def main(args):
checkpoint = torch.load(args.model_path)
plfd_backbone = PFLDInference().cuda()
plfd_backbone.load_state_dict(checkpoint['plfd_backbone'])
plfd_backbone.eval()
plfd_backbone = plfd_backbone.cuda()
transform = transforms.Compose([transforms.ToTensor()])
cap = cv2.VideoCapture(0)
while True:
ret, img = cap.read()
if not ret: break
height, width = img.shape[:2]
bounding_boxes, landmarks = detect_faces(img)
for box in bounding_boxes:
score = box[4]
x1, y1, x2, y2 = (box[:4] + 0.5).astype(np.int32)
w = x2 - x1 + 1
h = y2 - y1 + 1
size = int(max([w, h]) * 1.1)
cx = x1 + w // 2
cy = y1 + h // 2
x1 = cx - size // 2
x2 = x1 + size
y1 = cy - size // 2
y2 = y1 + size
dx = max(0, -x1)
dy = max(0, -y1)
x1 = max(0, x1)
y1 = max(0, y1)
edx = max(0, x2 - width)
edy = max(0, y2 - height)
x2 = min(width, x2)
y2 = min(height, y2)
cropped = img[y1:y2, x1:x2]
if (dx > 0 or dy > 0 or edx > 0 or edy > 0):
cropped = cv2.copyMakeBorder(cropped, dy, edy, dx, edx,
cv2.BORDER_CONSTANT, 0)
cropped = cv2.resize(cropped, (112, 112))
input = cv2.resize(cropped, (112, 112))
input = cv2.cvtColor(input, cv2.COLOR_BGR2RGB)
input = transform(input).unsqueeze(0).cuda()
_, landmarks = plfd_backbone(input)
pre_landmark = landmarks[0]
pre_landmark = pre_landmark.cpu().detach().numpy().reshape(
-1, 2) * [size, size]
for (x, y) in pre_landmark.astype(np.int32):
cv2.circle(img, (x1 + x, y1 + y), 1, (0, 0, 255))
cv2.imshow('0', img)
if cv2.waitKey(10) == 27:
break
def __init__(self, model_path):
checkpoint = torch.load(model_path)
plfd_backbone = PFLDInference().cuda()
plfd_backbone.load_state_dict(checkpoint['plfd_backbone'])
plfd_backbone.eval()
self.plfd_backbone = plfd_backbone.cuda()
self.transform = transforms.Compose([transforms.ToTensor()])
def main(args):
checkpoint = torch.load(args.model_path)
plfd_backbone = PFLDInference().cuda()
plfd_backbone.load_state_dict(checkpoint['plfd_backbone'])
plfd_backbone.eval()
plfd_backbone = plfd_backbone.cuda()
transform = transforms.Compose([transforms.ToTensor()])
cap = cv2.VideoCapture(0)
while True:
ret, img = cap.read()
if not ret: break
bounding_boxes, landmarks = detect_faces(img)
maxval_index = 0
if (len(bounding_boxes) > 0):
maxval_index = np.argmax(bounding_boxes[:, 4])
if (len(bounding_boxes) > maxval_index - 1
and len(bounding_boxes) > 0):
face = img[int(bounding_boxes[maxval_index][1]
):int(bounding_boxes[maxval_index][3]),
int(bounding_boxes[maxval_index][0]
):int(bounding_boxes[maxval_index][2])]
if face.size == 0:
continue
face_resized = cv2.resize(face,
dsize=(112, 112),
interpolation=cv2.INTER_LINEAR)
face_resized = cv2.cvtColor(face_resized, cv2.COLOR_BGR2RGB)
face_resized = transform(face_resized).unsqueeze(0).cuda()
_, landmarks = plfd_backbone(face_resized)
pre_landmark = landmarks.cpu().detach().numpy()[0].reshape(
-1, 2) * [
int(bounding_boxes[maxval_index][2]) -
int(bounding_boxes[maxval_index][0]),
int(bounding_boxes[maxval_index][3]) -
