def main():
args = parser.parse_args()
weights_pose = torch.load(args.pretrained_posenet)
pose_net = models.PoseResNet().to(device)
pose_net.load_state_dict(weights_pose['state_dict'], strict=False)
pose_net.eval()
image_dir = Path(args.dataset_dir + args.sequence + "/image_2/")
output_dir = Path(args.output_dir)
output_dir.makedirs_p()
test_files = sum(
[image_dir.files('*.{}'.format(ext)) for ext in args.img_exts], [])
test_files.sort()
print('{} files to test'.format(len(test_files)))
print(test_files)
global_pose = np.eye(4)
poses = [global_pose[0:3, :].reshape(1, 12)]
n = len(test_files)
tensor_img1 = load_tensor_image(test_files[0], args)
for iter in tqdm(range(n - 1)):
tensor_img2 = load_tensor_image(test_files[iter + 1], args)
pose = pose_net(tensor_img1, tensor_img2)
pose_mat = pose_vec2mat(pose).squeeze(0).cpu().numpy()
pose_mat = np.vstack([pose_mat, np.array([0, 0, 0, 1])])
global_pose = global_pose @ np.linalg.inv(pose_mat)
poses.append(global_pose[0:3, :].reshape(1, 12))
# update
tensor_img1 = tensor_img2
poses = np.concatenate(poses, axis=0)
filename = Path(args.output_dir + args.sequence + ".txt")
np.savetxt(filename, poses, delimiter=' ', fmt='%1.8e')
def main():
args = parser.parse_args()
weights_pose = torch.load(args.pretrained_posenet)
pose_net = models.PoseResNet().to(device)
pose_net.load_state_dict(weights_pose['state_dict'], strict=False)
pose_net.eval()
output_dir = Path(args.output_dir)
output_dir.makedirs_p()
test_files = [args.tensor_img_1, args.tensor_img_2]
print('{} files to test'.format(len(test_files)))
print(device)
#print(test_files)
global_pose = np.eye(4)
poses = [global_pose[0:3, :].reshape(1, 12)]
n = len(test_files)
vo_single_pkg.estimate_pose(pose_net, test_files, args, device)
def main():
args = parser.parse_args()
from kitti_eval.pose_evaluation_utils import test_framework_KITTI as test_framework
weights = torch.load(args.pretrained_posenet)
seq_length = 5
pose_net = models.PoseResNet(18, False).to(device)
pose_net.load_state_dict(weights['state_dict'], strict=False)
dataset_dir = Path(args.dataset_dir)
framework = test_framework(dataset_dir, args.sequences, seq_length)
print('{} snippets to test'.format(len(framework)))
errors = np.zeros((len(framework), 2), np.float32)
if args.output_dir is not None:
output_dir = Path(args.output_dir)
output_dir.makedirs_p()
predictions_array = np.zeros((len(framework), seq_length, 3, 4))
for j, sample in enumerate(tqdm(framework)):
imgs = sample['imgs']
h, w, _ = imgs[0].shape
if (not args.no_resize) and (h != args.img_height
or w != args.img_width):
imgs = [
imresize(img,
(args.img_height, args.img_width)).astype(np.float32)
for img in imgs
]
imgs = [np.transpose(img, (2, 0, 1)) for img in imgs]
squence_imgs = []
for i, img in enumerate(imgs):
img = torch.from_numpy(img).unsqueeze(0)
img = ((img / 255 - 0.45) / 0.225).to(device)
squence_imgs.append(img)
global_pose = np.eye(4)
poses = []
poses.append(global_pose[0:3, :])
for iter in range(seq_length - 1):
pose = pose_net(squence_imgs[iter], squence_imgs[iter + 1])
pose_mat = pose_vec2mat(pose).squeeze(0).cpu().numpy()
pose_mat = np.vstack([pose_mat, np.array([0, 0, 0, 1])])
global_pose = global_pose @ np.linalg.inv(pose_mat)
poses.append(global_pose[0:3, :])
final_poses = np.stack(poses, axis=0)
if args.output_dir is not None:
predictions_array[j] = final_poses
ATE, RE = compute_pose_error(sample['poses'], final_poses)
errors[j] = ATE, RE
mean_errors = errors.mean(0)
std_errors = errors.std(0)
error_names = ['ATE', 'RE']
print('')
print("Results")
