os.path.exists(save_path):
os.mkdir(save_path)
save_file = os.path.join(save_path, "detections.pkl")
with open(save_file, 'wb') as f:
pickle.dump(detections, f, 1)
save_hard_example(image_size, data, save_path)
def t_net(prefix, epoch, batch_size, test_mode, thresh, min_face_size=20,
stride=2, slide_window=False):
detectors = [None, None, None]
# 生成指定模型的困难样本
print("Test model: ", test_mode)
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
# PNet模型
print(model_path[0])
if slide_window:
p_net = Detector(P_Net, 12, batch_size[0], model_path[0])
else:
p_net = FcnDetector(P_Net, model_path[0])
detectors[0] = p_net
# RNet模型
if test_mode in ["RNet", "ONet"]:
print("================= {} =================".format(test_mode))
r_net = Detector(R_Net, 24, batch_size[1], model_path[1])
detectors[1] = r_net
# ONet模型，这个模式下生成的样本主要用来观察，而不是训练
if test_mode == "ONet":
print("================== {} ================".format(test_mode))
o_net = Detector(O_Net, 48, batch_size[2], model_path[2])
detectors[2] = o_net
# 读取bounding box的ground truth及图片，type:dict，include key 'images' and 'bboxes'
data = read_bboxes_data(path_config.point2_train_txt_path, path_config.images_dir)
mtcnn_detector = MtcnnDetector(detectors=detectors, min_face_size=min_face_size,
stride=stride, threshold=thresh, slide_window=slide_window)
print('加载原始图片数据，以进行检测及生成困难样本...')
test_data = TestLoader(data['images'])
print('加载完成， 开始检测...')
detections, _ = mtcnn_detector.detect_images(test_data)
print('检测完成！')
# 保存检测结果
if test_mode == "PNet":
save_path = path_config.rnet_save_hard_path
elif test_mode == "RNet":
save_path = path_config.onet_save_hard_path
else:
raise ValueError('网络类型(--test_mode)错误！')
print('保存检测结果的路径为:', save_path)
if not os.path.exists(save_path):
os.mkdir(save_path)
save_file = os.path.join(save_path, "detections.pkl")
with open(save_file, 'wb') as f:
pickle.dump(detections, f, 1)
print("%s测试完成，开始生成困难样本..." % test_mode)
save_hard_example(data, test_mode, save_path)
def GetDetector(
model_path,
minsize=20,
factor=0.709,
thresh_pred_p=0.6,
thresh_pred_r=0.7,
thresh_pred_o=0.8,
thresh_nms_p=0.5,
thresh_nms_r=0.7,
thresh_nms_o=0.7,
mode_p=nms_mode['Union'],
mode_r=nms_mode['Union'],
mode_o=nms_mode['Minimum'],
thresh_merge=0.7,
mode_merge=nms_mode['Union'],
):
paths = GetModelPaths(model_path)
detectors = [None, None, None]
detectors[0] = FcnDetector(P_Net, paths[0])
detectors[1] = Detector(R_Net, 24, 1, paths[1])
detectors[2] = Detector(O_Net, 48, 1, paths[2])
detector = MtcnnDetector(
detectors=detectors,
minsize=minsize,
factor=factor,
thresh_prediction=[thresh_pred_p, thresh_pred_r, thresh_pred_o],
thresh_nms=[thresh_nms_p, thresh_nms_r, thresh_nms_o],
modes=[mode_p, mode_r, mode_o],
thresh_merge=thresh_merge,
mode_merge=mode_merge)
return detector
def mtcnn_detector_init():
pnet_model_path = '../data/MTCNN_model/PNet_landmark/PNet'
rnet_model_path = '../data/MTCNN_model/RNet_landmark/RNet'
onet_model_path = '../data/MTCNN_model/ONet_landmark/ONet'
test_mode = "onet"
thresh = [0.9, 0.6, 0.7]
min_face_size = 24
stride = 2
slide_window = False
shuffle = False
#vis = True
detectors = [None, None, None]
prefix = [pnet_model_path, rnet_model_path, onet_model_path]
epoch = [18, 14, 16]
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
RNet = Detector(R_Net, 24, 1, model_path[1])
detectors[1] = RNet
ONet = Detector(O_Net, 48, 1, model_path[2])
detectors[2] = ONet
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=min_face_size,
stride=stride,
threshold=thresh,
slide_window=slide_window)
return mtcnn_detector
def load_mtcnn(conf):
# load mtcnn model
MODEL_PATH = conf.get("MTCNN", "MODEL_PATH")
MIN_FACE_SIZE = int(conf.get("MTCNN", "MIN_FACE_SIZE"))
STEPS_THRESHOLD = [
float(i) for i in conf.get("MTCNN", "STEPS_THRESHOLD").split(",")
]
detectors = [None, None, None]
prefix = [
MODEL_PATH + "/PNet_landmark/PNet", MODEL_PATH + "/RNet_landmark/RNet",
MODEL_PATH + "/ONet_landmark/ONet"
]
epoch = [18, 14, 16]
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
RNet = Detector(R_Net, 24, 1, model_path[1])
detectors[1] = RNet
ONet = Detector(O_Net, 48, 1, model_path[2])
detectors[2] = ONet
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=MIN_FACE_SIZE,
threshold=STEPS_THRESHOLD)
return mtcnn_detector
def mtcnn_detector_init():
test_mode = "ONet"
thresh = [0.9, 0.6, 0.7]
min_face_size = 24
stride = 2
slide_window = False
shuffle = False
detectors = [None, None, None]
prefix = ['../data/MTCNN_model/PNet_landmark/PNet', '../data/MTCNN_model/RNet_landmark/RNet', '../data/MTCNN_model/ONet_landmark/ONet']
epoch = [18, 14, 16]
batch_size = [2048, 256, 16]
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
# load pnet model
if slide_window:
PNet = Detector(P_Net, 12, batch_size[0], model_path[0])
else:
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
# load rnet model
if test_mode in ["RNet", "ONet"]:
RNet = Detector(R_Net, 24, batch_size[1], model_path[1])
detectors[1] = RNet
# load onet model
if test_mode == "ONet":
ONet = Detector(O_Net, 48, batch_size[2], model_path[2])
detectors[2] = ONet
mtcnn_detector = MtcnnDetector(detectors=detectors, min_face_size=min_face_size,
stride=stride, threshold=thresh, slide_window=slide_window)
return mtcnn_detector
def Load(self):
self.Load_pnet_model()
self.Load_rnet_model()
self.Load_onet_model()
return MtcnnDetector(detectors=self.detectors,
min_face_size=self.min_face_size,
stride=self.stride,
threshold=self.thresh,
slide_window=self.slide_window)
class MTCNN_Crop_Face(object):
def __init__(self):
test_mode = "ONet"
thresh = [0.9, 0.7, 0.7]
min_face_size = 32
stride = 2
slide_window = False
shuffle = False
batch_size = [2048, 64, 16]
detectors = [None, None, None]
prefix = ['./data2/MTCNN_model/PNet_landmark/PNet', './data2/MTCNN_model/RNet_landmark/RNet', './data2/MTCNN_model/ONet_landmark/ONet']
epoch = [18, 14, 16]
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
RNet = Detector(R_Net, 24, 1, model_path[1])
detectors[1] = RNet
