def compress_mags(
source_path: Path,
layer_name: str,
target_path: Optional[Path] = None,
mags: Optional[List[Mag]] = None,
args: Optional[Namespace] = None,
) -> None:
if target_path is None:
target = source_path.with_suffix(".tmp")
else:
target = target_path
layer = Dataset.open(source_path).get_layer(layer_name)
if mags is None:
mags = list(layer.mags.keys())
for mag, mag_view in Dataset.open(source_path).get_layer(
layer_name).mags.items():
if mag in mags:
mag_view.compress(target_path=target, args=args)
if target_path is None:
backup_dir = source_path.with_suffix(BACKUP_EXT)
(backup_dir / layer_name).mkdir(parents=True, exist_ok=True)
for mag in mags:
(source_path / layer_name / str(mag)).rename(
(backup_dir / layer_name / str(mag)))
(target / layer_name / str(mag)).rename(
str(source_path / layer_name / str(mag)), )
rmtree(target)
logging.info(
"Old files are still present in '{0}.bak'. Please remove them when not required anymore."
.format(source_path))
def test_downsampling(sample_wkw_path: Path, tmp_path: Path,
tiff_mag_2_reference_path: Path) -> None:
copytree(sample_wkw_path, tmp_path)
Dataset.open(tmp_path).get_layer("color").delete_mag("2")
check_call(
"python",
"-m",
"wkcuber.downsampling",
"--jobs",
2,
"--max",
8,
"--buffer_cube_size",
128,
"--layer_name",
"color",
"--sampling_mode",
"isotropic",
tmp_path,
)
assert (tmp_path / "color" / "2").exists()
assert (tmp_path / "color" / "4").exists()
assert (tmp_path / "color" / "8").exists()
assert not (tmp_path / "color" / "16").exists()
assert count_wkw_files(tmp_path / "color" / "2") == 1
assert count_wkw_files(tmp_path / "color" / "4") == 1
assert count_wkw_files(tmp_path / "color" / "8") == 1
assert (Dataset.open(tmp_path).get_layer("color").get_mag(
"2").content_is_equal(
Dataset.open(tiff_mag_2_reference_path).get_layer("color").get_mag(
"2")))
def upsample_mags(
path: Path,
layer_name: Optional[str] = None,
from_mag: Optional[Mag] = None,
target_mag: Mag = Mag(1),
buffer_shape: Optional[Vec3Int] = None,
compress: bool = True,
args: Optional[Namespace] = None,
sampling_mode: Union[str, SamplingModes] = SamplingModes.ANISOTROPIC,
) -> None:
assert layer_name and from_mag or not layer_name and not from_mag, (
"You provided only one of the following "
"parameters: layer_name, from_mag but both "
"need to be set or none. If you don't provide "
"the parameters you need to provide the path "
"argument with the mag and layer to upsample"
" (e.g dataset/color/1)."
)
if not layer_name or not from_mag:
layer_name = path.parent.name
from_mag = Mag(path.name)
path = path.parent.parent
Dataset.open(path).get_layer(layer_name).upsample(
from_mag=from_mag,
finest_mag=target_mag,
compress=compress,
sampling_mode=sampling_mode,
buffer_shape=buffer_shape,
args=args,
)
def check_equality(source_path: Path,
target_path: Path,
args: Optional[Namespace] = None) -> None:
logging.info(f"Comparing {source_path} with {target_path}")
source_dataset = Dataset.open(source_path)
target_dataset = Dataset.open(target_path)
source_layer_names = set(source_dataset.layers.keys())
target_layer_names = set(target_dataset.layers.keys())
layer_names = list(source_layer_names)
if args is not None and args.layer_name is not None:
assert (
args.layer_name in source_layer_names
), f"Provided layer {args.layer_name} does not exist in source dataset."
assert (
args.layer_name in target_layer_names
), f"Provided layer {args.layer_name} does not exist in target dataset."
