def get_models(mtcnn_w_path='mtcnn/weights'):
# First we create pnet, rnet, onet, and load weights from caffe model.
pnet, rnet, onet = mtcnn.get_net_caffe(mtcnn_w_path)
# Then we create a detector
detector = mtcnn.FaceDetector(pnet, rnet, onet, device='cpu')
embedder = insightface.iresnet100(pretrained=True)
embedder.eval()
return detector, embedder
def main(img):
# detect faces
pnet, rnet, onet = mtcnn.get_net_caffe('output/converted')
detector = mtcnn.FaceDetector(pnet, rnet, onet, device='cuda:0')
#img = '../FaceDetector/tests/asset/images/office5.jpg'
img = imread(img)
boxes, landmarks = detector.detect(img)
img = torch.tensor(img.astype(np.float32),
device=torch.device("cuda:0")).permute(2, 0, 1)
# embed faces
embedder = insightface.iresnet100(pretrained=True)
embedder.eval()
mean = [127.5] * 3 #[0.5] * 3
std = [128.] * 3 #[0.5 * 256 / 255] * 3
preprocess = transforms.Compose([transforms.Normalize(mean, std)])
landmarks = landmarks.float()
boxcpu = boxes.cpu().numpy()
for f0 in range(boxcpu.shape[0]):
angle = torch.atan2(landmarks[f0][1, 1] - landmarks[f0][0, 1], \
landmarks[f0][1, 0] - landmarks[f0][0, 0])# + np.pi/2
local_patch = img[:, boxes[f0][1]:boxes[f0][3],
boxes[f0][0]:boxes[f0][2]].unsqueeze(0)
local_patch = rot_img(local_patch, angle, \
[1./local_patch.shape[2]*\
(-0.5*(boxes[f0][2]+boxes[f0][0])+landmarks[f0][2, 0]), \
1./local_patch.shape[3]*\
(-0.5*(boxes[f0][3]+boxes[f0][1])+landmarks[f0][2, 1])], \
dtype=torch.cuda.FloatTensor)
local_patch = local_patch.squeeze(0)
tensor_face = F.interpolate(local_patch, size=112)
tensor_face = tensor_face.permute(0, 2, 1)
tensor_face = F.interpolate(tensor_face, size=112)
tensor_face = tensor_face.permute(0, 2, 1)
tensor_face = preprocess(tensor_face.cpu())
with torch.no_grad():
features = embedder(tensor_face.unsqueeze(0))[0].numpy()
print(features)
parser = argparse.ArgumentParser(description='this is a description')
parser.add_argument('--video_path', type=str, help="Read from video.")
parser.add_argument('--output_folder', type=str, help="Save the tracking result.")
parser.add_argument('--saved_path', type=str, default=None,
help="If set, Save as video. Or show it on screen.")
parser.add_argument("--minsize", type=int, default=24,
help="Min size of faces you want to detect. Larger number will speed up detect method.")
parser.add_argument('--min_interval', type=int, default=3, help="See FaceTracker.")
parser.add_argument("--device", type=str, default='cpu',
help="Target device to process video.")
args = parser.parse_args()
pnet, rnet, onet = mtcnn.get_net_caffe('output/converted')
detector = mtcnn.FaceDetector(pnet, rnet, onet, device=args.device)
tracker = mtcnn.FaceTracker(detector, min_interval=args.min_interval)
tracker.set_detect_params(minsize=args.minsize)
fourcc = cv2.VideoWriter_fourcc(*"XVID")
cap = cv2.VideoCapture(args.video_path)
fps = cap.get(cv2.CAP_PROP_FPS)
size = (int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)),
int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)))
if args.saved_path is not None:
out = cv2.VideoWriter(args.saved_path, fourcc, fps, size)
while True:
def setUp(self):
self.dataset = get_by_name(DEFAULT_DATASET)
self.output_folder = os.path.join(here, '../output/test')
self.top = 100
self.pnet, self.rnet, _ = get_net_caffe(
os.path.join(here, '../output/converted'))
def __init__(self):
# First we create pnet, rnet, onet, and load weights from caffe model.
pnet, rnet, onet = mtcnn.get_net_caffe('output/converted')
# Then we create a detector
self.__detector = mtcnn.FaceDetector(pnet, rnet, onet, device='cuda:0')