int(bounding_boxes[maxval_index][1])
]
for (x, y) in pre_landmark.astype(np.int32):
cv2.circle(face, (x, y), 1, (255, 0, 0), -1)
cv2.imshow("xxxx", face)
if cv2.waitKey(10) == 27:
break
def main(args):
checkpoint = torch.load(args.model_path)
plfd_backbone = PFLDInference().cuda()
plfd_backbone.load_state_dict(checkpoint['plfd_backbone'])
plfd_backbone.eval()
plfd_backbone = plfd_backbone.cuda()
transform = transforms.Compose([transforms.ToTensor()])
img = cv2.imread(args.image_path)
height, width = img.shape[:2]
bounding_boxes, landmarks = detect_faces(img)
for box in bounding_boxes:
#score = box[4]
x1, y1, x2, y2 = (box[:4] + 0.5).astype(np.int32)
w = x2 - x1 + 1
h = y2 - y1 + 1
size = int(max([w, h]) * 1.1)
cx = x1 + w // 2
cy = y1 + h // 2
x1 = cx - size // 2
x2 = x1 + size
y1 = cy - size // 2
y2 = y1 + size
dx = max(0, -x1)
dy = max(0, -y1)
x1 = max(0, x1)
y1 = max(0, y1)
edx = max(0, x2 - width)
edy = max(0, y2 - height)
x2 = min(width, x2)
y2 = min(height, y2)
cropped = img[y1:y2, x1:x2]
if (dx > 0 or dy > 0 or edx > 0 or edy > 0):
cropped = cv2.copyMakeBorder(cropped, dy, edy, dx, edx,
cv2.BORDER_CONSTANT, 0)
cv2.imwrite("cropped.jpg", cropped)
print("cropped shape:", cropped.shape) #cropped shape: (668, 668, 3)
cropped = cv2.resize(cropped, (112, 112))
input = cv2.resize(cropped, (112, 112))
input = cv2.cvtColor(input, cv2.COLOR_BGR2RGB)
input = transform(input).unsqueeze(0).cuda()
_, landmarks = plfd_backbone(input)
pre_landmark = landmarks[0]
print("size:", size) #size: 668
pre_landmark = pre_landmark.cpu().detach().numpy().reshape(
-1, 2) * [size, size]
for idx, (x, y) in enumerate(pre_landmark.astype(np.int32)):
cv2.circle(img, (x1 + x, y1 + y), 1, (0, 0, 255))
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(img, str(idx + 1), (x1 + x, y1 + y), font, 0.4,
(0, 0, 255), 1, cv2.LINE_AA)
points = transfer(pre_landmark)
for point in points:
cv2.circle(img,
(int(round(x1 + point[0])), int(round(y1 + point[1]))),
5, (255, 0, 0), 2)
cv2.imwrite("result.jpg", img)
# trained_model = './weights/Resnet50_epoch_95.pth'
retina_trained_model = './weights/mobilenet0.25_epoch_245.pth'
mask_trained_model = './weights/net_21.pth'
pfld_trained_model = './weights/checkpoint_epoch_500.pth.tar'
# net and model
retina_net = RetinaFace(cfg=cfg, phase='test')
mask_net = resnet50(num_classes=2)
pfld_backbone = PFLDInference()
# load pre-trained model
retina_net.load_state_dict(torch.load(retina_trained_model))
mask_net.load_state_dict(torch.load(mask_trained_model))
pfld_backbone.load_state_dict(torch.load(pfld_trained_model)['plfd_backbone'])
retina_net = retina_net.cuda(0)
mask_net = mask_net.cuda(0)
pfld_net = pfld_backbone.cuda(0)
retina_net.eval()
mask_net.eval()
pfld_net.eval()
resize = 1
top_k = 5000
keep_top_k = 750
nms_threshold = 0.5
cudnn.benchmark = True
transform1 = T.Compose([
T.Resize(size=(256, 256)),
T.ToTensor(),
T.Normalize([0.56687369, 0.44000871, 0.39886727],