print("\t {:>10}, {:>10}".format(*error_names))
print("mean \t {:10.4f}, {:10.4f}".format(*mean_errors))
print("std \t {:10.4f}, {:10.4f}".format(*std_errors))
if args.output_dir is not None:
np.save(output_dir / 'predictions.npy', predictions_array)
def main():
global best_error, n_iter, device
args = parser.parse_args()
timestamp = datetime.datetime.now().strftime("%m-%d-%H:%M")
save_path = Path(args.name)
args.save_path = 'checkpoints' / save_path / timestamp
print('=> will save everything to {}'.format(args.save_path))
args.save_path.makedirs_p()
torch.manual_seed(args.seed)
np.random.seed(args.seed)
cudnn.deterministic = True
cudnn.benchmark = True
training_writer = SummaryWriter(args.save_path)
output_writers = []
if args.log_output:
for i in range(3):
output_writers.append(
SummaryWriter(args.save_path / 'valid' / str(i)))
# Data loading code
normalize = custom_transforms.Normalize(mean=[0.45, 0.45, 0.45],
std=[0.225, 0.225, 0.225])
train_transform = custom_transforms.Compose([
custom_transforms.RandomHorizontalFlip(),
custom_transforms.RandomScaleCrop(),
custom_transforms.ArrayToTensor(), normalize
])
valid_transform = custom_transforms.Compose(
[custom_transforms.ArrayToTensor(), normalize])
print("=> fetching scenes in '{}'".format(args.data))
train_set = SequenceFolder(args.data,
transform=train_transform,
seed=args.seed,
train=True,
sequence_length=args.sequence_length)
# if no Groundtruth is avalaible, Validation set is the same type as training set to measure photometric loss from warping
if args.with_gt:
from datasets.validation_folders import ValidationSet
val_set = ValidationSet(args.data, transform=valid_transform)
else:
val_set = SequenceFolder(args.data,
transform=valid_transform,
seed=args.seed,
train=False,
sequence_length=args.sequence_length)
print('{} samples found in {} train scenes'.format(len(train_set),
len(train_set.scenes)))
print('{} samples found in {} valid scenes'.format(len(val_set),
len(val_set.scenes)))
train_loader = torch.utils.data.DataLoader(train_set,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.workers,
pin_memory=True)
val_loader = torch.utils.data.DataLoader(val_set,
batch_size=args.batch_size,
shuffle=False,
num_workers=args.workers,
pin_memory=True)
if args.epoch_size == 0:
args.epoch_size = len(train_loader)
# create model
print("=> creating model")
disp_net = models.DispResNet(args.resnet_layers,
args.with_pretrain).to(device)
pose_net = models.PoseResNet(18, args.with_pretrain).to(device)
# load parameters
if args.pretrained_disp:
print("=> using pre-trained weights for DispResNet")
weights = torch.load(args.pretrained_disp)
disp_net.load_state_dict(weights['state_dict'], strict=False)
if args.pretrained_pose:
print("=> using pre-trained weights for PoseResNet")
weights = torch.load(args.pretrained_pose)
pose_net.load_state_dict(weights['state_dict'], strict=False)
disp_net = torch.nn.DataParallel(disp_net)
pose_net = torch.nn.DataParallel(pose_net)
print('=> setting adam solver')
optim_params = [{
'params': disp_net.parameters(),
'lr': args.lr
}, {
'params': pose_net.parameters(),
'lr': args.lr
}]
optimizer = torch.optim.Adam(optim_params,
betas=(args.momentum, args.beta),
weight_decay=args.weight_decay)
with open(args.save_path / args.log_summary, 'w') as csvfile:
writer = csv.writer(csvfile, delimiter='\t')
writer.writerow(['train_loss', 'validation_loss'])
with open(args.save_path / args.log_full, 'w') as csvfile:
writer = csv.writer(csvfile, delimiter='\t')
writer.writerow([
'train_loss', 'photo_loss', 'smooth_loss',
'geometry_consistency_loss'