ONet = Detector(O_Net, 48, 1, model_path[2])
detectors[2] = ONet
self.mtcnn_detector = MtcnnDetector(detectors=detectors, min_face_size=min_face_size,
stride=stride, threshold=thresh, slide_window=slide_window)
def cropface(self, frame):
cropped_list = []
i = 0
image = np.array(frame)
all_boxes, landmarks = self.mtcnn_detector.detect(image)
# all_boxes,landmarks = self.mtcnn_detector.detect_face(test_data)
# image = cv2.imread(imagepath)
for bbox in all_boxes:
corpbbox = [int(bbox[0]), int(bbox[1]), int(bbox[2]), int(bbox[3])]
if abs(corpbbox[3] - corpbbox[1]) > abs(corpbbox[2] - corpbbox[0]):
n0 = int(0.5 * (corpbbox[2] + corpbbox[0]) - 0.5 * abs(corpbbox[3] - corpbbox[1]))
n1 = corpbbox[1]
n2 = int(0.5 * (corpbbox[2] + corpbbox[0]) + 0.5 * abs(corpbbox[3] - corpbbox[1]))
n3 = corpbbox[3]
else:
n0 = corpbbox[0]
n1 = int(0.5 * (corpbbox[3] + corpbbox[1]) - 0.5 * abs(corpbbox[2] - corpbbox[0]))
n2 = corpbbox[2]
n3 = int(0.5 * (corpbbox[3] + corpbbox[1]) + 0.5 * abs(corpbbox[2] - corpbbox[0]))
# cropped = image[n1:n3, n0:n2]
cropped = [int(n0), int(n1), int(n2), int(n3)]
cropped_list.append(cropped)
# cv2.rectangle(frame, (int(bbox[0]),int(bbox[1])),(int(bbox[2]),int(bbox[3])),(0,0,255))
# cv2.imwrite("../data/test_result/%d.png" %(count),image)
# cv2.imshow("image",frame)
# cv2.waitKey(0)
# return all_boxes
return cropped_list
def __init__(self, models_path, image_path, ground_truth_file):
""" 初始化：加载PNet模型、待测试图片路径及对应ground truth
:param models_path: [PNet, RNet, ONet]模型路径
:param image_path: 待测试图片路径
:param ground_truth_file: 待测图片目标ground_truth文件
"""
# 初始化PNet模型检测器
pnet_model = None
rnet_model = None
onet_model = None
if models_path[0] is not None:
pnet_model = FcnDetector(P_Net, models_path[0])
if models_path[1] is not None:
rnet_model = Detector(R_Net, 24, 256, models_path[1])
if models_path[2] is not None:
onet_model = Detector(O_Net, 48, 16, models_path[2])
self.detector = MtcnnDetector([pnet_model, rnet_model, onet_model], min_face_size=20, stride=2,
threshold=[0.7, 0.7, 0.7], scale_factor=0.79, slide_window=False)
# 初始化ground truth
self.ground_map = dict()
valid_image_path = list()
with open(ground_truth_file, 'r') as truth_file:
for ground_truth in truth_file:
ground_truth = ground_truth.strip().split(' ')
self.ground_map[ground_truth[0]] = np.array([float(_) for _ in ground_truth[1:]])
valid_image_path.append(ground_truth[0])
# 初始化图片加载器
if os.path.isdir(image_path):
images_path = PNetTester.search_file(image_path)
elif os.path.isfile(image_path) and image_path.endswith('.jpg'):
images_path = [image_path]
self.images_path = list()
for image_path in images_path:
if os.path.basename(image_path) in valid_image_path:
self.images_path.append(image_path)
print('待检测图片数量：', len(self.images_path))
self.test_loader = TestLoader(self.images_path)
return
def __init__(self):
test_mode = "ONet"
thresh = [0.9, 0.7, 0.7]
min_face_size = 32
stride = 2
slide_window = False
shuffle = False
batch_size = [2048, 64, 16]
detectors = [None, None, None]
prefix = ['./data2/MTCNN_model/PNet_landmark/PNet', './data2/MTCNN_model/RNet_landmark/RNet', './data2/MTCNN_model/ONet_landmark/ONet']
epoch = [18, 14, 16]
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
RNet = Detector(R_Net, 24, 1, model_path[1])
detectors[1] = RNet
ONet = Detector(O_Net, 48, 1, model_path[2])
detectors[2] = ONet
self.mtcnn_detector = MtcnnDetector(detectors=detectors, min_face_size=min_face_size,
stride=stride, threshold=thresh, slide_window=slide_window)
def load_mtcnn(conf):
# load mtcnn model
MODEL_PATH = conf.get("MTCNN", "MODEL_PATH")
MIN_FACE_SIZE = int(conf.get("MTCNN", "MIN_FACE_SIZE"))
STEPS_THRESHOLD = [
float(i) for i in conf.get("MTCNN", "STEPS_THRESHOLD").split(",")
]
detectors = [None, None, None]
prefix = [
MODEL_PATH + "/PNet_landmark/PNet", MODEL_PATH + "/RNet_landmark/RNet",
MODEL_PATH + "/ONet_landmark/ONet"
]
epoch = [18, 14, 16]
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
RNet = Detector(R_Net, 24, 1, model_path[1])
detectors[1] = RNet
ONet = Detector(O_Net, 48, 1, model_path[2])
detectors[2] = ONet
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=MIN_FACE_SIZE,
threshold=STEPS_THRESHOLD)
return mtcnn_detector
# Check if the model is a model directory (containing a metagraph and a checkpoint file)
# or if it is a protobuf file with a frozen graph
model_exp = os.path.expanduser(model)
if (os.path.isfile(model_exp)):
print('Model filename: %s' % model_exp)
with tf.gfile.FastGFile(model_exp, 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
tf.import_graph_def(graph_def, name='')
else:
print('Model directory: %s' % model_exp)
meta_file, ckpt_file = get_model_filenames(model_exp)
print('Metagraph file: %s' % meta_file)
print('Checkpoint file: %s' % ckpt_file)
saver = tf.train.import_meta_graph(os.path.join(model_exp, meta_file))
saver.restore(tf.get_default_session(),
os.path.join(model_exp, ckpt_file))
def process_img():
param = parameter()
min_size = param.min_size
score_threshold = param.threshold
slid_window = param.slid_window
if test_relu == 100:
batch_size = [1, 1, 1]
else:
batch_size = param.batch_size
epoch_load = param.epoch_load
multi_detector = [None, None, None]
#load paramter path
model_path = load_model(epoch_load)
#load net result
if config.train_face:
Pnet_det = FcnDetector(P_Net, model_path[0])
else:
Pnet_det = FcnDetector(P_Net_W, model_path[0])
Rnet_det = Detector(R_Net,
data_size=24,
batch_size=batch_size[1],
model_path=model_path[1])
if len(model_path) == 3:
Onet_det = Detector(O_Net,
data_size=48,
batch_size=batch_size[2],
model_path=model_path[2])
multi_detector = [Pnet_det, Rnet_det, Onet_det]
else:
multi_detector = [Pnet_det, Rnet_det, None]
#get bbox and landmark
Mtcnn_detector = MtcnnDetector(multi_detector,
min_size,
threshold=score_threshold)
#bboxs,bbox_clib,landmarks = Mtcnn_detector.detect(img)
return Mtcnn_detector
def build_camera(self, camera_id, path_name):
#print("Loading Deep Face Detector(MTCNN) recognition model ............")
