def main():
rank, world_size = dist_init()
logger.info("init done")
# load cfg
cfg.merge_from_file(args.cfg)
if rank == 0:
if not os.path.exists(cfg.TRAIN.LOG_DIR):
os.makedirs(cfg.TRAIN.LOG_DIR)
init_log('global', logging.INFO)
if cfg.TRAIN.LOG_DIR:
add_file_handler('global',
os.path.join(cfg.TRAIN.LOG_DIR, 'logs.txt'),
logging.INFO)
logger.info("Version Information: \n{}\n".format(commit()))
logger.info("config \n{}".format(json.dumps(cfg, indent=4)))
# create model
model = ModelBuilder().cuda().train()
# dist_model = DistModule(model)
# load pretrained backbone weights
if cfg.BACKBONE.PRETRAINED:
cur_path = os.path.dirname(os.path.realpath(__file__))
backbone_path = os.path.join(cur_path, '../', cfg.BACKBONE.PRETRAINED)
load_pretrain(model.backbone, backbone_path)
# create tensorboard writer
if rank == 0 and cfg.TRAIN.LOG_DIR:
tb_writer = SummaryWriter(cfg.TRAIN.LOG_DIR)
else:
tb_writer = None
# build dataset loader
train_loader = build_data_loader()
# build optimizer and lr_scheduler
optimizer, lr_scheduler = build_opt_lr(model, cfg.TRAIN.START_EPOCH)
# resume training
if cfg.TRAIN.RESUME:
logger.info("resume from {}".format(cfg.TRAIN.RESUME))
assert os.path.isfile(cfg.TRAIN.RESUME), \
'{} is not a valid file.'.format(cfg.TRAIN.RESUME)
model, optimizer, cfg.TRAIN.START_EPOCH = \
restore_from(model, optimizer, cfg.TRAIN.RESUME)
# load pretrain
elif cfg.TRAIN.PRETRAINED:
load_pretrain(model, cfg.TRAIN.PRETRAINED)
dist_model = DistModule(model)
logger.info(lr_scheduler)
logger.info("model prepare done")
# start training
train(train_loader, dist_model, optimizer, lr_scheduler, tb_writer)
def setup_tracker():
cfg.merge_from_file(cfg_file)
model = ModelBuilder()
model = load_pretrain(model, model_file).cuda().eval()
tracker = build_tracker(model)
warmup(model)
return tracker
def __init__(self):
super(SiamBAN, self).__init__("SiamBAN")
# load config
cfg.merge_from_file(path_config.SIAMBAN_CONFIG)
# create model
model = ModelBuilder()
# load model
model = load_pretrain(model,
path_config.SIAMBAN_SNAPSHOT).cuda().eval()
# build tracker
self.tracker = build_tracker(model)
def main():
# load config
cfg.merge_from_file(args.config)
cur_dir = os.path.dirname(os.path.realpath(__file__))
# create model
model = ModelBuilder()
# load model
model = load_pretrain(model, args.snapshot).cuda().eval()
# build tracker
tracker = build_tracker(model)
handle = vot.VOT("rectangle")
region = handle.region()
imagefile = handle.frame()
if not imagefile:
sys.exit(0)
img = cv2.imread(imagefile)
left = max(region.x, 0)
top = max(region.y, 0)
right = min(region.x + region.width, img.shape[1] - 1)
bottom = min(region.y + region.height, img.shape[0] - 1)
cx, cy, w, h = corner2center(Corner(left, top, right, bottom))
gt_bbox_ = [cx - (w - 1) / 2, cy - (h - 1) / 2, w, h]
tracker.init(img, gt_bbox_)
while True:
imagefile = handle.frame()
if not imagefile:
break
image = cv2.imread(imagefile)
outputs = tracker.track(image)
pred_bbox = outputs['bbox']
conf = outputs['best_score']
handle.report(vot.Rectangle(*pred_bbox), conf)
def main():
# load config
cfg.merge_from_file(args.config)
# 当前目录
cur_dir = os.path.dirname(os.path.realpath(__file__))
# 数据集的路径
dataset_root = os.path.join(cur_dir, r'C:\Users\639\PycharmProjects\siamban\testing_dataset', args.dataset)
# create model
model = ModelBuilder()
# load model
model = load_pretrain(model, args.snapshot).cuda().eval()
# build tracker
tracker = build_tracker(model)
# create dataset
dataset = DatasetFactory.create_dataset(name=args.dataset,
dataset_root=dataset_root,
load_img=False)
model_name = args.snapshot.split('/')[-1].split('.')[0]
total_lost = 0
if args.dataset in ['VOT2016', 'VOT2018', 'VOT2019']:
# restart tracking
for v_idx, video in enumerate(dataset):
if args.video != '':
# test one special video
if video.name != args.video:
continue
frame_counter = 0
lost_number = 0
toc = 0
pred_bboxes = []
for idx, (img, gt_bbox) in enumerate(video):
if len(gt_bbox) == 4:
gt_bbox = [gt_bbox[0], gt_bbox[1],
gt_bbox[0], gt_bbox[1]+gt_bbox[3]-1,
gt_bbox[0]+gt_bbox[2]-1, gt_bbox[1]+gt_bbox[3]-1,
gt_bbox[0]+gt_bbox[2]-1, gt_bbox[1]]
tic = cv2.getTickCount()
if idx == frame_counter:
cx, cy, w, h = get_axis_aligned_bbox(np.array(gt_bbox))
gt_bbox_ = [cx-(w-1)/2, cy-(h-1)/2, w, h]
tracker.init(img, gt_bbox_)
pred_bbox = gt_bbox_
pred_bboxes.append(1)
elif idx > frame_counter:
outputs = tracker.track(img)
pred_bbox = outputs['bbox']
overlap = vot_overlap(pred_bbox, gt_bbox, (img.shape[1], img.shape[0]))
if overlap > 0:
# not lost
pred_bboxes.append(pred_bbox)
else:
# lost object
pred_bboxes.append(2)
frame_counter = idx + 5 # skip 5 frames
lost_number += 1
else:
pred_bboxes.append(0)
toc += cv2.getTickCount() - tic
if idx == 0:
cv2.destroyAllWindows()
if args.vis and idx > frame_counter:
cv2.polylines(img, [np.array(gt_bbox, np.int).reshape((-1, 1, 2))],
True, (0, 255, 0), 3)
bbox = list(map(int, pred_bbox))
cv2.rectangle(img, (bbox[0], bbox[1]),
(bbox[0]+bbox[2], bbox[1]+bbox[3]), (0, 255, 255), 3)
cv2.putText(img, str(idx), (40, 40), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 255), 2)
cv2.putText(img, str(lost_number), (40, 80), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
cv2.imshow(video.name, img)
cv2.waitKey(1)
toc /= cv2.getTickFrequency()
# save results
video_path = os.path.join('results', args.dataset, model_name,
'baseline', video.name)
if not os.path.isdir(video_path):
os.makedirs(video_path)
result_path = os.path.join(video_path, '{}_001.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in pred_bboxes:
if isinstance(x, int):
f.write("{:d}\n".format(x))
else:
f.write(','.join([vot_float2str("%.4f", i) for i in x])+'\n')
print('({:3d}) Video: {:12s} Time: {:4.1f}s Speed: {:3.1f}fps Lost: {:d}'.format(
v_idx+1, video.name, toc, idx / toc, lost_number))
total_lost += lost_number
print("{:s} total lost: {:d}".format(model_name, total_lost))
else:
# OPE tracking
for v_idx, video in enumerate(dataset):
if args.video != '':
# test one special video
if video.name != args.video:
continue
toc = 0
pred_bboxes = []
scores = []
track_times = []
for idx, (img, gt_bbox) in enumerate(video):
tic = cv2.getTickCount()
if idx == 0:
cx, cy, w, h = get_axis_aligned_bbox(np.array(gt_bbox))
gt_bbox_ = [cx-(w-1)/2, cy-(h-1)/2, w, h]
tracker.init(img, gt_bbox_)
pred_bbox = gt_bbox_
scores.append(None)
if 'VOT2018-LT' == args.dataset:
pred_bboxes.append([1])
else:
pred_bboxes.append(pred_bbox)
else:
outputs = tracker.track(img)
pred_bbox = outputs['bbox']
pred_bboxes.append(pred_bbox)
scores.append(outputs['best_score'])
toc += cv2.getTickCount() - tic
track_times.append((cv2.getTickCount() - tic)/cv2.getTickFrequency())
if idx == 0:
cv2.destroyAllWindows()
if args.vis and idx > 0:
gt_bbox = list(map(int, gt_bbox))
pred_bbox = list(map(int, pred_bbox))
cv2.rectangle(img, (gt_bbox[0], gt_bbox[1]),
(gt_bbox[0]+gt_bbox[2], gt_bbox[1]+gt_bbox[3]), (0, 255, 0), 3)
cv2.rectangle(img, (pred_bbox[0], pred_bbox[1]),
(pred_bbox[0]+pred_bbox[2], pred_bbox[1]+pred_bbox[3]), (0, 255, 255), 3)
cv2.putText(img, str(idx), (40, 40), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 255), 2)
cv2.imshow(video.name, img)
cv2.waitKey(1)
toc /= cv2.getTickFrequency()
# save results
if 'VOT2018-LT' == args.dataset:
video_path = os.path.join('results', args.dataset, model_name,
'longterm', video.name)
if not os.path.isdir(video_path):
