def init_siam_model(self, weights_filepath, config_filepath):
class TempLoader:
resume = weights_filepath
config = config_filepath
cpu = False
args = TempLoader()
# Setup device
self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
torch.backends.cudnn.benchmark = True
# Setup Model
self.cfg = load_config(args)
self.siammask = Custom(anchors=self.cfg['anchors'])
self.siammask = load_pretrain(self.siammask, args.resume)
self.siammask.eval().to(self.device)
def init_siam_model(self):
class TempLoader:
resume = os.path.join(self.weights_path, 'SiamMask_DAVIS.pth')
config = os.path.join(self.weights_path, 'config_davis.json')
cpu = False
args = TempLoader()
# Setup device
self.device = torch.device(
'cuda' if torch.cuda.is_available() else 'cpu')
torch.backends.cudnn.benchmark = True
# Setup Model
self.cfg = load_config(args)
self.siammask = Custom(anchors=self.cfg['anchors'])
self.siammask = load_pretrain(self.siammask, args.resume)
self.siammask.eval().to(self.device)
def __init__(self):
class temp:
resume = r'E:\Shabtay\fonda_pytorch\SiamMask_master\models\SiamMask_DAVIS.pth' # ,help='path to latest checkpoint (default: none)')
config = r'E:\Shabtay\fonda_pytorch\SiamMask_master\experiments\siammask_sharp\config_davis.json' # help='hyper-parameter of SiamMask in json format')
# base_path=r'E:\Shabtay\fonda_pytorch\SiamMask_master\data\tennis' # help='datasets')
base_path = r'C:\Users\Dataloop\.dataloop\datasets\5ce2b280fe3b45001c2c7a51\image\Arlozorov1'
cpu = False # help='cpu mode')
args = temp()
# Setup device
self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
torch.backends.cudnn.benchmark = True
# Setup Model
self.cfg = load_config(args)
from SiamMask_master.experiments.siammask_sharp.custom import Custom
self.siammask = Custom(anchors=self.cfg['anchors'])
if args.resume:
assert os.path.isfile(args.resume), 'Please download {} first.'.format(args.resume)
self.siammask = load_pretrain(self.siammask, args.resume)
self.siammask.eval().to(self.device)
def main():
global args, logger, v_id
args = parser.parse_args()
cfg = load_config(args)
init_log('global', logging.INFO)
if args.log != "":
add_file_handler('global', args.log, logging.INFO)
logger = logging.getLogger('global')
logger.info(args)
# setup model
if args.arch == 'Custom':
from custom import Custom
model = Custom(anchors=cfg['anchors'])
else:
parser.error('invalid architecture: {}'.format(args.arch))
if args.resume:
assert isfile(args.resume), '{} is not a valid file'.format(
args.resume)
model = load_pretrain(model, args.resume)
model.eval()
device = torch.device('cuda' if (
torch.cuda.is_available() and not args.cpu) else 'cpu')
model = model.to(device)
# setup dataset
dataset = load_dataset(args.dataset)
# VOS or VOT?
if args.dataset in ['DAVIS2016', 'DAVIS2017', 'ytb_vos'] and args.mask:
vos_enable = True # enable Mask output
else:
vos_enable = False
total_lost = 0 # VOT
iou_lists = [] # VOS
speed_list = []
for v_id, video in enumerate(dataset.keys(), start=1):
if args.video != '' and video != args.video:
continue
if vos_enable:
iou_list, speed = track_vos(
model,
dataset[video],
cfg['hp'] if 'hp' in cfg.keys() else None,
args.mask,
args.refine,
args.dataset in ['DAVIS2017', 'ytb_vos'],
device=device)
iou_lists.append(iou_list)
else:
lost, speed = track_vot(model,
dataset[video],
cfg['hp'] if 'hp' in cfg.keys() else None,
args.mask,
args.refine,
device=device)
total_lost += lost
speed_list.append(speed)
# report final result
if vos_enable:
for thr, iou in zip(thrs, np.mean(np.concatenate(iou_lists), axis=0)):
logger.info('Segmentation Threshold {:.2f} mIoU: {:.3f}'.format(
thr, iou))
else:
logger.info('Total Lost: {:d}'.format(total_lost))
logger.info('Mean Speed: {:.2f} FPS'.format(np.mean(speed_list)))