layer_names = [args.layer_name]
else:
assert (
source_layer_names == target_layer_names
), f"The provided input datasets have different layers: {source_layer_names} != {target_layer_names}"
for layer_name in layer_names:
logging.info(f"Checking layer_name: {layer_name}")
source_layer = source_dataset.layers[layer_name]
target_layer = target_dataset.layers[layer_name]
assert (
source_layer.bounding_box == target_layer.bounding_box
), f"The bounding boxes of {source_path}/{layer_name} and {target_path}/{layer_name} are not equal: {source_layer.bounding_box} != {target_layer.bounding_box}"
source_mags = set(source_layer.mags.keys())
target_mags = set(target_layer.mags.keys())
assert (
source_mags == target_mags
), f"The mags of {source_path}/{layer_name} and {target_path}/{layer_name} are not equal: {source_mags} != {target_mags}"
for mag in source_mags:
source_mag = source_layer.mags[mag]
target_mag = target_layer.mags[mag]
logging.info(f"Start verification of {layer_name} in mag {mag}")
assert source_mag.content_is_equal(target_mag, args)
logging.info(
f"The following datasets seem to be equal (with regard to the layers: {layer_names}):"
)
logging.info(source_path)
logging.info(target_path)
def compress_mag(
source_path: Path,
layer_name: str,
target_path: Path,
mag: Mag,
args: Optional[Namespace] = None,
) -> None:
Dataset.open(source_path).get_layer(layer_name).get_mag(mag).compress(
target_path=target_path, args=args)
def test_in_place_compression(sample_wkw_path: Path, tmp_path: Path) -> None:
copytree(sample_wkw_path, tmp_path)
check_call(
"python",
"-m",
"wkcuber.compress",
"--jobs",
2,
"--layer_name",
"color",
tmp_path,
)
assert Dataset.open(tmp_path).get_layer("color").get_mag(
"1").info.compression_mode
assert Dataset.open(tmp_path).get_layer("color").get_mag(
"2").info.compression_mode
def downsample_mags(
path: Path,
layer_name: Optional[str] = None,
from_mag: Optional[Mag] = None,
max_mag: Optional[Mag] = None,
interpolation_mode: str = "default",
buffer_shape: Optional[Vec3Int] = None,
compress: bool = True,
args: Optional[Namespace] = None,
sampling_mode: Union[str, SamplingModes] = SamplingModes.ANISOTROPIC,
force_sampling_scheme: bool = False,
) -> None:
"""
Argument `path` expects the directory containing the dataset.
Argument `layer_name` expects the name of the layer (color or segmentation).
Argument `from_mag` expects the resolution to base downsampling on.
For the other parameters see the CLI help or `Layer.downsample` and `Layer.downsampling_mag`.
"""
assert layer_name and from_mag or not layer_name and not from_mag, (
"You provided only one of the following "
"parameters: layer_name, from_mag but both "
"need to be set or none. If you don't provide "
"the parameters you need to provide the path "
"argument with the mag and layer to downsample"
" (e.g dataset/color/1).")
if not layer_name or not from_mag:
layer_name = path.parent.name
from_mag = Mag(path.name)
path = path.parent.parent
assert layer_name is not None # for mypy
assert from_mag is not None # for mypy
Dataset.open(path).get_layer(layer_name).downsample(
from_mag=from_mag,
coarsest_mag=max_mag,
interpolation_mode=interpolation_mode,
compress=compress,
sampling_mode=sampling_mode,
buffer_shape=buffer_shape,
force_sampling_scheme=force_sampling_scheme,
args=args,
)
def test_upsampling(sample_wkw_path: Path, tmp_path: Path,
tiff_mag_2_reference_path: Path) -> None:
copytree(sample_wkw_path, tmp_path)
color_layer = Dataset.open(tmp_path).get_layer("color")
color_layer.delete_mag("1")
color_layer.bounding_box = color_layer.bounding_box.align_with_mag(
Mag("2"), ceil=True)
check_call(
"python",
"-m",
"wkcuber.upsampling",
"--jobs",
2,
"--from_mag",
"2-2-2",
"--target_mag",
1,
"--buffer_cube_size",
1024,
"--layer_name",
"color",
tmp_path,
)
color_layer = Dataset.open(tmp_path).get_layer("color")
color_layer.delete_mag("2")
check_call(
"python",
"-m",
"wkcuber.downsampling",
"--jobs",
2,
"--from_mag",
1,
"--max",
2,
"--sampling_mode",
"isotropic",
"--buffer_cube_size",
256,
"--layer_name",
"color",
"--interpolation_mode",
"nearest",
tmp_path,
)
assert (Dataset.open(tmp_path).get_layer("color").get_mag("2").bounding_box
) == (Dataset.open(tiff_mag_2_reference_path).get_layer(
"color").get_mag("2").bounding_box)
assert (Dataset.open(tmp_path).get_layer("color").get_mag(
"2").content_is_equal(