os.makedirs(video_path)
result_path = os.path.join(video_path,
'{}_001.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in pred_bboxes:
f.write(','.join([str(i) for i in x])+'\n')
result_path = os.path.join(video_path,
'{}_001_confidence.value'.format(video.name))
with open(result_path, 'w') as f:
for x in scores:
f.write('\n') if x is None else f.write("{:.6f}\n".format(x))
result_path = os.path.join(video_path,
'{}_time.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in track_times:
f.write("{:.6f}\n".format(x))
elif 'GOT-10k' == args.dataset:
video_path = os.path.join('results', args.dataset, model_name, video.name)
if not os.path.isdir(video_path):
os.makedirs(video_path)
result_path = os.path.join(video_path, '{}_001.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in pred_bboxes:
f.write(','.join([str(i) for i in x])+'\n')
result_path = os.path.join(video_path,
'{}_time.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in track_times:
f.write("{:.6f}\n".format(x))
else:
model_path = os.path.join('results', args.dataset, model_name)
if not os.path.isdir(model_path):
os.makedirs(model_path)
result_path = os.path.join(model_path, '{}.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in pred_bboxes:
f.write(','.join([str(i) for i in x])+'\n')
print('({:3d}) Video: {:12s} Time: {:5.1f}s Speed: {:3.1f}fps'.format(
v_idx+1, video.name, toc, idx / toc))
def main():
# load config
cfg.merge_from_file(args.config)
cur_dir = os.path.dirname(os.path.realpath(__file__))
dataset_root = os.path.join('./datasets', args.dataset)
# -------------------------------------hp_search---------------------------------------#
params = [0.0, 0.0, 0.0]
# Interpolation learning rate
params[0] = cfg.TRACK.LR
# Scale penalty
params[1] = cfg.TRACK.PENALTY_K
# Window influence
params[2] = cfg.TRACK.WINDOW_INFLUENCE
params_name = args.snapshot.split(
'/')[-1] + ' ' + args.dataset + ' lr-' + str(
params[0]) + ' pk-' + '_' + str(params[1]) + ' win-' + '_' + str(
params[2])
# create model
model = ModelBuilder()
# load model
model = load_pretrain(model, args.snapshot).cuda().eval()
# build tracker
tracker = build_tracker(model)
# create dataset
dataset = DatasetFactory.create_dataset(name=args.dataset,
dataset_root=dataset_root,
load_img=False)
model_name = args.snapshot.split('/')[-1].split('.')[0]
if args.dataset in ['VOT2016', 'VOT2018', 'VOT2019']:
total_lost = 0
avg_speed = 0 # linlin
for v_idx, video in tqdm(enumerate(dataset)):
#for v_idx, video in tqdm(dataset):
if args.video != '':
# test one special video
if video.name != args.video:
continue
frame_counter = 0
lost_number = 0
toc = 0
pred_bboxes = []
for idx, (img, gt_bbox) in enumerate(video):
if len(gt_bbox) == 4:
gt_bbox = [
gt_bbox[0], gt_bbox[1], gt_bbox[0],
gt_bbox[1] + gt_bbox[3] - 1,
gt_bbox[0] + gt_bbox[2] - 1,
gt_bbox[1] + gt_bbox[3] - 1,
gt_bbox[0] + gt_bbox[2] - 1, gt_bbox[1]
]
tic = cv2.getTickCount()
if idx == frame_counter:
cx, cy, w, h = get_axis_aligned_bbox(np.array(gt_bbox))
gt_bbox_ = [cx - (w - 1) / 2, cy - (h - 1) / 2, w,
h] #[topx,topy,w,h]
tracker.init(img, gt_bbox_)
pred_bbox = gt_bbox_
pred_bboxes.append(1)
elif idx > frame_counter:
outputs = tracker.track(img)
pred_bbox = outputs['bbox']
if cfg.MASK.MASK:
pred_bbox = outputs['polygon']
overlap = vot_overlap(pred_bbox, gt_bbox,
(img.shape[1], img.shape[0]))
if overlap > 0:
# not lost
pred_bboxes.append(pred_bbox)
else:
# lost object
pred_bboxes.append(2)
frame_counter = idx + 5 # skip 5 frames
lost_number += 1
else:
pred_bboxes.append(0)
toc += cv2.getTickCount() - tic
if idx == 0:
cv2.destroyAllWindows()
if args.vis and idx > frame_counter:
cv2.polylines(
img, [np.array(gt_bbox, np.int).reshape(