#test_mode = "onet"
thresh = [0.9, 0.9, 0.8]
min_face_size = 81
stride = 2
slide_window = False
#shuffle = False
#vis = True
detectors = [None, None, None]
prefix = ['../execute_system/MTCNN_Tensorflow_fast/data/MTCNN_model/PNet_landmark/PNet',
'../execute_system/MTCNN_Tensorflow_fast/data/MTCNN_model/RNet_landmark/RNet',
'../execute_system/MTCNN_Tensorflow_fast/data/MTCNN_model/ONet_landmark/ONet']
epoch = [40, 36, 36]
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
RNet = Detector(R_Net, 24, 1, model_path[1])
detectors[1] = RNet
ONet = Detector(O_Net, 48, 1, model_path[2])
detectors[2] = ONet
mtcnn_detector = MtcnnDetector(detectors=detectors, min_face_size=min_face_size,
stride=stride, threshold=thresh, slide_window=slide_window)
# read names from dataset
name_list = read_name_list(path_name)
cap = cv2.VideoCapture(camera_id)
#fps1 = cap.get(cv2.CAP_PROP_FPS)
#size = (int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)),
# int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)))
#size = 640 x 480
cap.set(cv2.CAP_PROP_FRAME_WIDTH,528)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT,384)
while True:
t1 = cv2.getTickCount()
success, frame = cap.read()
if success:
thickness = (frame.shape[0] + frame.shape[1]) // 350
image = np.array(frame)
boxes_c,landmarks = mtcnn_detector.detect(image)
#print(landmarks.shape)
t2 = cv2.getTickCount()
t = (t2 - t1) / cv2.getTickFrequency()
fps = 1.0 / t
print('fps:',fps)
for i in range(boxes_c.shape[0]):
bbox = boxes_c[i, :4]
#score = boxes_c[i, 4]
cropbbox = [int(bbox[0]), int(bbox[1]), int(bbox[2]), int(bbox[3])]
W = -int(cropbbox[0]) + int(cropbbox[2])
H = -int(cropbbox[1]) + int(cropbbox[3])
paddingH = 0.02 * H
paddingW = 0.01 * W
crop_img = frame[int(cropbbox[1]+paddingH):int(cropbbox[3]-paddingH), int(cropbbox[0]-paddingW):int(cropbbox[2]+paddingW)]
if crop_img is None:
continue
if crop_img.shape[0] < 0 or crop_img.shape[1] < 0:
continue
label,prob = self.model.face_predict(crop_img)
if prob > 0.7:
show_name = name_list[label]
else:
show_name = 'Stranger'
person_tag = "%s: %.2f" %(show_name, prob)
#text_end = (int(cropbbox[0]) + len(person_tag) * 10,int(cropbbox[1]) - 20 )
text_start = (max(int(cropbbox[0]), 10), max(int(cropbbox[1]), 10))
#cv2.rectangle(draw, text_end, text_start, (255, 255, 0), -1, cv2.LINE_AA )
cv2.putText(frame, person_tag, text_start, cv2.FONT_HERSHEY_SIMPLEX, 1, (255,0,255), 1)
# rectangle for face area
for i in range(thickness):
start = (int(cropbbox[0]) + i, int(cropbbox[1]) + i)
end = (int(cropbbox[2] - i), int(cropbbox[3]) - i)
frame = cv2.rectangle(frame, start, end, (0, 255, 0), 1)
# display the landmarks
for i in range(landmarks.shape[0]):
for j in range(len(landmarks[i])//2):
cv2.circle(frame, (int(landmarks[i][2*j]),int(int(landmarks[i][2*j+1]))), 2, (0,0,255))
cv2.imshow("Camera", frame)
k = cv2.waitKey(10)
if k & 0xFF == ord('q'):
break
else:
print ('device not find')
break
cap.release()
cv2.destroyAllWindows()
def t_net(prefix,
epoch,
batch_size,
test_mode="PNet",
thresh=[0.6, 0.6, 0.7],
min_face_size=25,
stride=2,
slide_window=False,
shuffle=False,
vis=False):
"""
Parameter
----------------
"""
detectors = [None, None, None]
print("Test model: ", test_mode)
#PNet-echo
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
print(model_path[0])
# load pnet model
if slide_window:
PNet = Detector(P_Net, 12, batch_size[0], model_path[0])
else:
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
# load rnet model
pnet_detections = None
if test_mode in ["RNet", "ONet"]:
print("==================================", test_mode)
RNet = Detector(R_Net, 24, batch_size[1], model_path[1])
detectors[1] = RNet
print("load pnet predictions...")
pnet_detections = pickle.load(
open(os.path.join("../data/24/RNet", 'detections.pkl'), 'rb'))
print("load pnet predictions done.")
# load onet model
rnet_detections = None
if test_mode == "ONet":
print("==================================", test_mode)
ONet = Detector(O_Net, 48, batch_size[2], model_path[2])
detectors[2] = ONet
print("load rnet predictions...")
rnet_detections = pickle.load(
open(os.path.join("../data/48/ONet", 'detections.pkl'), 'rb'))
print("load rnet predictions done.")