Dataset.open(tiff_mag_2_reference_path).get_layer("color").get_mag(
"2")))
def sample_wkw_path() -> Path:
ds_path = TESTDATA_DIR / "tiff_wkw"
if ds_path.exists():
rmtree(ds_path)
check_call(
[
"python",
"-m",
"wkcuber.cubing",
"--jobs",
"2",
"--voxel_size",
"1,1,1",
str(TESTDATA_DIR / "tiff"),
str(ds_path),
]
)
copytree(
TESTDATA_DIR / "tiff" / "datasource-properties.wkw-fixture.json",
ds_path / PROPERTIES_FILE_NAME,
)
Dataset.open(ds_path).get_layer("color").downsample_mag(Mag(1), Mag(2))
return ds_path
def downsample_test_helper(WT1_path: Path, tmp_path: Path, use_compress: bool,
chunk_size: Vec3Int) -> None:
source_path = WT1_path
target_path = tmp_path / "WT1_wkw"
source_ds = Dataset.open(source_path)
target_ds = source_ds.copy_dataset(target_path,
chunk_size=chunk_size,
chunks_per_shard=16)
target_layer = target_ds.get_layer("color")
mag1 = target_layer.get_mag("1")
target_layer.delete_mag("2-2-1") # This is not needed for this test
# The bounding box has to be set here explicitly because the downsampled data is written to a different dataset.
target_layer.bounding_box = source_ds.get_layer("color").bounding_box
mag2 = target_layer._initialize_mag_from_other_mag("2", mag1, use_compress)
# The actual size of mag1 is (4600, 4600, 512).
# To keep this test case fast, we are only downsampling a small part
offset = (4096, 4096, 0)
size = (504, 504, 512)
source_buffer = mag1.read(
absolute_offset=offset,
size=size,
)[0]
assert np.any(source_buffer != 0)
downsample_cube_job(
(
mag1.get_view(absolute_offset=offset, size=size),
mag2.get_view(
absolute_offset=offset,
size=size,
),
0,
),
Vec3Int(2, 2, 2),
InterpolationModes.MAX,
Vec3Int.full(128),
)
assert np.any(source_buffer != 0)
target_buffer = mag2.read(absolute_offset=offset, size=size)[0]
assert np.any(target_buffer != 0)
assert np.all(target_buffer == downsample_cube(source_buffer, [2, 2, 2],
InterpolationModes.MAX))
def test_main(tmp_path: Path, order: str,
flip_axes: Optional[Tuple[int, int]]) -> None:
raw_file = tmp_path / "input.raw"
input_dtype = "float32"
shape = 64, 128, 256
data = np.arange(np.prod(shape), dtype=input_dtype).reshape(shape,
order=order)
with raw_file.open("wb") as f:
f.write(data.tobytes(order=order))
output_path = tmp_path / "output"
output_path.mkdir()
args_list = [
str(raw_file),
str(output_path),
"--input_dtype",
input_dtype,
"--shape",
",".join(str(i) for i in shape),
"--order",
order,
"--jobs",
"1",
]
if flip_axes is not None:
args_list.extend(
["--flip_axes", ",".join(str(a + 1) for a in flip_axes)])
args = create_parser().parse_args(args_list)
main(args)
dataset = Dataset.open(output_path)
layer = dataset.get_color_layers()[0]
mag_view = layer.get_mag(1)
view = mag_view.get_view()
read_data = view.read()
assert view.size == shape
assert view.get_dtype() == data.dtype
assert np.array_equal(
read_data[0],
data if flip_axes is None else np.flip(data, flip_axes),
)
def test_main(tmp_path: Path, category: str) -> None:
input_folder = tmp_path / "raw_dataset" / category
input_folder.mkdir(parents=True, exist_ok=True)
raw_file = input_folder / "input.tif"
input_dtype = "uint32"
shape = 64, 128, 256
data = np.arange(np.prod(shape), dtype=input_dtype).reshape(shape)
with TiffWriter(raw_file) as tif:
tif.write(data.transpose([2, 1, 0]))
output_path = tmp_path / "output_2"
output_path.mkdir()
args_list = [
str(tmp_path / "raw_dataset"),
str(output_path),
"--jobs",
"1",
"--voxel_size",
"11,11,11",
"--max_mag",
"4",
]
args = create_parser().parse_args(args_list)
cube_with_args(args)
dataset = Dataset.open(output_path)
if category == "color":
layer = dataset.get_color_layers()[0]
else:
layer = dataset.get_segmentation_layers()[0]
mag_view = layer.get_mag(1)
view = mag_view.get_view()
read_data = view.read()
assert view.size == shape
assert view.get_dtype() == data.dtype
assert np.array_equal(
read_data[0],
data,
)
def export_wkw_as_tiff(args: Namespace) -> None:
setup_logging(args)
mag_view = (Dataset.open(args.source_path).get_layer(
args.layer_name).get_mag(args.mag))
bbox = mag_view.bounding_box if args.bbox is None else args.bbox
logging.info(f"Starting tiff export for bounding box: {bbox}")
if args.tiles_per_dimension is not None:
args.tile_size = [
int(s.strip()) for s in args.tiles_per_dimension.split(",")
]
assert len(args.tile_size) == 2
logging.info(
f"Using tiling with {args.tile_size[0]},{args.tile_size[1]} tiles in the dimensions."