(-1, 1, 2))], True, (0, 255, 0), 3)
if cfg.MASK.MASK:
cv2.polylines(
img,
[np.array(pred_bbox, np.int).reshape(
(-1, 1, 2))], True, (0, 255, 255), 3)
else:
bbox = list(map(int, pred_bbox))
cv2.rectangle(img, (bbox[0], bbox[1]),
(bbox[0] + bbox[2], bbox[1] + bbox[3]),
(0, 255, 255), 3)
cv2.putText(img, str(idx), (40, 40),
cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 255), 2)
cv2.putText(img, str(lost_number), (40, 80),
cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
cv2.imshow(video.name, img)
cv2.waitKey(1)
toc /= cv2.getTickFrequency()
# save results
video_path = os.path.join(args.save_path, args.dataset,
args.tracker_name, 'baseline',
video.name)
if not os.path.isdir(video_path):
os.makedirs(video_path)
result_path = os.path.join(video_path,
'{}_001.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in pred_bboxes:
if isinstance(x, int):
f.write("{:d}\n".format(x))
else:
f.write(','.join([vot_float2str("%.4f", i)
for i in x]) + '\n')
# print('({:3d}) Video: {:12s} Time: {:4.1f}s Speed: {:3.1f}fps Lost: {:d}'.format(
# v_idx+1, video.name, toc, idx / toc, lost_number))
total_lost += lost_number
avg_speed += idx / toc
print('Speed: {:3.1f}fps'.format(avg_speed / 60))
print(params_name)
#print(" stage:{:d} model:{:s} epoch:{:s} update_lr:{:f}".format(args.update_stage,args.update_path, args.update_path.split('/')[-1],update_lr[args.update_lr])
else:
# OPE tracking
for v_idx, video in tqdm(enumerate(dataset)):
if args.video != '':
# test one special video
if video.name != args.video:
continue
toc = 0
pred_bboxes = []
scores = []
track_times = []
for idx, (img, gt_bbox) in enumerate(video):
tic = cv2.getTickCount()
if idx == 0:
cx, cy, w, h = get_axis_aligned_bbox(np.array(gt_bbox))
gt_bbox_ = [cx - (w - 1) / 2, cy - (h - 1) / 2, w,
h] #[topx,topy,w,h]
tracker.init(img, gt_bbox_)
pred_bbox = gt_bbox_
scores.append(None)
if 'VOT2018-LT' == args.dataset:
pred_bboxes.append([1])
else:
pred_bboxes.append(pred_bbox)
else:
outputs = tracker.track(img)
pred_bbox = outputs['bbox']
pred_bboxes.append(pred_bbox)
#scores.append(outputs['best_score'])
toc += cv2.getTickCount() - tic
track_times.append(
(cv2.getTickCount() - tic) / cv2.getTickFrequency())
if idx == 0:
cv2.destroyAllWindows()
if args.vis and idx > 0:
gt_bbox = list(map(int, gt_bbox))
pred_bbox = list(map(int, pred_bbox))
cv2.rectangle(
img, (gt_bbox[0], gt_bbox[1]),
(gt_bbox[0] + gt_bbox[2], gt_bbox[1] + gt_bbox[3]),
(0, 255, 0), 3)
cv2.rectangle(img, (pred_bbox[0], pred_bbox[1]),
(pred_bbox[0] + pred_bbox[2],
pred_bbox[1] + pred_bbox[3]), (0, 255, 255),
3)
cv2.putText(img, str(idx), (40, 40),
cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 255), 2)
cv2.imshow(video.name, img)
cv2.waitKey(1)
toc /= cv2.getTickFrequency()
# save results
if 'VOT2018-LT' == args.dataset:
video_path = os.path.join(args.save_path, args.dataset,
args.tracker_name, 'longterm',
video.name)
if not os.path.isdir(video_path):
os.makedirs(video_path)
result_path = os.path.join(video_path,
'{}_001.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in pred_bboxes:
f.write(','.join([str(i) for i in x]) + '\n')
result_path = os.path.join(
video_path, '{}_001_confidence.value'.format(video.name))
with open(result_path, 'w') as f:
for x in scores:
f.write('\n') if x is None else f.write(
"{:.6f}\n".format(x))
result_path = os.path.join(video_path,
'{}_time.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in track_times:
f.write("{:.6f}\n".format(x))
elif 'GOT-10k' == args.dataset:
video_path = os.path.join(args.save_path, args.dataset,
args.tracker_name, video.name)
if not os.path.isdir(video_path):
os.makedirs(video_path)
result_path = os.path.join(video_path,