# detec的数据源始终是一样的
basedir = 'E:/Document/Datasets/Wider Face'
#anno_file
filename = 'wider_face_train_bbx_gt.txt'
#data是一个dict，data["images"]为所有照片路径list，data["bboxes"]是所有照片bboxes的值，一一对应
data = read_annotation(basedir, filename)
# 初始化mtcnn_detector，就是训练好的模型
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=min_face_size,
stride=stride,
threshold=thresh,
slide_window=slide_window)
print("==================================")
# 注意是在“test”模式下
# imdb = IMDB("wider", image_set, root_path, dataset_path, 'test')
# gt_imdb = imdb.gt_imdb()
print('load test data')
#所有照片，训练时为12880张
test_data = TestLoader(data['images'])
print('finish loading')
#list
print('start detecting....')
detections, _ = mtcnn_detector.detect_face(
test_data, pnet_detections, rnet_detections) #调用训练好的pnet，返回的是candidate
print('finish detecting ')
save_net = 'RNet'
if test_mode == "PNet":
save_net = "RNet"
elif test_mode == "RNet":
save_net = "ONet"
# #save detect result
save_path = os.path.join(data_dir, save_net)
print('save_path is :')
print(save_path)
if not os.path.exists(save_path):
os.mkdir(save_path)
# 把所有candidate写到文件中序列化
save_file = os.path.join(save_path, "detections.pkl")
with open(save_file, 'wb') as f:
pickle.dump(detections, f, 1)
print("save done.")
print("%s测试完成开始OHEM" % image_size)
# 然后根据candidate和gt的Iou把每个candidate分类并保存到文本和相应的照片
save_hard_example(image_size, data, save_path)
def RTrecognization(facenet_model_path, SVCpath, database_path):
#facenet_model_path为facenet模型路径
#SVCpath为SVM分类模型路径
#database_path为人脸库数据
with tf.Graph().as_default():
with tf.Session() as sess:
# Load the model
print('Loading feature extraction model')
facenet.load_model(facenet_model_path)
with open(SVCpath, 'rb') as infile:
(classifymodel, class_names) = pickle.load(infile)
print('Loaded classifier model from file "%s"' % SVCpath)
# 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]
Database = np.load(database_path)
test_mode = "onet"
thresh = [0.9, 0.6, 0.7]
min_face_size = 24
stride = 2
slide_window = False
shuffle = False
#vis = True
detectors = [None, None, None]
prefix = [
'../data/MTCNN_model/PNet_landmark/PNet',
'../data/MTCNN_model/RNet_landmark/RNet',
'../data/MTCNN_model/ONet_landmark/ONet'
]
epoch = [18, 14, 16]
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
RNet = Detector(R_Net, 24, 1, model_path[1])
detectors[1] = RNet
ONet = Detector(O_Net, 48, 1, model_path[2])
detectors[2] = ONet
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=min_face_size,
stride=stride,
threshold=thresh,
slide_window=slide_window)
video_capture = cv2.VideoCapture(0)
# video_capture.set(3, 340)
# video_capture.set(4, 480)
video_capture.set(3, 800)
video_capture.set(4, 800)
corpbbox = None
while True:
t1 = cv2.getTickCount()
ret, frame = video_capture.read()
if ret:
image = np.array(frame)
img_size = np.array(image.shape)[0:2]
boxes_c, landmarks = mtcnn_detector.detect(image)
# print(boxes_c.shape)
# print(boxes_c)
# print(img_size)
t2 = cv2.getTickCount()
t = (t2 - t1) / cv2.getTickFrequency()
fps = 1.0 / t
for i in range(boxes_c.shape[0]):
bbox = boxes_c[i, :4] #检测出的人脸区域，左上x，左上y，右下x，右下y
score = boxes_c[i, 4] #检测出人脸区域的得分
corpbbox = [
int(bbox[0]),
int(bbox[1]),
int(bbox[2]),
int(bbox[3])
]
x1 = np.maximum(int(bbox[0]) - 16, 0)
y1 = np.maximum(int(bbox[1]) - 16, 0)
x2 = np.minimum(int(bbox[2]) + 16, img_size[1])
y2 = np.minimum(int(bbox[3]) + 16, img_size[0])
crop_img = image[y1:y2, x1:x2]
scaled = misc.imresize(crop_img, (160, 160),
interp='bilinear')
img = load_image(scaled, False, False, 160)
img = np.reshape(img, (-1, 160, 160, 3))
feed_dict = {
images_placeholder: img,
phase_train_placeholder: False
}
embvecor = sess.run(embeddings, feed_dict=feed_dict)
embvecor = np.array(embvecor)
#利用人脸特征与数据库中所有人脸进行一一比较的方法
# tmp=np.sqrt(np.sum(np.square(embvecor-Database['emb'][0])))
# tmp_lable=Database['lab'][0]
# for j in range(len(Database['emb'])):
# t=np.sqrt(np.sum(np.square(embvecor-Database['emb'][j])))
# if t<tmp:
# tmp=t
# tmp_lable=Database['lab'][j]
# print(tmp)
#利用SVM对人脸特征进行分类
predictions = classifymodel.predict_proba(embvecor)
best_class_indices = np.argmax(predictions, axis=1)
tmp_lable = class_names[best_class_indices]
best_class_probabilities = predictions[
np.arange(len(best_class_indices)),
best_class_indices]
print(best_class_probabilities)
if best_class_probabilities < 0.4:
tmp_lable = "others"
cv2.rectangle(frame, (corpbbox[0], corpbbox[1]),
(corpbbox[2], corpbbox[3]), (255, 0, 0),
1)
cv2.putText(frame, '{0}'.format(tmp_lable),
(corpbbox[0], corpbbox[1] - 2),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255),
2)
cv2.putText(
frame, '{:.4f}'.format(t) + " " + '{:.3f}'.format(fps),
(10, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 0, 255),
2)
for i in range(landmarks.shape[0]):
for j in range(len(landmarks[i]) // 2):
cv2.circle(frame,
(int(landmarks[i][2 * j]),
int(int(landmarks[i][2 * j + 1]))), 2,
(0, 0, 255))
# time end
cv2.imshow("", frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
else:
print('device not find')
break
video_capture.release()
cv2.destroyAllWindows()
def t_net(prefix,
epoch,
batch_size,
test_mode="PNet",
thresh=(0.6, 0.6, 0.7),
min_face_size=25,
stride=2,
slide_window=False,
shuffle=False,
vis=False):
"""
:param prefix:
:param epoch:
:param batch_size:
:param test_mode:
:param thresh:
:param min_face_size:
:param stride:
:param slide_window:
:param shuffle:
:param vis:
:return:
"""
detectors = [None, None, None]
print("Test model: ", test_mode)
# PNet-echo
model_path = []
for x, y in zip(prefix, epoch):
model_path.append(os.path.join(x, test_mode.lower() + '.ckpt-%s' % y))
# model_path = ['%s/pnet.ckpt-%s' % (x, y) for x, y in zip(prefix, epoch)]
# load pnet model
if slide_window:
PNet = Detector(P_Net, 12, batch_size[0], model_path[0])
else:
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
# load rnet model
if test_mode in ["RNet", "ONet"]:
print("==================================", test_mode)
RNet = Detector(R_Net, 24, batch_size[1], model_path[1])
detectors[1] = RNet
# load onet model
if test_mode == "ONet":
print("==================================", test_mode)
ONet = Detector(O_Net, 48, batch_size[2], model_path[2])
detectors[2] = ONet
basedir = '../../DATA/'
# anno_file
filename = './wider_face_train_bbx_gt.txt'
# read anotation(type:dict), include 'images' and 'bboxes'
data = read_annotation(basedir, filename) # 12880张图片
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=min_face_size,
stride=stride,
threshold=thresh,
slide_window=slide_window)
# 注意是在“test”模式下
# imdb = IMDB("wider", image_set, root_path, dataset_path, 'test')
# gt_imdb = imdb.gt_imdb()
print('load test data')
test_data = TestLoader(data['images'])
print('finish loading')
# list
print('start detecting....')