)
args.tile_size[0] = ceil(
bbox.in_mag(mag_view.mag).size.x / args.tile_size[0])
args.tile_size[1] = ceil(
bbox.in_mag(mag_view.mag).size.y / args.tile_size[1])
elif args.tile_size is not None:
args.tile_size = [int(s.strip()) for s in args.tile_size.split(",")]
assert len(args.tile_size) == 2
logging.info(
f"Using tiling with the size of {args.tile_size[0]},{args.tile_size[1]}."
)
args.batch_size = int(args.batch_size)
export_tiff_stack(
mag_view=mag_view,
bbox=bbox,
destination_path=args.destination_path,
name=args.name,
tiling_slice_size=args.tile_size,
batch_size=args.batch_size,
downsample=args.downsample,
args=args,
)
def test_export_nifti_file(tmp_path: Path) -> None:
destination_path = tmp_path / f"{DS_NAME}_nifti"
destination_path.mkdir()
bbox = BoundingBox((100, 100, 10), (100, 500, 50))
bbox_dict = bbox.to_config_dict()
args_list = [
"--source_path",
str(SOURCE_PATH),
"--destination_path",
str(destination_path),
"--name",
"test_export",
"--source_bbox",
bbox.to_csv(),
"--mag",
"1",
]
export_wkw_as_nifti_from_arg_list(args_list)
wk_ds = Dataset.open(SOURCE_PATH)
for layer_name, layer in wk_ds.layers.items():
correct_image = layer.get_mag(Mag(1)).read(bbox_dict["topleft"],
bbox_dict["size"])
# nifti is transposed
correct_image = correct_image.transpose(1, 2, 3, 0)
correct_image = np.squeeze(correct_image)
nifti_path = destination_path.joinpath(f"test_export_{layer_name}.nii")
assert nifti_path.is_file(
), f"Expected a nifti to be written at: {nifti_path}."
nifti = nib.load(str(nifti_path))
test_image = np.array(nifti.get_fdata())
assert np.array_equal(correct_image, test_image), (
f"The nifti file {nifti_path} that was written is not "
f"equal to the original wkw_file.")