'{}_001.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in pred_bboxes:
f.write(','.join([str(i) for i in x]) + '\n')
result_path = os.path.join(video_path,
'{}_time.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in track_times:
f.write("{:.6f}\n".format(x))
else:
model_path = os.path.join(args.save_path, args.dataset,
args.tracker_name)
if not os.path.isdir(model_path):
os.makedirs(model_path)
result_path = os.path.join(model_path,
'{}.txt'.format(video.name))
with open(result_path, 'w') as f:
for x in pred_bboxes:
f.write(','.join([str(i) for i in x]) + '\n')
# print('({:3d}) Video: {:12s} Time: {:5.1f}s Speed: {:3.1f}fps'.format(
# v_idx+1, video.name, toc, idx / toc))
print(params_name)
# os.chdir(model_path)
# save_file = '../%s' % dataset
# shutil.make_archive(save_file, 'zip')
# print('Records saved at', save_file + '.zip')
evaluate(args)
def main():
# load config
cfg.merge_from_file(args.config)
cfg.CUDA = torch.cuda.is_available() and cfg.CUDA
device = torch.device('cuda' if cfg.CUDA else 'cpu')
# create model
model = ModelBuilder()
# load model
# model.load_state_dict(torch.load(args.snapshot,
# map_location=lambda storage, loc: storage.cpu()))
# model.eval().to(device)
# load model
model = load_pretrain(model, args.snapshot).cuda().eval()
# build tracker
tracker = build_tracker(model)
first_frame = True
if args.video_name:
video_name = args.video_name.split('/')[-1].split('.')[0]
else:
video_name = 'webcam'
cv2.namedWindow(video_name, cv2.WND_PROP_FULLSCREEN)
for frame in get_frames(args.video_name):
if first_frame:
# build video writer
if args.save:
if args.video_name.endswith('avi') or \
args.video_name.endswith('mp4') or \
args.video_name.endswith('mov'):
cap = cv2.VideoCapture(args.video_name)
fps = int(round(cap.get(cv2.CAP_PROP_FPS)))
else:
fps = 30
save_video_path = args.video_name.split(
video_name)[0] + video_name + '_tracking.mp4'
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
frame_size = (frame.shape[1], frame.shape[0]) # (w, h)
video_writer = cv2.VideoWriter(save_video_path, fourcc, fps,
frame_size)
try:
init_rect = cv2.selectROI(video_name, frame, False, False)
except:
exit()
tracker.init(frame, init_rect)
first_frame = False
else:
outputs = tracker.track(frame)
if 'polygon' in outputs:
polygon = np.array(outputs['polygon']).astype(np.int32)
cv2.polylines(frame, [polygon.reshape((-1, 1, 2))], True,
(0, 255, 0), 3)
mask = ((outputs['mask'] > cfg.TRACK.MASK_THERSHOLD) * 255)
mask = mask.astype(np.uint8)
mask = np.stack([mask, mask * 255, mask]).transpose(1, 2, 0)
frame = cv2.addWeighted(frame, 0.77, mask, 0.23, -1)
else:
bbox = list(map(int, outputs['bbox']))
cv2.rectangle(frame, (bbox[0], bbox[1]),
(bbox[0] + bbox[2], bbox[1] + bbox[3]),
(0, 255, 0), 3)
cv2.imshow(video_name, frame)
cv2.waitKey(40)
if args.save:
video_writer.write(frame)
if args.save:
video_writer.release()
torch.set_num_threads(1)
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu_id
# load config
cfg.merge_from_file(args.config)
cur_dir = os.path.dirname(os.path.realpath(__file__))
dataset_root = os.path.join(cur_dir, '../testing_dataset', args.dataset)
# create model
model = ModelBuilder()
# load model
model = load_pretrain(model, args.snapshot).cuda().eval()
# create dataset
dataset = DatasetFactory.create_dataset(name=args.dataset,
dataset_root=dataset_root,
load_img=False)
# Eval dataset
root = os.path.realpath(
os.path.join(os.path.dirname(__file__), '../testing_dataset'))
root = os.path.join(root, args.dataset)
if 'OTB' in args.dataset:
dataset_eval = OTBDataset(args.dataset, root)
elif 'LaSOT' == args.dataset:
dataset_eval = LaSOTDataset(args.dataset, root)
elif 'UAV' in args.dataset: