def get_gpu_tensor_if_possible(self, data: T) -> Any:
""""
Get a cuda tensor if this transform was cuda enabled and a GPU is available, otherwise
return the input.
"""
import torch
if isinstance(data, torch.Tensor):
if self.use_gpu and not is_gpu_tensor(data):
return data.cuda()
else:
return data
else:
return data
def test_ct_range_manual(
image_rand_pos_gpu: Union[torch.Tensor, np.ndarray]) -> None:
image_out = CTRange.transform(data=image_rand_pos_gpu,
output_range=output,
window=window,
level=level,
use_gpu=use_gpu)
if use_gpu:
assert is_gpu_tensor(image_out)
image_out = image_out.cpu().numpy()
assert np.mean(image_out) == approx(0.0929241235)
assert_image_out_datatype(image_out)
def test_ct_range_liver(
image_rand_pos_gpu: Union[torch.Tensor, np.ndarray]) -> None:
image_out = CTRange.transform(data=image_rand_pos_gpu,
output_range=output,
window=200,
level=55,
use_gpu=use_gpu)
if use_gpu:
assert is_gpu_tensor(image_out)
image_out = image_out.cpu().numpy()
assert np.mean(image_out, dtype=np.float) == approx(0.9399296555978557)
assert_image_out_datatype(image_out)
def test_transform_compose(use_gpu: bool = False) -> None:
class Identity(Transform3D[torch.Tensor]):
def __call__(self, sample: torch.Tensor) -> torch.Tensor:
return self.get_gpu_tensor_if_possible(sample)
class Square(Transform3D[torch.Tensor]):
def __call__(self, sample: torch.Tensor) -> torch.Tensor:
return self.get_gpu_tensor_if_possible(sample)**2
a = torch.randint(low=2, high=4, size=[1])
if use_gpu:
a = a.cuda()
# test that composition of multiple identity operations holds
identity_compose = Compose3D([Identity(use_gpu=use_gpu)] * 3)
a_t = identity_compose(a)
assert torch.equal(Compose3D.apply(identity_compose, a), a_t)
assert torch.equal(a_t, a)
assert is_gpu_tensor(a_t) == use_gpu
# test that composition of multiple square operations holds
square_compose = Compose3D([Square(use_gpu=use_gpu)] * 3)
assert torch.equal(square_compose(a), a**8)
assert torch.equal(Compose3D.apply(square_compose, a), a**8)