def get_dataset(conv_type, task):
num_points = 1024
features = 2
batch_size = 2
if task == "object_detection":
include_box = True
else:
include_box = False
if conv_type.lower() == "dense":
num_points = 2048
batch_size = 1
if task == "registration":
if conv_type.lower() == "dense":
return PairMockDataset(features,
num_points=num_points,
batch_size=batch_size)
if conv_type.lower() == "sparse":
tr = Compose([
XYZFeature(True, True, True),
GridSampling3D(size=0.01, quantize_coords=True, mode="last")
])
return PairMockDatasetGeometric(features,
transform=tr,
num_points=num_points,
batch_size=batch_size)
return PairMockDatasetGeometric(features, batch_size=batch_size)
else:
if conv_type.lower() == "dense":
num_points = 2048
return MockDataset(
features,
num_points=num_points,
include_box=include_box,
panoptic=task == "panoptic",
batch_size=batch_size,
)
if conv_type.lower() == "sparse":
return MockDatasetGeometric(
features,
include_box=include_box,
panoptic=task == "panoptic",
transform=Compose([
XYZFeature(True, True, True),
GridSampling3D(size=0.01,
quantize_coords=True,
mode="last")
]),
num_points=num_points,
batch_size=batch_size,
)
return MockDatasetGeometric(
features,
batch_size=batch_size,
num_points=num_points,
include_box=include_box,
panoptic=task == "panoptic",
)
def get_dataset(conv_type, task):
features = 2
if task == "registration":
if conv_type.lower() == "dense":
return PairMockDataset(features, num_points=2048)
if conv_type.lower() == "sparse":
tr = Compose([
XYZFeature(True, True, True),
GridSampling(size=0.01,
quantize_coords=True,
mode="last")
])
return PairMockDatasetGeometric(features,
transform=tr,
num_points=1024)
return PairMockDatasetGeometric(features)
else:
if conv_type.lower() == "dense":
return MockDataset(features, num_points=2048)
if conv_type.lower() == "sparse":
return MockDatasetGeometric(features,
transform=GridSampling(
size=0.01,
quantize_coords=True,
mode="last"),
num_points=1024)
return MockDatasetGeometric(features)
def test_siamese_minkowski(self):
params = load_model_config("registration", "minkowski", "MinkUNet_Fragment")
transform = Compose(
[XYZFeature(True, True, True), GridSampling3D(size=0.01, quantize_coords=True, mode="last")]
)
dataset = PairMockDatasetGeometric(5, transform=transform, num_points=1024, is_pair_ind=True)
model = instantiate_model(params, dataset)
d = dataset[0]
model.set_input(d, device)
model.forward()
model.backward()
ratio = test_hasgrad(model)
if ratio < 1:
print(
"Model registration.minkowski.MinkUNet_Fragment has %i%% of parameters with 0 gradient" % (100 * ratio)
)
def test_siamese_minkowski(self):
params = load_model_config("registration", "minkowski",
"MinkUNet_Fragment")
transform = Compose([
XYZFeature(True, True, True),
GridSampling(size=0.01, quantize_coords=True, mode="last")
])
dataset = PairMockDatasetGeometric(5,
transform=transform,
num_points=1024,
is_pair_ind=True)
model = instantiate_model(params, dataset)
d = dataset[0]
model.set_input(d, device)
model.forward()
model.backward()
def test_XYZFeature(self):
pos = torch.from_numpy(np.asarray([[1, 2, 3], [4, 5, 6], [7, 8, 9]]))
data = Data(pos=pos)
t = XYZFeature()
data_out = t(data.clone())
x = data_out.z
self.assertEqual(np.array_equal(x, pos[:, -1]), True)
pos += 1
self.assertEqual(np.array_equal(x, pos[:, -1]), False)
self.assertIn("z", data_out.keys)
self.assertIn("pos", data_out.keys)
self.assertNotIn("x", data_out.keys)
self.assertNotIn("y", data_out.keys)