def main():
global args, v_id
args = parser.parse_args()
net = SiamRPNotb()
net.load_state_dict(torch.load(join(realpath(dirname(__file__)), 'SiamRPNOTB.model')))
net.eval().cuda()
dataset = load_dataset(args.dataset)
fps_list = []
for v_id, video in enumerate(dataset.keys()):
fps_list.append(track_video(net, dataset[video]))
print('Mean Running Speed {:.1f}fps'.format(np.mean(np.array(fps_list))))
def SiamRPN_load(image, boxes, txt_path):
if not os.path.exists(txt_path):
os.makedirs(txt_path)
multiTracker = cv2.MultiTracker_create()
net = SiamRPNotb()
net.load_state_dict(
torch.load(join(realpath(dirname(__file__)), 'SiamRPNOTB.model')))
net.eval().cuda()
states, labels = [], []
for bbox in boxes:
#init_rbox = [bbox[0],bbox[1],bbox[0]+bbox[2],bbox[1],bbox[0]+bbox[2],bbox[1]+bbox[3],bbox[0],bbox[1]+bbox[3]]
init_rbox = [
bbox[0], bbox[1], bbox[2], bbox[1], bbox[2], bbox[3], bbox[0],
bbox[3]
]
[cx, cy, w, h] = get_axis_aligned_bbox(init_rbox)
# print(cx, cy, w, h,'-----',init_rbox)
target_pos, target_sz = np.array([cx, cy]), np.array([w, h])
states.append(SiamRPN_init(image, target_pos, target_sz, net))
labels.append(bbox[-1])
return states, labels
class DaSiamRPN(BaseTracker):
def __init__(self):
super(DaSiamRPN, self).__init__(name="DaSiamRPN")
self.net_file = path_config.DASIAMRPN_MODEL
def initialize(self, image_file, box):
self.net = SiamRPNotb()
self.net.load_state_dict(torch.load(self.net_file))
self.net.eval().cuda()
image = cv2.imread(image_file)
box = box - np.array([1, 1, 0, 0])
self.state = SiamRPN_init(image, box[:2] + box[2:] / 2.0, box[2:],
self.net) # init tracker
def track(self, image_file):
image = cv2.imread(image_file)
self.state = SiamRPN_track(self.state, image) # track
center = self.state["target_pos"] + 1
target_sz = self.state["target_sz"]
box = cxy_wh_2_rect(center, target_sz)
return box