detections, _ = mtcnn_detector.detect_face(test_data)
print('finish detecting ')
save_net = 'RNet'
if test_mode == "PNet":
save_net = "RNet"
elif test_mode == "RNet":
save_net = "ONet"
# save detect result
save_path = os.path.join(data_dir, save_net)
print('save_path is :')
print(save_path)
if not os.path.exists(save_path):
os.mkdir(save_path)
save_file = os.path.join(save_path, "detections.pkl")
with open(save_file, 'wb') as f:
pickle.dump(detections, f, 1)
print("%s测试完成开始OHEM" % image_size)
save_hard_example(image_size, data, save_path)
def RTrecognization(facenet_model_path,SVCpath,database_path):
#facenet_model_path为facenet模型路径
#SVCpath为SVM分类模型路径
#database_path为人脸库数据
with tf.Graph().as_default():
with tf.Session() as sess:
# Load the model
print('Loading feature extraction model')
facenet.load_model(facenet_model_path)
with open(SVCpath, 'rb') as infile:
(classifymodel, class_names) = pickle.load(infile)
print('Loaded classifier model from file "%s"' % SVCpath)
# 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]
Database=np.load(database_path)
"""
model_folder : string
path for the models
训练好的模型路径
minsize : float number
minimal face to detect
threshold : float number
detect threshold for 3 stages
threshold参数是一个包含3个值的列表，这3个值在算法的3个stage中将分别用到，
可以看到这3个threshold值是递增的，是因为在3个stage中对一个bbox是否是人脸的置信度要求越来越高。
factor: float number
scale factor for image pyramid
factor表示和图像金字塔相关的一个参数，表示图像金字塔的每相邻两层之间的倍数关系是factor。
num_worker: int number
number of processes we use for first stage
accurate_landmark: bool
use accurate landmark localization or not
"""
test_mode = "onet"
thresh = [0.9, 0.6, 0.7]
min_face_size = 24
stride = 2
slide_window = False
shuffle = False
#vis = True
detectors = [None, None, None]
prefix = ['../data/MTCNN_model/PNet_landmark/PNet', '../data/MTCNN_model/RNet_landmark/RNet',
'../data/MTCNN_model/ONet_landmark/ONet']
epoch = [18, 14, 16]
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
RNet = Detector(R_Net, 24, 1, model_path[1])
detectors[1] = RNet
ONet = Detector(O_Net, 48, 1, model_path[2])
detectors[2] = ONet
mtcnn_detector = MtcnnDetector(detectors=detectors, min_face_size=min_face_size,
stride=stride, threshold=thresh, slide_window=slide_window)
video_capture = cv2.VideoCapture(0)
# video_capture.set(3, 340)
# video_capture.set(4, 480)
video_capture.set(3, 800)
video_capture.set(4, 800)
corpbbox = None
while True:
t1 = cv2.getTickCount()
ret, frame = video_capture.read()
if ret:
image = np.array(frame)
img_size=np.array(image.shape)[0:2]
boxes_c,landmarks = mtcnn_detector.detect(image)
# print(boxes_c.shape)
# print(boxes_c)
# print(img_size)
t2 = cv2.getTickCount()
t = (t2 - t1) / cv2.getTickFrequency()
fps = 1.0 / t
for i in range(boxes_c.shape[0]):
bbox = boxes_c[i, :4]#检测出的人脸区域，左上x，左上y，右下x，右下y
score = boxes_c[i, 4]#检测出人脸区域的得分
corpbbox = [int(bbox[0]), int(bbox[1]), int(bbox[2]), int(bbox[3])]
x1=np.maximum(int(bbox[0])-16,0)
y1=np.maximum(int(bbox[1])-16,0)
x2=np.minimum( int(bbox[2])+16,img_size[1])
y2=np.minimum( int(bbox[3])+16,img_size[0])
crop_img=image[y1:y2,x1:x2]
scaled=misc.imresize(crop_img,(160,160),interp='bilinear')
img=load_image(scaled,False, False,160)
img=np.reshape(img,(-1,160,160,3))
feed_dict = { images_placeholder:img, phase_train_placeholder:False }
embvecor=sess.run(embeddings, feed_dict=feed_dict)
embvecor=np.array(embvecor)
#利用人脸特征与数据库中所有人脸进行一一比较的方法
# tmp=np.sqrt(np.sum(np.square(embvecor-Database['emb'][0])))
# tmp_lable=Database['lab'][0]
# for j in range(len(Database['emb'])):
# t=np.sqrt(np.sum(np.square(embvecor-Database['emb'][j])))
# if t<tmp:
# tmp=t
# tmp_lable=Database['lab'][j]
# print(tmp)
# 利用SVM对人脸特征进行分类
# 通过输入的图片的编码，通过此分类器预测模型的名称
# 得到的结果是对于每张图片，都进行预测，得出可能是某个人物的可能性
predictions = classifymodel.predict_proba(embvecor)
# 返回每行最大值的索引,也就是返回这张图片对应的人物的可能性最大的姓名的索引
best_class_indices = np.argmax(predictions, axis=1)
tmp_lable=class_names[best_class_indices]
# 行索引，加列索引，就得到了所有图片预测的可能性
best_class_probabilities = predictions[np.arange(len(best_class_indices)), best_class_indices]
print(best_class_probabilities)
if best_class_probabilities<0.4:
tmp_lable="unknown"
cv2.rectangle(frame, (corpbbox[0], corpbbox[1]),
(corpbbox[2], corpbbox[3]), (255, 0, 0), 1)
cv2.putText(frame, '{0}'.format(tmp_lable), (corpbbox[0], corpbbox[1] - 2), cv2.FONT_HERSHEY_SIMPLEX, 0.5,
(0, 0, 255), 2)
cv2.putText(frame, '{:.4f}'.format(t) + " " + '{:.3f}'.format(fps), (10, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.5,
(255, 0, 255), 2)
for i in range(landmarks.shape[0]):
for j in range(len(landmarks[i])//2):
cv2.circle(frame, (int(landmarks[i][2*j]),int(int(landmarks[i][2*j+1]))), 2, (0,0,255))
# time end
cv2.imshow("", frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
else:
print('device not find')
break
video_capture.release()
cv2.destroyAllWindows()
detectors = [None, None, None]
prefix = ['../data/MTCNN_model/PNet/model', '../data/MTCNN_model/RNet/model', '../data/MTCNN_model/ONet/model']
epoch = [30, 22, 22]
batch_size = [2048, 256, 16]
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
if slide_window:
PNet = Detector(P_Net, 12, batch_size[0], model_path[0])
else:
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
RNet = Detector(R_Net, 24, batch_size[1], model_path[1])
detectors[1] = RNet
mtcnn_detector = MtcnnDetector(detectors=detectors, min_face_size=min_face_size,
stride=stride, threshold=thresh, slide_window=slide_window)
data, num = tools.get_val(label_path)
f = open('../data/val_rnet.txt', 'w')
print('total_images = ' + str(num))
for id in range(num):
mean_iou = 0
im = cv2.imread(data['images'][id])
# cv2.imshow('test', im)
# cv2.waitKey(0)
print im.shape
labels = data['bboxes'][id]
_, all_boxes, _ = mtcnn_detector.detect_pnet(im)
if all_boxes is None:
f.write('%s : num_boxes = %s ; mean_iou = %s ; accuracy = %s\n' % (data['images'][id], 0, 0, 0))
print(data['images'][id] + ' : No face after PNet!')
