def detect_faces(args, img, min_face_size=MIN_FACE_SIZE, thresholds=THRESHOLDS,
nms_thresholds=NMS_THRESHOLDS):
pnet, rnet, onet = load_net(args, 'pnet'), load_net(args, 'rnet'), load_net(args, 'onet')
# STAGE 1
bounding_boxes = pnet_boxes(img, pnet, show_boxes=False)
# STAGE 2
bounding_boxes = rnet_boxes(img, rnet, bounding_boxes, show_boxes=False)
# STAGE 3
bounding_boxes, landmarks = onet_boxes(img, onet, bounding_boxes, show_boxes=True)
return bounding_boxes, landmarks
def onet_test(args, img_path):
img = load_img(img_path)
net = load_net(args, 'pnet')
output = net((transforms.ToTensor()(img.resize(
(12, 12), Image.BILINEAR))).unsqueeze(0))
print('prob:', output[0])
show_bboxes(img, [[(250 * t.item() + 250 * (i > 1))
for i, t in enumerate(output[1][0])]]).show()
def img_face_detect(args, img_path, th=[0.6, 0.7, 0.8]):
img = None
try:
print('===> loading the img...')
img = Image.open(img_path)
img = img.convert('RGB')
except Exception:
print('*** warning loading fail!')
return
img_tensor = transforms.ToTensor()(img).unsqueeze(0)
pnet, rnet, onet = load_net(args, 'pnet'), load_net(args,
'rnet'), load_net(
args, 'onet')
resize_ratio = 0.7071
det, box, _ = pnet(img_tensor)
det_faces = det.ge(th[0])
print(det)
def create_rnet_data(save_dir_name='R_net_dataset',
crop_size=24,
use_rnet=False):
def img2tensor(img):
from torchvision import transforms
pass
def get_name_from_path(img_path):
return osp.splitext(osp.split(img_path)[1])[0]
def make_dir(save_dir):
if not osp.exists(save_dir):
os.makedirs(save_dir)
def crop_img(img_np, crop_box, crop_size):
# print('img_np:{}, crop_box:{}'.format(img_np, crop_box))
# print('img_np.shape:{}'.format(img_np.shape))
crop_img_np = img_np[crop_box[1]:crop_box[3],
crop_box[0]:crop_box[2], :]
# print('crop_img_np size:{}'.format(crop_img_np))
crop_img = Image.fromarray(crop_img_np)
crop_img = crop_img.resize((crop_size, crop_size),
resample=PIL.Image.BILINEAR)
return crop_img
def limit_box(box):
new_box = [
min(max(0, int(box[i])), width if i % 2 == 0 else hight)
for i in range(4)
]
return new_box
def cal_offset(face, box):
offset = [
(face[0] - box[0]) / float(box[2] - box[0]),
(face[1] - box[1]) / float(box[3] - box[1]),
(face[2] - box[2]) / float(box[2] - box[0]),
(face[3] - box[3]) / float(box[3] - box[1]),
]
return offset
def cal_landmark_offset(box, ldmk):
if ldmk is None:
return []
else:
minx, miny = box[0], box[1]
w, h = box[2] - box[0], box[3] - box[1]
ldmk_offset = [
(ldmk[i] - [minx, miny][i % 2]) / float([w, h][i % 2])
for i in range(len(ldmk))
]
# print('box:{},ldmk:{},ldmk_offset:{}'.format(box, ldmk, ldmk_offset))
return ldmk_offset
def txt_to_write(path, label, offset, ldmk_offset):
s = ''
s += '{} '.format(path)
s += '{} '.format(label)
for i in offset:
s += '{} '.format(i)
for i in ldmk_offset:
s += '{} '.format(i)
s += '\n'
print(s)
return s
from train import load_net, config
from config import DEVICE
import torch
# args = config()
dataset_args = dataset_config()
pnet = load_net(dataset_args, net_name='pnet').to(torch.device('cpu'))
# dataset_args = dataset_config()
# [img_num*[absolute_img_path,[faces_num*4(which is x1,y1,w,h)]]]
cls_img_faces = create_pnet_data_txt_parser(
txt_path=dataset_args.class_data_txt_path,
img_dir=dataset_args.class_data_dir)
# [absolute_img_path,[x1,x2,y1,y2],(x,y)of[left_eye,right_eye,nose,mouse_left, mouse_right]]
ldmk_img_faces = landmark_dataset_txt_parser(
txt_path=dataset_args.landmark_data_txt_path,
img_dir=dataset_args.landmark_data_dir)
img_faces = ldmk_img_faces + cls_img_faces
# img_faces = cls_img_faces + ldmk_img_faces
output_path = osp.join(dataset_args.output_path, save_dir_name)
make_dir(output_path)
txt_path = osp.join(output_path, '{}.txt'.format(save_dir_name))
txt = open(txt_path, 'a')
for img_face in tqdm(img_faces):
# print('img_face:{}'.format(img_face))
img_path = img_face[0]
