def run():
parser = argparse.ArgumentParser(description='Choose the model')
parser.add_argument('-model', default="HOG")
args = parser.parse_args()
cuda = torch.device('cuda')
poser = MorphRotateCombinePoser256Param6(
morph_module_spec=FaceMorpherSpec(),
morph_module_file_name="data/face_morpher.pt",
rotate_module_spec=TwoAlgoFaceRotatorSpec(),
rotate_module_file_name="data/two_algo_face_rotator.pt",
combine_module_spec=CombinerSpec(),
combine_module_file_name="data/combiner.pt",
device=cuda)
if args.model == "HOG":
face_detector = dlib.get_frontal_face_detector()
else:
cnn_face_detection_model = face_recognition_models.cnn_face_detector_model_location(
)
face_detector = dlib.cnn_face_detection_model_v1(
cnn_face_detection_model)
landmark_locator = dlib.shape_predictor(
"data/shape_predictor_68_face_landmarks.dat")
video_capture = cv2.VideoCapture(0)
master = Tk()
PuppeteerApp(master, poser, face_detector, landmark_locator, video_capture,
cuda, args.model)
master.mainloop()
def get_age(self, img):
cnn_face_detection_model = face_recognition_models.cnn_face_detector_model_location(
)
detector = dlib.cnn_face_detection_model_v1(cnn_face_detection_model)
input_img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
detected = [r.rect for r in detector(input_img, 1)]
return zip([
_trim_css_to_bounds(_rect_to_css(face), input_img.shape)
for face in detected
], self.get_age_from_faces(img, detected))
def __init__(self, gpu):
cuda.set_device(gpu)
face_detector = dlib.get_frontal_face_detector()
predictor_68_point_model = face_recognition_models.pose_predictor_model_location(
)
pose_predictor_68_point = dlib.shape_predictor(
predictor_68_point_model)
cnn_face_detection_model = face_recognition_models.cnn_face_detector_model_location(
)
self.cnn_face_detector = dlib.cnn_face_detection_model_v1(
cnn_face_detection_model)
face_recognition_model = face_recognition_models.face_recognition_model_location(
)
face_encoder = dlib.face_recognition_model_v1(face_recognition_model)
"pip install git+https://github.com/ageitgey/face_recognition_models")
quit()
ImageFile.LOAD_TRUNCATED_IMAGES = True
face_detector = dlib.get_frontal_face_detector()
predictor_68_point_model = face_recognition_models.pose_predictor_model_location(
)
pose_predictor_68_point = dlib.shape_predictor(predictor_68_point_model)
predictor_5_point_model = face_recognition_models.pose_predictor_five_point_model_location(
)
pose_predictor_5_point = dlib.shape_predictor(predictor_5_point_model)
cnn_face_detection_model = face_recognition_models.cnn_face_detector_model_location(
)
cnn_face_detector = dlib.cnn_face_detection_model_v1(cnn_face_detection_model)
face_recognition_model = face_recognition_models.face_recognition_model_location(
)
face_encoder = dlib.face_recognition_model_v1(face_recognition_model)
def _rect_to_css(rect):
"""
Convert a dlib 'rect' object to a plain tuple in (top, right, bottom, left) order
:param rect: a dlib 'rect' object
:return: a plain tuple representation of the rect in (top, right, bottom, left) order
"""
return rect.top(), rect.right(), rect.bottom(), rect.left()
def set_model_path(self):
""" Model path handled by face_recognition_models """
model_path = face_recognition_models.cnn_face_detector_model_location()
logger.debug("Loading model: '%s'", model_path)
return model_path
class FaceFrameAnnotator(FrameAnnotator):
name = 'face'
cfd = dlib.cnn_face_detection_model_v1(
frm.cnn_face_detector_model_location())
hfd = dlib.get_frontal_face_detector()
def __init__(self):
#prototxt = "/home/taylor/face-test/resnet50_256.prototxt"
#caffemodel = "/home/taylor/face-test/resnet50_256.caffemodel"
prototxt = "/home/taylor/face-test/caffe_model/resnet50_scratch_caffe/resnet50_scratch.prototxt"
caffemodel = "/home/taylor/face-test/caffe_model/resnet50_scratch_caffe/resnet50_scratch.caffemodel"
caffe.set_device(0)
caffe.set_mode_gpu()
self.net = caffe.Net(prototxt, 1, weights=caffemodel)
self.net.blobs['data'].reshape(1, 3, 224, 224)
self.transformer = caffe.io.Transformer(
{'data': self.net.blobs['data'].data.shape})
self.transformer.set_transpose('data', (2, 0, 1))
self.transformer.set_mean('data',
np.array([91.4953, 103.8827, 131.0912]))
self.transformer.set_raw_scale('data', 255)
def process_next(self, img, foutput):
img2 = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
faces, hog, conf, hscore = self.detect_faces(img2)
embed = self.face_features(img, faces)
#embed = fr.face_encodings(img, faces, num_jitters=10)
#lndmk = fr.face_landmarks(img, faces)
#print([round(x, 4) for x in em.tolist()])
#print(type([round(x, 4) for x in em.tolist()]))
output = []
for face, co, em in zip(faces, conf, embed):
overlap, score = cnn_to_hog_conf(face, hog, hscore)
output.append({
'box': {
'top': face[0],
'bottom': face[2],
'left': face[3],
'right': face[1]
},
'cnn_score': co,
'hog_overlap': overlap,
'hog_score': score,
'embed': [round(x, 4) for x in em.tolist()]
})
return (output)
def face_features(self, img, faces):
X = []
for face in faces:
c = [int((face[3] + face[1]) / 2), int((face[0] + face[2]) / 2)]
h = int((face[2] - face[0]) / 2 * 1.3)
w = int((face[1] - face[3]) / 2 * 1.3)
d = [c[1] - h, c[1] + h, c[0] - w, c[0] + w]
d[0] = max(0, d[0])
d[2] = max(0, d[2])
d[1] = min(img.shape[0], d[1])
d[3] = min(img.shape[1], d[3])
crop_img = img[d[0]:d[1], d[2]:d[3], :]
img_scaled = skimage.transform.resize(crop_img, (224, 224),
mode='constant')
self.net.blobs['data'].data[...] = self.transformer.preprocess(
'data', img_scaled)
out = self.net.forward()
#X.append(self.net.blobs['feat_extract'].data[0].flatten())
X.append(self.net.blobs['pool5/7x7_s1'].data[0].flatten())
return X
def detect_faces(self, img):
dets = self.cfd(img, 1)
rect_cnn = [_trim_bounds(f.rect, img.shape) for f in dets]
conf = [f.confidence for f in dets]
hog_triple = self.hfd.run(img, 1)
dets = hog_triple[0]
hscore = hog_triple[1]
rect_hog = [_trim_bounds(f, img.shape) for f in dets]
return rect_cnn, rect_hog, conf, hscore
import face_recognition_models
except:
print("Please install `face_recognition_models` with this command before using `face_recognition`:")
print()
print("pip install git+https://github.com/ageitgey/face_recognition_models")
quit()
face_detector = dlib.get_frontal_face_detector()
predictor_68_point_model = face_recognition_models.pose_predictor_model_location()
pose_predictor_68_point = dlib.shape_predictor(predictor_68_point_model)
predictor_5_point_model = face_recognition_models.pose_predictor_five_point_model_location()
pose_predictor_5_point = dlib.shape_predictor(predictor_5_point_model)
cnn_face_detection_model = face_recognition_models.cnn_face_detector_model_location()
cnn_face_detector = dlib.cnn_face_detection_model_v1(cnn_face_detection_model)
face_recognition_model = face_recognition_models.face_recognition_model_location()
face_encoder = dlib.face_recognition_model_v1(face_recognition_model)
def _rect_to_css(rect):
"""
Convert a dlib 'rect' object to a plain tuple in (top, right, bottom, left) order
:param rect: a dlib 'rect' object
:return: a plain tuple representation of the rect in (top, right, bottom, left) order
"""
return rect.top(), rect.right(), rect.bottom(), rect.left()
def set_model_path(self):
""" Model path handled by face_recognition_models """
return face_recognition_models.cnn_face_detector_model_location()
import scipy.misc
import dlib
import numpy as np
import face_recognition_models as frm
face_detector = dlib.get_frontal_face_detector()
predictor_68_point_model = frm.pose_predictor_model_location()
pose_predictor_68_point = dlib.shape_predictor(predictor_68_point_model)
predictor_5_point_model = frm.pose_predictor_five_point_model_location()
pose_predictor_5_point = dlib.shape_predictor(predictor_5_point_model)
cnn_face_detection_model = frm.cnn_face_detector_model_location()
cnn_face_detector = dlib.cnn_face_detection_model_v1(cnn_face_detection_model)
face_recognition_model = frm.face_recognition_model_location()
face_encoder = dlib.face_recognition_model_v1(face_recognition_model)
def rect_to_css(rect):
return rect.top(), rect.right(), rect.bottom(), rect.left()
def css_to_rect(css):
return dlib.rectangle(css[3], css[0], css[1], css[2])
def trim_css_to_bounds(css, image_shape):
return max(css[0],
0), min(css[1],
import dlib
import numpy as np
import face_recognition_models as models
# import models
# ====================================================================================================================
# models에 있는 모델 변수 적용
face_detector = dlib.get_frontal_face_detector()
point_68_predictor = models.pose_predictor_model_location()
point_68_pose = dlib.shape_predictor(point_68_predictor)
point_5_predictor = models.pose_predictor_five_point_model_location()
point_5_pose = dlib.shape_predictor(point_5_predictor)
face_detection_model = models.cnn_face_detector_model_location()
face_detector_tool = dlib.cnn_face_detection_model_v1(face_detection_model)
face_recognition_model = models.face_recognition_model_location()
face_encoder = dlib.face_recognition_model_v1(face_recognition_model)
# ====================================================================================================================
# dlib 'rect' 객체를 top, right, bottom, left 순서로 변환
# param rect : dlib 'rect' 오브젝트
# return : tuple (top, right, bottom, left)
def _rect_to_css(rect):
return rect.top(), rect.right(), rect.bottom(), rect.left()
# tuple (top, right, bottom, left) -> dlib 'rect' 객체 변환
def get_age(output_dir, img_dir, faces, resume=None):
cfg.freeze()
if output_dir is not None:
if img_dir is None:
raise ValueError(
"=> --img_dir argument is required if --output_dir is used")
output_dir = Path(output_dir)
output_dir.mkdir(parents=True, exist_ok=True)
# create model
print("=> creating model '{}'".format(cfg.MODEL.ARCH))
model = get_model(model_name=cfg.MODEL.ARCH, pretrained=None)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = model.to(device)
# load checkpoint
resume_path = resume
if resume_path is None:
resume_path = Path(__file__).resolve().parent.joinpath(
"misc", "epoch044_0.02343_3.9984.pth")
if not resume_path.is_file():
print(
f"=> model path is not set; start downloading trained model to {resume_path}"
)
url = "https://github.com/yu4u/age-estimation-pytorch/releases/download/v1.0/epoch044_0.02343_3.9984.pth"
urllib.request.urlretrieve(url, str(resume_path))
print("=> download finished")
if Path(resume_path).is_file():
print("=> loading checkpoint '{}'".format(resume_path))
checkpoint = torch.load(resume_path, map_location="cpu")
model.load_state_dict(checkpoint['state_dict'])
print("=> loaded checkpoint '{}'".format(resume_path))
else:
raise ValueError("=> no checkpoint found at '{}'".format(resume_path))
if device == "cuda":
cudnn.benchmark = True
model.eval()
margin = args.margin
img_dir = img_dir
cnn_face_detection_model = face_recognition_models.cnn_face_detector_model_location(
)
detector = dlib.cnn_face_detection_model_v1(cnn_face_detection_model)
img_size = cfg.MODEL.IMG_SIZE
image_generator = yield_images_from_dir(img_dir)
with torch.no_grad():
for img, name in image_generator:
input_img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img_h, img_w, _ = np.shape(input_img)
# detect faces using dlib detector
detected = [r.rect for r in detector(input_img, 1)]
faces = np.empty((len(detected), img_size, img_size, 3))
if len(detected) > 0:
for i, d in enumerate(detected):
x1, y1, x2, y2, w, h = d.left(), d.top(
), d.right() + 1, d.bottom() + 1, d.width(), d.height()
xw1 = max(int(x1 - margin * w), 0)
yw1 = max(int(y1 - margin * h), 0)
xw2 = min(int(x2 + margin * w), img_w - 1)
yw2 = min(int(y2 + margin * h), img_h - 1)
cv2.rectangle(img, (x1, y1), (x2, y2), (255, 255, 255), 2)
cv2.rectangle(img, (xw1, yw1), (xw2, yw2), (255, 0, 0), 2)
faces[i] = cv2.resize(img[yw1:yw2 + 1, xw1:xw2 + 1],
(img_size, img_size))
# predict ages
inputs = torch.from_numpy(
np.transpose(faces.astype(np.float32),
(0, 3, 1, 2))).to(device)
outputs = F.softmax(model(inputs), dim=-1).cpu().numpy()
ages = np.arange(0, 101)
predicted_ages = (outputs * ages).sum(axis=-1)
return zip(faces, predicted_ages)