def t_net(prefix, epoch,batch_size, img_saved_dir,anno_file,gen_anno_file,gen_imgs_dir,data_set_name,ignore_det=False,test_mode="PNet",thresh=[0.6, 0.6, 0.7], min_face_size=25,\
stride=2):
slide_window = False
detectors = [None, None, None]
print("Test model: ", test_mode)
#PNet-echo
print("epoch num ", epoch[0])
''' #for Pnet test
epoch_num = epoch[0]
epoch_c = np.arange(2,epoch_num,2)
prefix_c = []
prefix = prefix[0]
[prefix_c.append(prefix) for i in range(len(epoch_c))]
'''
print("prefixs is ", prefix)
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
#print("after zip model_path is ",model_path)
#model_path[0] = prefix + '-'+str(epoch_num) #for Pnet test
print("model_path 0 is ", model_path[0])
# load pnet model
if slide_window:
PNet = Detector(P_Net, 12, batch_size[0], model_path[0])
else:
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
# load rnet model
if test_mode in ["RNet", "ONet"]:
print("==================================", test_mode)
RNet = Detector(R_Net, 24, batch_size[1], model_path[1])
detectors[1] = RNet
# load onet model
if test_mode == "ONet":
print("==================================", test_mode)
ONet = Detector(O_Net, 48, batch_size[2], model_path[2])
detectors[2] = ONet
#read annatation(type:dict)
#img_box_dic = read_annotation(img_saved_dir,anno_file)
img_box_dic = rd_anotation(img_saved_dir, anno_file, data_set_name)
print("gen_hardexample threshold ", thresh)
if not ignore_det:
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=min_face_size,
stride=stride,
threshold=thresh)
print("==================================")
# 注意是在“test”模式下
# imdb = IMDB("wider", image_set, root_path, dataset_path, 'test')
# gt_imdb = imdb.gt_imdb()
test_data = TestLoader(img_box_dic['images'])
#list
if not ignore_det:
detections, _ = mtcnn_detector.detect_face(test_data)
if test_mode == "PNet":
save_net = "RNet"
save_path = '24/RNet'
elif test_mode == "RNet":
save_net = "ONet"
save_path = "48/ONet"
#save detect result
#save_path = os.path.join(data_dir, save_net)
print("save path is", save_path)
if not os.path.exists(save_path):
os.mkdir(save_path)
save_file = os.path.join(save_path, "detections.pkl")
if not ignore_det:
with open(save_file, 'wb') as f:
pickle.dump(detections, f, 1)
f.close()
print("%s Test is Over and begin OHEM" % image_size)
save_hard_example(gen_anno_file, gen_imgs_dir, img_box_dic, save_path,
test_mode)
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
# load rnet model
if test_mode in ["RNet", "ONet"]:
RNet = Detector(R_Net, 24, batch_size[1], model_path[1])
detectors[1] = RNet
# load onet model
if test_mode == "ONet":
ONet = Detector(O_Net, 48, batch_size[2], model_path[2])
detectors[2] = ONet
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=min_face_size,
stride=stride,
threshold=thresh,
slide_window=slide_window)
image_info = get_image_info(anno_file)
current_event = ''
save_path = ''
idx = 0
for item in image_info:
idx += 1
image_file_name = os.path.join(data_dir, item[0], item[1])
if current_event != item[0]:
current_event = item[0]
save_path = os.path.join(output_file, item[0])
def t_net(
prefix,
epoch,
batch_size,
test_mode="PNet",
thresh=[0.6, 0.6, 0.7],
min_face_size=25, # prefix保存模型文件路径
stride=2,
slide_window=False,
shuffle=False,
vis=False):
detectors = [None, None, None]
print("Test model: ", test_mode)
#PNet-echo
model_path = [
'%s-%s' % (x, y) for x, y in zip(prefix, epoch)
] # model_path == <class 'list'>: ['../data/MTCNN_model/PNet_landmark/PNet-16', '../data/MTCNN_model/RNet_landmark/RNet-6', '../data/MTCNN_model/ONet/ONet-22']
if slide_window:
PNet = Detector(P_Net, 12, batch_size[0], model_path[0])
else:
PNet = FcnDetector(
P_Net, model_path[0]
) # '../data/MTCNN_model/PNet_landmark/PNet-16'， 生成全连接detection的检测对象P_Net
detectors[0] = PNet # 将PNet对象放入检测器的第1个位
# load rnet model
if test_mode in ["RNet", "ONet"]:
print("==================================", test_mode)
RNet = Detector(R_Net, 24, batch_size[1], model_path[1])
detectors[1] = RNet
# load onet model
if test_mode == "ONet":
print("==================================", test_mode)
ONet = Detector(O_Net, 48, batch_size[2], model_path[2])
detectors[2] = ONet
basedir = '.'
