def main():
args = options()
torch.backends.cudnn.deterministic = True
testset = RegistrationData(ModelNet40Data(train=False, num_points=args.num_points, unseen=args.unseen),
partial_source=args.partial_source, noise=args.noise, outliers=args.outliers,
additional_params={'use_masknet': True})
test_loader = DataLoader(testset, batch_size=args.test_batch_size, shuffle=False, drop_last=False, num_workers=args.workers)
if not torch.cuda.is_available():
args.device = 'cpu'
args.device = torch.device(args.device)
# Load Pretrained MaskNet.
model = MaskNet()
if args.pretrained:
assert os.path.isfile(args.pretrained)
model.load_state_dict(torch.load(args.pretrained, map_location='cpu'))
model = model.to(args.device)
test(args, model, test_loader)
def main():
args = options()
torch.backends.cudnn.deterministic = True
if args.user_data:
template = np.random.randn(1, 100, 3) # Define/Read template point cloud. [Shape: BATCH x No. of Points x 3]
source = np.random.randn(1, 75, 3) # Define/Read source point cloud. [Shape: BATCH x No. of Points x 3]
mask = np.zeros((1, 100, 1)) # Define/Read mask for point cloud. [Not mandatory in testing]
igt = np.zeros((1, 4, 4)) # Define/Read igt transformation. [Not mandatory during testing]
testset = UserData(template=template, source=source, mask=None, igt=None)
elif args.any_data:
# Read Stanford bunny's point cloud.
bunny_path = os.path.join('learning3d/data/bunny/reconstruction/bun_zipper.ply')
if not os.path.exists(bunny_path):
print("Please download bunny dataset from http://graphics.stanford.edu/data/3Dscanrep/")
print("Add the extracted folder in learning3d/data/")
data = o3d.io.read_point_cloud(bunny_path)
points = np.array(data.points)
idx = np.arange(points.shape[0])
np.random.shuffle(idx)
points = points[idx[:args.num_points]]
testset = AnyData(pc=points, mask=True)
else:
testset = RegistrationData(ModelNet40Data(train=False, num_points=args.num_points, unseen=args.unseen),
partial_source=args.partial_source, noise=args.noise, outliers=args.outliers)
test_loader = DataLoader(testset, batch_size=args.test_batch_size, shuffle=False, drop_last=False, num_workers=args.workers)
if not torch.cuda.is_available():
args.device = 'cpu'
args.device = torch.device(args.device)
# Load Pretrained MaskNet.
model = MaskNet()
if args.pretrained:
assert os.path.isfile(args.pretrained)
model.load_state_dict(torch.load(args.pretrained, map_location='cpu'))
model = model.to(args.device)
test(args, model, test_loader)
def main():
args = options()
torch.backends.cudnn.deterministic = True
torch.manual_seed(args.seed)
torch.cuda.manual_seed_all(args.seed)
np.random.seed(args.seed)
boardio = SummaryWriter(log_dir='checkpoints/' + args.exp_name)
_init_(args)
textio = IOStream('checkpoints/' + args.exp_name + '/run.log')
textio.cprint(str(args))
trainset = RegistrationData('PointNetLK', ModelNet40Data(train=True))
testset = RegistrationData('PointNetLK', ModelNet40Data(train=False))
train_loader = DataLoader(trainset,
batch_size=args.batch_size,
shuffle=True,
drop_last=True,
num_workers=args.workers)
test_loader = DataLoader(testset,
batch_size=8,
shuffle=False,
drop_last=False,
num_workers=args.workers)
if not torch.cuda.is_available():
args.device = 'cpu'
args.device = torch.device(args.device)
# Create PointNet Model.
ptnet = PointNet(emb_dims=args.emb_dims, use_bn=True)
if args.transfer_ptnet_weights and os.path.isfile(
args.transfer_ptnet_weights):
ptnet.load_state_dict(
torch.load(args.transfer_ptnet_weights, map_location='cpu'))
if args.fine_tune_pointnet == 'tune':
pass
elif args.fine_tune_pointnet == 'fixed':
for param in ptnet.parameters():
param.requires_grad_(False)
model = PointNetLK(feature_model=ptnet)
model = model.to(args.device)
checkpoint = None
if args.resume:
assert os.path.isfile(args.resume)
checkpoint = torch.load(args.resume)
args.start_epoch = checkpoint['epoch']
model.load_state_dict(checkpoint['model'])
if args.pretrained:
assert os.path.isfile(args.pretrained)
model.load_state_dict(torch.load(args.pretrained, map_location='cpu'))
model.to(args.device)
if args.eval:
test(args, model, test_loader, textio)
else:
train(args, model, train_loader, test_loader, boardio, textio,
checkpoint)
from learning3d.data_utils import ModelNet40Data, ClassificationData, RegistrationData, FlowData
modelnet40 = ModelNet40Data(train=True, num_points=1024, download=True)
classification_data = ClassificationData(data_class=ModelNet40Data())
registration_data = RegistrationData(algorithm='PointNetLK',
data_class=ModelNet40Data(),
partial_source=False,
partial_template=False,
noise=False)
flow_data = FlowData()
print(flow_data)