])
logger = TermLogger(n_epochs=args.epochs,
train_size=min(len(train_loader), args.epoch_size),
valid_size=len(val_loader))
logger.epoch_bar.start()
for epoch in range(args.epochs):
logger.epoch_bar.update(epoch)
# train for one epoch
logger.reset_train_bar()
train_loss = train(args, train_loader, disp_net, pose_net, optimizer,
args.epoch_size, logger, training_writer)
logger.train_writer.write(' * Avg Loss : {:.3f}'.format(train_loss))
# evaluate on validation set
logger.reset_valid_bar()
if args.with_gt:
errors, error_names = validate_with_gt(args, val_loader, disp_net,
epoch, logger,
output_writers)
else:
errors, error_names = validate_without_gt(args, val_loader,
disp_net, pose_net,
epoch, logger,
output_writers)
error_string = ', '.join('{} : {:.3f}'.format(name, error)
for name, error in zip(error_names, errors))
logger.valid_writer.write(' * Avg {}'.format(error_string))
for error, name in zip(errors, error_names):
training_writer.add_scalar(name, error, epoch)
# Up to you to chose the most relevant error to measure your model's performance, careful some measures are to maximize (such as a1,a2,a3)
decisive_error = errors[1]
if best_error < 0:
best_error = decisive_error
# remember lowest error and save checkpoint
is_best = decisive_error < best_error
best_error = min(best_error, decisive_error)
save_checkpoint(args.save_path, {
'epoch': epoch + 1,
'state_dict': disp_net.module.state_dict()
}, {
'epoch': epoch + 1,
'state_dict': pose_net.module.state_dict()
}, is_best)
with open(args.save_path / args.log_summary, 'a') as csvfile:
writer = csv.writer(csvfile, delimiter='\t')
writer.writerow([train_loss, decisive_error])
logger.epoch_bar.finish()
def main():
args = parser.parse_args()
weights_pose = torch.load(args.pretrained_posenet)
pose_net = models.PoseResNet().to(device)
pose_net.load_state_dict(weights_pose['state_dict'], strict=False)
pose_net.eval()
image_dir = Path(args.dataset_dir)
output_dir = Path(args.output_dir)
output_dir.makedirs_p()
test_files = sum(
[image_dir.files('*.{}'.format(ext)) for ext in args.img_exts], [])
test_files.sort()
print('{} files to test'.format(len(test_files)))
#print(test_files)
global_pose = np.eye(4)
if 'advio-04' in args.dataset_dir:
global_pose = np.array([[
0.2337503561460601, 0.71124984004749991, -0.66293618387207998,
0.0037387620000000001
],
[
0.10487759004941999, 0.65940272844750003,
0.74443851971943986, 0.082704390000000003
],
[
0.96662371684119996, -0.24353990138999998,
0.079541459813400106, -0.023607989999999999
], [0.0, 0.0, 0.0, 1.0]]) # advio-04
elif 'advio-23' in args.dataset_dir:
global_pose = np.array([[
-0.02024017794777988, -0.7758527702428, 0.630589204478,
-0.005759389
], [0.11342629147720007, 0.62486446287, 0.7724499038534, -0.09049783],
[
-0.993340194646, 0.08715994761339996,
0.0753547505262201, -0.001374606
], [0.0, 0.0, 0.0, 1.0]]) # advio-23
print(str(global_pose))
poses = [global_pose[0:3, :].reshape(1, 12)]
n = len(test_files)
tensor_img1 = load_tensor_image(test_files[0], args)
for iter in tqdm(range(n - 1)):
tensor_img2 = load_tensor_image(test_files[iter + 1], args)
pose = pose_net(tensor_img1, tensor_img2)
pose_mat = pose_vec2mat(pose).squeeze(0).cpu().numpy()
pose_mat = np.vstack([pose_mat, np.array([0, 0, 0, 1])])
global_pose = global_pose @ np.linalg.inv(pose_mat)
poses.append(global_pose[0:3, :].reshape(1, 12))
# update
tensor_img1 = tensor_img2
poses = np.concatenate(poses, axis=0)
filename = Path(args.output_dir + args.sequence + ".txt")
np.savetxt(filename, poses, delimiter=' ', fmt='%1.8e')