def export_nifti(
source_path: Path,
source_bbox: Optional[BoundingBox],
mag: Mag,
destination_path: Path,
name: str,
padding: Optional[Tuple[int, ...]] = None,
) -> None:
dataset = Dataset.open(source_path)
for layer_name, layer in dataset.layers.items():
logging.info(f"Starting nifti export for bounding box: {source_bbox}")
export_layer_to_nifti(
source_path,
layer.bounding_box if source_bbox is None else source_bbox,
mag,
layer_name,
destination_path,
name + "_" + layer_name,
padding,
)
def export_layer_to_nifti(
source_path: Path,
source_bbox: BoundingBox,
mag: Mag,
layer_name: str,
destination_path: Path,
name: str,
padding: Optional[Tuple[int, ...]] = None,
) -> None:
dataset = Dataset.open(source_path)
layer = dataset.get_layer(layer_name)
mag_layer = layer.get_mag(mag)
is_segmentation_layer = layer.category == SEGMENTATION_CATEGORY
data = mag_layer.read(source_bbox.topleft, source_bbox.size)
data = data.transpose(1, 2, 3, 0)
logging.info(f"Shape with layer {data.shape}")
data = np.array(data)
if is_segmentation_layer and data.max() > 0:
factor = np.iinfo("uint8").max / data.max()
data = data * factor
data = data.astype(np.dtype("uint8"))
if padding:
assert len(padding) == 6, "padding needs 6 values"
padding_per_axis = list(zip(padding[:3], padding[3:]))
padding_per_axis.append((0, 0))
data = np.pad(data, padding_per_axis, mode="constant", constant_values=0)
img = nib.Nifti1Image(data, np.eye(4))
destination_file = str(destination_path.joinpath(name + ".nii"))
logging.info(f"Writing to {destination_file} with shape {data.shape}")
nib.save(img, destination_file)
f"Number of simultaneous upload processes. Defaults to {DEFAULT_SIMULTANEOUS_UPLOADS}.",
)
parser.add_argument(
"--name",
help=
"Specify a new name for the dataset. Defaults to the name specified in `datasource-properties.json`.",
default=None,
)
add_verbose_flag(parser)
return parser
if __name__ == "__main__":
setup_warnings()
args = create_parser().parse_args()
setup_logging(args)
url = (args.url if args.url is not None else environ.get(
"WK_URL", DEFAULT_WEBKNOSSOS_URL))
token = args.token if args.token is not None else environ.get(
"WK_TOKEN", None)
assert (
token is not None
), f"An auth token needs to be supplied either through the --token command line arg or the WK_TOKEN environment variable. Retrieve your auth token on {url}/auth/token."
with webknossos_context(url=url, token=token):
Dataset.open(args.source_path).upload(new_dataset_name=args.name,
jobs=args.jobs)
def test_anisotropic_downsampling(sample_wkw_path: Path,
tmp_path: Path) -> None:
copytree(sample_wkw_path, tmp_path)
# We need to delete mag two as it already exists. Then it is replaced by an anisotropic mag.
color_layer = Dataset.open(tmp_path).get_layer("color")
color_layer.delete_mag("2")
check_call(
"python",
"-m",
"wkcuber.downsampling",
"--jobs",
2,
"--from",
1,
"--max",
2,
"--sampling_mode",
"constant_z",
"--buffer_cube_size",
128,
"--layer_name",
"color",
tmp_path,
)
check_call(
"python",
"-m",
"wkcuber.downsampling",
"--jobs",
2,
"--from",
"2-2-1",
"--max",
4,
"--sampling_mode",
"constant_z",
"--buffer_cube_size",
128,
"--layer_name",
"color",
tmp_path,
)
assert (tmp_path / "color" / "2-2-1").exists()
assert (tmp_path / "color" / "4-4-1").exists()
assert count_wkw_files(tmp_path / "color" / "2-2-1") == 1
assert count_wkw_files(tmp_path / "color" / "4-4-1") == 1
check_call(
"python",
"-m",
"wkcuber.downsampling",
"--jobs",
2,
"--from",
"4-4-1",
"--max",
16,
"--buffer_cube_size",
128,
"--layer_name",
"color",
tmp_path,
)
assert (tmp_path / "color" / "8-8-4").exists()
assert (tmp_path / "color" / "16-16-8").exists()
assert count_wkw_files(tmp_path / "color" / "8-8-4") == 1
assert count_wkw_files(tmp_path / "color" / "16-16-8") == 1
type=parse_path,
)
parser.add_argument(
"--no_compression",
help="Use compression, default false",
type=bool,
default=False,
)
add_verbose_flag(parser)
add_distribution_flags(parser)
add_data_format_flags(parser)
return parser
if __name__ == "__main__":
setup_warnings()
args = create_parser().parse_args()
setup_logging(args)
Dataset.open(args.source_path).copy_dataset(
args.target_path,
data_format=args.data_format,
chunk_size=args.chunk_size,
chunks_per_shard=args.chunks_per_shard,
compress=not args.no_compression,
args=args,
)
def compress_mag_inplace(target_path: Path,
layer_name: str,
mag: Mag,
args: Optional[Namespace] = None) -> None:
Dataset.open(target_path).get_layer(layer_name).get_mag(mag).compress(
args=args)