filename = './wider_face_train_bbx_gt.txt' # 获取检测框的ground truth值
data = read_annotation(
basedir, filename
) # 读pic的文件名，和box的ground truth值，data['images']==all image pathes
# data['bboxes'] =all image bboxes
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=min_face_size,
stride=stride,
threshold=thresh,
slide_window=slide_window)
print("==================================")
test_data = TestLoader(
data['images']
) # 生成输入图片的管理对象test_data， # 注意是在“test”模式下， imdb = IMDB("wider", image_set, root_path, dataset_path, 'test')， gt_imdb = imdb.gt_imdb()
detections, _ = mtcnn_detector.detect_face(
test_data) # 从test_data输入人脸pixel,返回detection和cls
save_net = 'RNet'
if test_mode == "PNet":
save_net = "RNet"
elif test_mode == "RNet":
save_net = "ONet"
#save detect result
save_path = os.path.join(data_dir, save_net) # save_path == “24 / Rnet”
print(save_path)
if not os.path.exists(save_path):
os.mkdir(save_path)
save_file = os.path.join(save_path, "detections.pkl")
with open(save_file, 'wb') as f: # save_file == detections.pkl
pickle.dump(detections, f, 1) # 将detection结果写入文件
print("%s测试完成开始OHEM" % image_size)
save_hard_example(image_size, data,
save_path) # data，读pic的文件名，和box的ground truth值，
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
# load rnet model
if test_mode in ["RNet", "ONet"]:
RNet = Detector(R_Net, 24, batch_size[1], model_path[1])
detectors[1] = RNet
# load onet model
if test_mode == "ONet":
ONet = Detector(O_Net, 48, batch_size[2], model_path[2])
detectors[2] = ONet
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=min_face_size,
stride=stride,
threshold=thresh,
slide_window=slide_window)
def extract_face(avideo_path, num_share, total_share):
# set_trace(term_size=(80, 24))
# print('run task %s (%s)...' % (avideo_path, os.getpid()))
# if slide_window:
# PNet = Detector(P_Net, 12, batch_size[0], model_path[0])
# else:
# PNet = FcnDetector(P_Net, model_path[0])
# detectors[0] = PNet
# # load rnet model
# if test_mode in ["RNet", "ONet"]:
PNet = Detector(P_Net, 12, batch_size[0], model_path[0])
else:
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
# load rnet model
if test_mode in ["RNet", "ONet"]:
RNet = Detector(R_Net, 24, batch_size[1], model_path[1])
detectors[1] = RNet
# load onet model
if test_mode == "ONet":
ONet = Detector(O_Net, 48, batch_size[2], model_path[2])
detectors[2] = ONet
mtcnn_detector = MtcnnDetector(detectors=detectors, min_face_size=min_face_size,
stride=stride, threshold=thresh, slide_window=slide_window)
gt_imdb = []
#gt_imdb.append("35_Basketball_Basketball_35_515.jpg")
#imdb_ = dict()"
#imdb_['image'] = im_path
#imdb_['label'] = 5
path = "lala"
for item in os.listdir(path):
gt_imdb.append(os.path.join(path,item))
test_data = TestLoader(gt_imdb)
all_boxes,landmarks = mtcnn_detector.detect_face(test_data)
count = 0
for imagepath in gt_imdb:
print imagepath
image = cv2.imread(imagepath)
for bbox in all_boxes[count]:
prefix = [
'data/MTCNN_model/PNet_landmark/PNet',
'data/MTCNN_model/RNet_landmark/RNet',
'data/MTCNN_model/ONet_landmark/ONet'
]
epoch = [18, 14, 16]
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
RNet = Detector(R_Net, 24, 1, model_path[1])
detectors[1] = RNet
ONet = Detector(O_Net, 48, 1, model_path[2])
detectors[2] = ONet
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=min_face_size,
stride=stride,
threshold=thresh,
slide_window=slide_window)
camera = cv2.VideoCapture(1)
name = 'test'
count = 0
path = os.getcwd() + '/data-face/' + name
if not os.path.exists(path):
os.makedirs(path)
while True:
_, frame = camera.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
boxes_c, _ = mtcnn_detector.detect(frame)
for i in range(boxes_c.shape[0]):
#PNet = FcnDetector(P_Net_new, model_path[0])
PNet = FcnDetector(P_Net, model_path[0], COLOR_GRAY)
detectors[0] = PNet
# load rnet model
if test_mode in ["RNet", "ONet"]:
RNet = Detector(R_Net, 24, batch_size[1], model_path[1], COLOR_GRAY)
detectors[1] = RNet
# load onet model
if test_mode == "ONet":
ONet = Detector(O_Net_new, 48, batch_size[2], model_path[2], COLOR_GRAY)
detectors[2] = ONet
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=min_face_size,
stride=stride,
threshold=thresh,
slide_window=slide_window,
COLO_GRA=COLOR_GRAY)
gt_imdb = []
#gt_imdb.append("35_Basketball_Basketball_35_515.jpg")
#imdb_ = dict()"
#imdb_['image'] = im_path
#imdb_['label'] = 5
path = "X:\\deeplearn\\mtcnn\\MTCNN-Tensorflow-master_change\\test\\lala"
for item in os.listdir(path):
if item.find('.png') == -1 and item.find('.bmp') == -1 and item.find(
'.jpg') == -1:
continue
gt_imdb.append(os.path.join(path, item))
test_data = TestLoader(gt_imdb,
batch_size=1,
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
# load rnet model
if test_mode in ["RNet", "ONet"]:
RNet = Detector(R_Net, 24, batch_size[1], model_path[1])
detectors[1] = RNet
# load onet model
if test_mode == "ONet":
ONet = Detector(O_Net, 48, batch_size[2], model_path[2])
detectors[2] = ONet
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=min_face_size,
stride=stride,
threshold=thresh,
slide_window=slide_window)
imdb = get_imdb_fddb(data_dir)
nfold = len(imdb)
for i in xrange(nfold):
image_names = imdb[i]
print image_names
dets_file_name = os.path.join(out_dir,
'FDDB-det-fold-%02d.txt' % (i + 1))
fid = open(dets_file_name, 'w')
sys.stdout.write('%s ' % (i + 1))
image_names_abs = [
os.path.join(data_dir, image_name + '.jpg')
for image_name in image_names
PNet = Detector(P_Net, 12, batch_size[0], model_path[0])
else:
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
# load rnet model
if test_mode in ["RNet", "ONet"]:
RNet = Detector(R_Net, 24, batch_size[1], model_path[1])
detectors[1] = RNet
# load onet model
if test_mode == "ONet":
ONet = Detector(O_Net, 48, batch_size[2], model_path[2])
detectors[2] = ONet
mtcnn_detector = MtcnnDetector(detectors=detectors, min_face_size=min_face_size,
stride=stride, threshold=thresh, slide_window=slide_window)
imdb = get_imdb_fddb(data_dir)
nfold = len(imdb)
for i in xrange(nfold):
image_names = imdb[i]
print image_names
dets_file_name = os.path.join(out_dir, 'FDDB-det-fold-%02d.txt' % (i + 1))
fid = open(dets_file_name,'w')
sys.stdout.write('%s ' % (i + 1))
image_names_abs = [os.path.join(data_dir,'originalPics',image_name+'.jpg') for image_name in image_names]
test_data = TestLoader(image_names_abs)
all_boxes,_ = mtcnn_detector.detect_face(test_data, vis=vis)
def t_net(prefix,
epoch,
batch_size,
test_mode='PNet',
thresh=[0.6, 0.6, 0.6],
min_face_size=25,
stride=2,
slide_window=False,
shuffle=False,
vis=False):
"""
:param prefix: 模型名字的前缀
:param epoch:上一个模型的训练次数
:param batch_size:用在预测中的批的尺寸
:param test_mode:测试模式
:param thresh:阈值
:param min_face_size:最小检测人脸大小
:param stride:
:param slide_window:是否在pnet中应用了sliding window
:param shuffle:
:param vis:
:return:
"""
detectors = [None, None, None]
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
if slide_window:
PNet = Detector(P_Net, 12, batch_size[0], model_path[0])
else:
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
if test_mode in ["RNet", "ONet"]:
RNet = Detector(R_Net, 24, batch_size[1], model_path[1])
detectors[1] = RNet
basedir = '.'