img_name = get_name_from_path(img_path)
save_dir = osp.join(output_path, img_name)
make_dir(save_dir)
faces = np.array(img_face[1])
# print('faces.ndim:{}'.format(faces.ndim))
if faces.ndim is 1:
faces = np.expand_dims(faces, 0)
faces[:, :] = faces[:, (0, 2, 1, 3)]
else:
faces[:, 2] += faces[:, 0]
faces[:, 3] += faces[:, 1]
# print('faces:{}'.format(faces))
ldmk = None if len(img_face) < 3 else [int(i) for i in img_face[2]]
img = load_img(img_path)
width, hight = img.size
# print('width:{}, hight:{}'.format(width, hight))
img_np = np.array(img)
# print('img_np:{}'.format(img_np))
bounding_boxes = pnet_boxes(img, pnet, show_boxes=1)
bounding_boxes = rnet_boxes(img, rnet, bounding_boxes)
if use_rnet:
rnet = load_net(args, net_name='rnet').to(torch.device('cpu'))
bounding_boxes = rnet_boxes(img, rnet, bounding_boxes)
# print('bounding_boxes:{}'.format(bounding_boxes[:, 4]))
# ioumax = 0.0
for id, box in enumerate(bounding_boxes, start=1):
# box[(4+1)float]
# print('box:{}'.format(box))
box = limit_box(box)
# print('box:{},faces:{}'.format(box, faces))
iou = IoU(box, faces)
iou_max = iou.max()
iou_index = iou.argmax()
closet_face = faces[iou_index]
# print('iou_max:{}, iou_index:{}'.format(iou_max, iou_index))
# ioumax = max(iou, iou_max)
img_box = crop_img(img_np=img_np,
crop_box=box,
crop_size=crop_size)
# img_box.show()
label = None
# [(0, 0.3), (0.4, 0.65), (0.65, 1.0)]
if iou <= 0.3:
label = 'n'
img_box_path = osp.join(save_dir,
'{}_{:.8f}.jpg'.format(id, iou_max))
img_box.save(img_box_path, format='jpeg')
txt.write(
txt_to_write(
osp.relpath(img_box_path,
osp.split(txt_path)[0]), label, [], []))
pass
elif 0.4 <= iou <= 0.65:
label = 'pf' if ldmk is None else 'l'
img_box_path = osp.join(save_dir,
'{}_{:.8f}.jpg'.format(id, iou_max))
img_box.save(img_box_path, format='jpeg')
offset = cal_offset(closet_face, box)
ldmk_offset = cal_landmark_offset(box, ldmk)
txt.write(
txt_to_write(
osp.relpath(img_box_path,
osp.split(txt_path)[0]), label, offset,
ldmk_offset))
pass
elif 0.65 < iou:
label = 'p' if ldmk is None else 'l'
img_box_path = osp.join(save_dir,
'{}_{:.8f}.jpg'.format(id, iou_max))
img_box.save(img_box_path, format='jpeg')
offset = cal_offset(closet_face, box)
ldmk_offset = cal_landmark_offset(box, ldmk)
txt.write(
txt_to_write(
osp.relpath(img_box_path,
osp.split(txt_path)[0]), label, offset,
ldmk_offset))
# print('iou:{}'.format(iou))
txt.close()
crop_img, label, offset, ldmk = self.get_crop_img_label_offset_ldmk(img, faces, ldmk, index)
if crop_img is None: return self.__getitem__(random.randint(0, self.__len__()))
img_tensor = transforms.ToTensor()(crop_img)
# label = torch.tensor([1.0]) if item[1] in ['p', 'pf', 'l'] else torch.tensor([0.0])
landmark_flag = torch.FloatTensor([1.0 if label == 'l' else 0.0])
label = torch.FloatTensor([1.0 if label in ['p', 'pf', 'l'] else 0.0])
offset = torch.FloatTensor(offset if 4 == len(offset) else 4 * [0.0])
landmark = torch.FloatTensor(ldmk if 10 == len(ldmk) else 10 * [0.0])
# print('label type:', label.type())
# print('data_imformation:', label, offset, landmark_flag, landmark)
return (img_tensor, label, offset, landmark_flag, landmark)
def __len__(self):
# self.ct += 1
# return self.ct
return len(self.img_faces)
if __name__ == '__main__':
from create_dataset import create_pnet_data_txt_parser, landmark_dataset_txt_parser, dataset_config
args = dataset_config()
img_faces = create_pnet_data_txt_parser(args.class_data_txt_path, args.class_data_dir)
img_face_landmark = landmark_dataset_txt_parser(args.landmark_data_txt_path, args.landmark_data_dir)
IDS = InplaceDataset(img_face_landmark, img_faces, cropsize=48,
pnet=load_net(args, 'pnet'), rnet=load_net(args, 'rnet'))
for i, (img_tensor, label, offset, landmark_flag, landmark) in enumerate(IDS):
print(label, offset, landmark_flag, landmark)
print(i)
pass