def run_from_file(self):
if self.args.KITTI == '2015':
from dataloader import KITTI_submission_loader as DA
else:
from dataloader import KITTI_submission_loader2012 as DA
test_left_img, test_right_img = DA.dataloader(self.args.datapath)
if not os.path.isdir(self.args.save_path):
os.makedirs(self.args.save_path)
for inx in range(len(test_left_img)):
imgL_o = (skimage.io.imread(test_left_img[inx]).astype('float32'))
imgR_o = (skimage.io.imread(test_right_img[inx]).astype('float32'))
img = self.disp_pred_net.run(imgL_o, imgR_o)
# file output
print(test_left_img[inx].split('/')[-1])
if self.args.save_figure:
skimage.io.imsave(
self.args.save_path + '/' +
test_left_img[inx].split('/')[-1],
(img * 256).astype('uint16'))
else:
np.save(
self.args.save_path + '/' +
test_left_img[inx].split('/')[-1][:-4], img)
def run_from_file(self):
if self.args_disp.KITTI == '2015':
from dataloader import KITTI_submission_loader as DA
else:
from dataloader import KITTI_submission_loader2012 as DA
test_left_img, test_right_img = DA.dataloader(self.args_disp.datapath)
if not os.path.isdir(self.args_disp.save_path):
os.makedirs(self.args_disp.save_path)
for inx in range(len(test_left_img)):
imgL_o = (skimage.io.imread(test_left_img[inx]).astype('float32'))
imgR_o = (skimage.io.imread(test_right_img[inx]).astype('float32'))
img = self.disp_pred_net.run(imgL_o, imgR_o)
# # file output
# print(test_left_img[inx].split('/')[-1])
# if self.args.save_figure:
# skimage.io.imsave(self.args.save_path+'/'+test_left_img[inx].split('/')[-1],(img*256).astype('uint16'))
# else:
# np.save(self.args.save_path+'/'+test_left_img[inx].split('/')[-1][:-4], img)
predix = test_left_img[inx].split('/')[-1][:-4]
calib_file = '{}/{}.txt'.format(self.args_gen_lidar.calib_dir,
predix)
calib = kitti_util.Calibration(calib_file)
img = (img * 256).astype(np.uint16) / 256.
lidar = self.pcl_generator.run(calib, img)
# pad 1 in the indensity dimension
lidar = np.concatenate([lidar, np.ones((lidar.shape[0], 1))], 1)
lidar = lidar.astype(np.float32)
lidar.tofile('{}/{}.bin'.format(self.args_gen_lidar.save_dir,
predix))
print('Finish Depth {}'.format(predix))
default=1,
metavar='S',
help='random seed (default: 1)')
args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)
if args.KITTI == '2015':
from dataloader import KITTI_submission_loader as DA
else:
from dataloader import KITTI_submission_loader2012 as DA
test_left_img, test_right_img = DA.dataloader(args.datapath)
if args.model == 'stackhourglass':
model = stackhourglass(args.maxdisp)
elif args.model == 'basic':
model = basic(args.maxdisp)
else:
print('no model')
model = nn.DataParallel(model, device_ids=[0])
model.cuda()
if args.loadmodel is not None:
state_dict = torch.load(args.loadmodel)
model.load_state_dict(state_dict['state_dict'])
args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)
kitti2015 = False
kitti2012 = False
kitti_vkt2 = False
if args.KITTI == '2015':
print("processing KT15!")
data_type_str = "kt15"
from dataloader import KITTI_submission_loader as DA
test_left_img, test_right_img = DA.dataloader(args.datapath,
args.file_txt_path)
test_left_disp = None
kitti2015 = True
elif args.KITTI == '2012':
print("processing KT12!")
data_type_str = "kt12"
from dataloader import KITTI_submission_loader2012 as DA
test_left_img, test_right_img = DA.dataloader(args.datapath,
args.file_txt_path)
test_left_disp = None
kitti2012 = True
# added by CCJ on 2020/05/22:
elif args.KITTI == 'virtual_kt_2':
print("processing Virtual KT 2!")
data_type_str = "virtual_kt2"
args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)
if args.KITTI == '2015':
from dataloader import KITTI_submission_loader as DA
else:
from dataloader import KITTI_submission_loader2012 as DA
import sintel_loader as DA
test_left_img, test_right_img = DA.dataloader(args.datapath, args.left_dir,
args.right_dir)
device = torch.device("cuda:1" if torch.cuda.is_available() else "cpu")
if args.model == 'stackhourglass':
model = stackhourglass(args.maxdisp,
device=device,
dfd_net=args.dfd,
dfd_at_end=args.dfd_at_end,
right_head=args.right_head)
elif args.model == 'basic':
model = basic(args.maxdisp)
else:
print('no model')
model = nn.DataParallel(model, device_ids=[0])
model.cuda()