# 注解文件
filename = './wider_face_train_bbx_gt.txt'
data = read_annotation(basedir, filename)
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=min_face_size,
stride=stride,
threshold=thresh,
slide_window=slide_window)
test_data = TestLoader(data['images'])
detections, _ = mtcnn_detector.detect_face(test_data)
save_net = 'RNet'
if test_mode == "PNet":
save_net = "RNet"
elif test_mode == "RNet":
save_net = "ONet"
# 保存探测结果
save_path = os.path.join(data_dir, save_net)
if not os.path.exists(save_path):
os.mkdir(save_path)
save_file = os.path.join(save_path, "detections.pkl")
with open(save_file, 'wb') as f:
pickle.dump(detections, f, 1)
print("%s测试完成开始OHEM" % image_size)
save_hard_example(image_size, data, save_path)
def t_net(data_dir,
prefix=[
'./modelfiles/PNet/PNet', './modelfiles/RNet/RNet',
'./modelfiles/ONet/ONet'
],
epoch=[18, 14, 16],
batch_size=[2048, 256, 16],
test_mode="PNet",
thresh=[0.6, 0.6, 0.7],
min_face_size=25,
stride=2,
slide_window=False,
shuffle=False,
vis=False):
detectors = [None, None, None]
print("Test model: ", test_mode)
#PNet-echo
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
print(model_path[0])
# load pnet model
if slide_window:
PNet = Detector(P_Net, 12, batch_size[0], model_path[0])
else:
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
# load rnet model
if test_mode in ["RNet", "ONet"]:
print("==================================", test_mode)
RNet = Detector(R_Net, 24, batch_size[1], model_path[1])
detectors[1] = RNet
# load onet model
if test_mode == "ONet":
print("==================================", test_mode)
ONet = Detector(O_Net, 48, batch_size[2], model_path[2])
detectors[2] = ONet
# anno_file
# read anotation(type:dict), include 'images' and 'bboxes'
data = read_annotation(data_dir,
'./prepare_data/wider_face_train_bbx_gt.txt')
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=min_face_size,
stride=stride,
threshold=thresh,
slide_window=slide_window)
print("==================================")
print('load test data')
test_data = TestLoader(data['images'])
print('finish loading')
save_net = 'RNet'
if test_mode == "PNet":
save_net = "RNet"
image_size = 24
elif test_mode == "RNet":
save_net = "ONet"
image_size = 48
# save detect result
save_path = os.path.join(data_dir, save_net)
print('save_path is :')
print(save_path)
if not os.path.exists(save_path):
os.mkdir(save_path)
save_file = os.path.join(save_path, "detections.pkl")
print('start detecting....')
if not os.path.exists(save_file):
detections, _ = mtcnn_detector.detect_face(test_data)
with open(save_file, 'wb') as f:
pickle.dump(detections, f, 1)
print('finish detecting ')
print("%s测试完成开始OHEM" % image_size)
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
# load R-net model
if test_mode in ['RNet', 'ONet']:
RNet = Detector(R_Net, 24, batch_size[1], model_path[1])
detectors[1] = RNet
# load O-net model
if test_mode == 'ONet':
ONet = Detector(O_Net, 48, batch_size[2], model_path[2])
detectors[2] = ONet
mtcnn_detector = MtcnnDetector(detectors=detectors,
min_face_size=min_face_size,
stride=stride,
threshold=thresh,
slide_window=slide_window)
path = os.path.join(os.pardir, 'data/test/lfpw_testImage')
gt_imdb = [os.path.join(path, item) for item in os.listdir(path)]
test_data = TestLoader(gt_imdb)
# boxes, landmarks = mtcnn_detector.detect_face(test_data)
out_dir = os.path.dirname(gt_imdb[0]) + '_out'
if not os.path.exists(out_dir):
os.makedirs(out_dir)
for path in gt_imdb:
print(path)
stride = 2
slide_window = False
shuffle = False
#vis = True
detectors = [None, None, None]
prefix = ['../data/MTCNN_model/PNet_landmark/PNet', '../data/MTCNN_model/RNet_landmark/RNet', '../data/MTCNN_model/ONet_landmark/ONet']
epoch = [18, 14, 16]
model_path = ['%s-%s' % (x, y) for x, y in zip(prefix, epoch)]
PNet = FcnDetector(P_Net, model_path[0])
detectors[0] = PNet
RNet = Detector(R_Net, 24, 1, model_path[1])
detectors[1] = RNet
ONet = Detector(O_Net, 48, 1, model_path[2])
detectors[2] = ONet
videopath = "./video_test.avi"
mtcnn_detector = MtcnnDetector(detectors=detectors, min_face_size=min_face_size,
stride=stride, threshold=thresh, slide_window=slide_window)
video_capture = cv2.VideoCapture(videopath)
video_capture.set(3, 340)
video_capture.set(4, 480)
corpbbox = None
while True:
# fps = video_capture.get(cv2.CAP_PROP_FPS)
t1 = cv2.getTickCount()
ret, frame = video_capture.read()
if ret:
image = np.array(frame)
boxes_c,landmarks = mtcnn_detector.detect(image)
print landmarks.shape
t2 = cv2.getTickCount()
