def test_output(self):
a = ArrayKey("A")
b = ArrayKey("B")
source_a = TestSourceRandomLocation(a)
source_b = TestSourceRandomLocation(b)
pipeline = (source_a, source_b) + \
MergeProvider() + CustomRandomLocation()
with build(pipeline):
for i in range(10):
batch = pipeline.request_batch(
BatchRequest({
a: ArraySpec(roi=Roi((0, 0, 0), (20, 20, 20))),
b: ArraySpec(roi=Roi((0, 0, 0), (20, 20, 20)))
}))
self.assertTrue(np.sum(batch.arrays[a].data) > 0)
self.assertTrue(np.sum(batch.arrays[b].data) > 0)
# Request a ROI with the same shape as the entire ROI
full_roi_a = Roi((0, 0, 0), source_a.roi.get_shape())
full_roi_b = Roi((0, 0, 0), source_b.roi.get_shape())
batch = pipeline.request_batch(
BatchRequest({
a: ArraySpec(roi=full_roi_a),
b: ArraySpec(roi=full_roi_b)
}))
def test_placeholder(self):
test_labels = ArrayKey("TEST_LABELS")
test_points = GraphKey("TEST_POINTS")
pipeline = (
PointTestSource3D() + RandomLocation(ensure_nonempty=test_points) +
ElasticAugment([10, 10, 10], [0.1, 0.1, 0.1], [0, 2.0 * math.pi]) +
Snapshot(
{test_labels: "volumes/labels"},
output_dir=self.path_to(),
output_filename="elastic_augment_test{id}-{iteration}.hdf",
))
with build(pipeline):
for i in range(2):
request_size = Coordinate((40, 40, 40))
request_a = BatchRequest(random_seed=i)
request_a.add(test_points, request_size)
request_a.add(test_labels, request_size, placeholder=True)
request_b = BatchRequest(random_seed=i)
request_b.add(test_points, request_size)
request_b.add(test_labels, request_size)
batch_a = pipeline.request_batch(request_a)
batch_b = pipeline.request_batch(request_b)
points_a = batch_a[test_points].nodes
points_b = batch_b[test_points].nodes
for a, b in zip(points_a, points_b):
assert all(np.isclose(a.location, b.location))
def test_ensure_center_non_zero(self):
path = Path(self.path_to("test_swc_source.swc"))
# write test swc
self._write_swc(path, self._toy_swc_points().to_nx_graph())
# read arrays
swc = PointsKey("SWC")
img = ArrayKey("IMG")
pipeline = (SwcFileSource(
path, [swc], [PointsSpec(roi=Roi((0, 0, 0), (11, 11, 11)))]) +
RandomLocation(ensure_nonempty=swc, ensure_centered=True) +
RasterizeSkeleton(
points=swc,
array=img,
array_spec=ArraySpec(
interpolatable=False,
dtype=np.uint32,
voxel_size=Coordinate((1, 1, 1)),
),
))
request = BatchRequest()
request.add(img, Coordinate((5, 5, 5)))
request.add(swc, Coordinate((5, 5, 5)))
with build(pipeline):
batch = pipeline.request_batch(request)
data = batch[img].data
g = batch[swc]
assert g.num_vertices() > 0
self.assertNotEqual(data[tuple(np.array(data.shape) // 2)], 0)
def test_voxel_size(self):
locations = [[0, 0, 0], [91, 20, 20], [42, 24, 57]]
pipeline = (
ExampleSourceSpecifiedLocation(roi=Roi((0, 0, 0), (100, 100, 100)),
voxel_size=(5, 2, 2)) +
SpecifiedLocation(
locations, choose_randomly=False, extra_data=None,
jitter=None))
with build(pipeline):
batch = pipeline.request_batch(
BatchRequest({
ArrayKeys.RAW:
ArraySpec(roi=Roi((0, 0, 0), (20, 20, 20)))
}))
# first locations is skipped
# second should start at [80/5, 10/2, 10/2] = [16, 5, 5]
self.assertEqual(batch.arrays[ArrayKeys.RAW].data[0, 0, 0], 40255)
batch = pipeline.request_batch(
BatchRequest({
ArrayKeys.RAW:
ArraySpec(roi=Roi((0, 0, 0), (20, 20, 20)))
}))
# third should start at [30/5, 14/2, 48/2] = [6, 7, 23]
self.assertEqual(batch.arrays[ArrayKeys.RAW].data[0, 0, 0], 15374)
def test_precache(self):
logging.getLogger("gunpowder.torch.nodes.predict").setLevel(
logging.INFO)
a = ArrayKey("A")
pred = ArrayKey("PRED")
model = ExampleModel()
reference_request = BatchRequest()
reference_request[a] = ArraySpec(roi=Roi((0, 0), (7, 7)))
reference_request[pred] = ArraySpec(roi=Roi((1, 1), (5, 5)))
source = ExampleTorchTrain2DSource()
predict = Predict(
model=model,
inputs={"a": a},
outputs={0: pred},
array_specs={pred: ArraySpec()},
)
pipeline = source + predict + PreCache(cache_size=3, num_workers=2)
request = BatchRequest({
a: ArraySpec(roi=Roi((0, 0), (17, 17))),
pred: ArraySpec(roi=Roi((0, 0), (15, 15))),
})
# train for a couple of iterations
with build(pipeline):
batch = pipeline.request_batch(request)
assert pred in batch
def test_merge_basics(self):
voxel_size = (1, 1, 1)
GraphKey("PRESYN")
ArrayKey("GT_LABELS")
graphsource = GraphTestSource(voxel_size)
arraysource = ArrayTestSoure(voxel_size)
pipeline = (graphsource, arraysource) + MergeProvider() + RandomLocation()
window_request = Coordinate((50, 50, 50))
with build(pipeline):
# Check basic merging.
request = BatchRequest()
request.add((GraphKeys.PRESYN), window_request)
request.add((ArrayKeys.GT_LABELS), window_request)
batch_res = pipeline.request_batch(request)
self.assertTrue(ArrayKeys.GT_LABELS in batch_res.arrays)
self.assertTrue(GraphKeys.PRESYN in batch_res.graphs)
# Check that request of only one source also works.
request = BatchRequest()
request.add((GraphKeys.PRESYN), window_request)
batch_res = pipeline.request_batch(request)
self.assertFalse(ArrayKeys.GT_LABELS in batch_res.arrays)
self.assertTrue(GraphKeys.PRESYN in batch_res.graphs)
# Check that it fails, when having two sources that provide the same type.
arraysource2 = ArrayTestSoure(voxel_size)
pipeline_fail = (arraysource, arraysource2) + MergeProvider() + RandomLocation()
with self.assertRaises(PipelineSetupError):
with build(pipeline_fail):
pass
def test_3d(self):
test_graph = GraphKey("TEST_GRAPH")
graph_spec = GraphSpec(roi=Roi((0, 0, 0), (5, 5, 5)))
test_array = ArrayKey("TEST_ARRAY")
array_spec = ArraySpec(
roi=Roi((0, 0, 0), (5, 5, 5)), voxel_size=Coordinate((1, 1, 1))
)
test_array2 = ArrayKey("TEST_ARRAY2")
array2_spec = ArraySpec(
roi=Roi((0, 0, 0), (5, 5, 5)), voxel_size=Coordinate((1, 1, 1))
)
snapshot_request = BatchRequest()
snapshot_request.add(test_graph, Coordinate((5, 5, 5)))
pipeline = ExampleSource(
[test_graph, test_array, test_array2], [graph_spec, array_spec, array2_spec]
) + Snapshot(
{
test_graph: "graphs/graph",
test_array: "volumes/array",
test_array2: "volumes/array2",
},
output_dir=str(self.test_dir),
every=2,
additional_request=snapshot_request,
output_filename="snapshot.hdf",
)
snapshot_file_path = Path(self.test_dir, "snapshot.hdf")
with build(pipeline):
request = BatchRequest()
roi = Roi((0, 0, 0), (5, 5, 5))
request[test_array] = ArraySpec(roi=roi)
request[test_array2] = ArraySpec(roi=roi)
pipeline.request_batch(request)
assert snapshot_file_path.exists()
f = h5py.File(snapshot_file_path)
assert f["volumes/array"] is not None
assert f["graphs/graph-ids"] is not None
snapshot_file_path.unlink()
pipeline.request_batch(request)
assert not snapshot_file_path.exists()
def test_without_placeholder(self):
test_labels = ArrayKey("TEST_LABELS")
test_points = GraphKey("TEST_POINTS")
pipeline = (
PointTestSource3D() + RandomLocation(ensure_nonempty=test_points) +
ElasticAugment([10, 10, 10], [0.1, 0.1, 0.1], [0, 2.0 * math.pi]) +
Snapshot(
{test_labels: "volumes/labels"},
output_dir=self.path_to(),
output_filename="elastic_augment_test{id}-{iteration}.hdf",
))
with build(pipeline):
for i in range(2):
request_size = Coordinate((40, 40, 40))
request_a = BatchRequest(random_seed=i)
request_a.add(test_points, request_size)
request_b = BatchRequest(random_seed=i)
request_b.add(test_points, request_size)
request_b.add(test_labels, request_size)
# No array to provide a voxel size to ElasticAugment
with pytest.raises(PipelineRequestError):
pipeline.request_batch(request_a)
batch_b = pipeline.request_batch(request_b)
self.assertIn(test_labels, batch_b)
def test_embedding_pipeline(
tmpdir, aux_task, blend_mode, fusion_pipeline, train_embedding, snapshot_every
):
setup_config = DEFAULT_CONFIG
setup_config["FUSION_PIPELINE"] = fusion_pipeline
setup_config["TRAIN_EMBEDDING"] = train_embedding
setup_config["SNAPSHOT_EVERY"] = snapshot_every
setup_config["TENSORBOARD_LOG_DIR"] = tmpdir
setup_config["SNAPSHOT_DIR"] = tmpdir
setup_config["SNAPSHOT_FILE_NAME"] = "test_snapshot"
setup_config["MATCHING_FAILURES_DIR"] = None
setup_config["BLEND_MODE"] = blend_mode
setup_config["AUX_TASK"] = aux_task
voxel_size = Coordinate(setup_config["VOXEL_SIZE"])
output_size = Coordinate(setup_config["OUTPUT_SHAPE"]) * voxel_size
input_size = Coordinate(setup_config["INPUT_SHAPE"]) * voxel_size
pipeline, raw, output, inputs = embedding_pipeline(
setup_config, get_test_data_sources
)
request = BatchRequest()
request.add(raw, input_size)
request.add(output, output_size)
for key in inputs:
request.add(key, output_size)
with build(pipeline):
batch = pipeline.request_batch(request)
assert output in batch
assert raw in batch
def process_function():
scheduler = Client()
worker_id = scheduler.context.worker_id
num_workers = scheduler.context.num_workers
gpu = actor_id_to_gpu_mapping(worker_id)
os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu)
_logger.info("Worker %d uses gpu %d with %d workers", worker_id, gpu,
num_workers)
_logger.info("Environment:")
for name in os.environ.keys():
_logger.info(' %s:%s', name, os.environ[name])
# _logger.info("GPU is available: %s", tf.test.is_gpu_available())
# from tensorflow.python.client import device_lib
# def get_available_gpus():
# local_device_protos = device_lib.list_local_devices()
# return [x.name for x in local_device_protos if x.device_type == 'GPU']
# available_gpus = get_available_gpus()
# for gpu in available_gpus:
# print("Worker %d sees gpus %s" % (actor_id, available_gpus))
import tensorflow as tf
with tf.device('/gpu:%d' % 0):
from gunpowder import ArrayKey, ArraySpec, build, BatchRequest, DaisyRequestBlocks
_RAW = ArrayKey('RAW')
roi_map = {
ArrayKey('OUTPUT_%d' % i): 'write_roi'
for i in range(len(outputs))
}
roi_map[_RAW] = 'read_roi'
reference = BatchRequest()
reference[_RAW] = ArraySpec(roi=None, voxel_size=input_voxel_size)
for i in range(len(outputs)):
reference[ArrayKey('OUTPUT_%d' % i)] = ArraySpec(
roi=None, voxel_size=output_voxel_size)
pipeline = pipeline_factory()
pipeline += DaisyRequestBlocks(reference=reference,
roi_map=roi_map,
num_workers=num_cpu_workers)
with build(pipeline):
pipeline.request_batch(BatchRequest())
def prepare(self, request):
deps = BatchRequest()
if self.descriptor in request:
dims = len(request[self.descriptor].roi.get_shape())
if dims == 2:
self.context = self.context[0:2]
# increase segmentation ROI to fit Gaussian
context_roi = request[self.descriptor].roi.grow(
self.context, self.context)
# ensure context roi is multiple of voxel size
context_roi = context_roi.snap_to_grid(self.voxel_size,
mode='shrink')
grown_roi = request[self.segmentation].roi.union(context_roi)
deps[self.segmentation] = request[self.descriptor].copy()
deps[self.segmentation].roi = grown_roi
else:
self.skip = True
if self.unlabelled:
deps[self.unlabelled] = deps[self.segmentation].copy()
if self.labels_mask:
deps[self.labels_mask] = deps[self.segmentation].copy()
return deps
def test_relabel_components(self):
path = Path(self.path_to("test_swc_source.swc"))
# write test swc
self._write_swc(path, self._toy_swc_points().to_nx_graph())
# read arrays
swc = GraphKey("SWC")
source = SwcFileSource(path, [swc])
with build(source):
batch = source.request_batch(
BatchRequest({swc:
GraphSpec(roi=Roi((0, 1, 5), (11, 10, 1)))}))
temp_g = batch.points[swc]
temp_g.relabel_connected_components()
previous_label = None
ccs = list(temp_g.connected_components)
self.assertEqual(len(ccs), 3)
for cc in ccs:
self.assertEqual(len(cc), 10)
label = None
for point_id in cc:
if label is None:
label = temp_g.node(point_id).attrs["component"]
self.assertNotEqual(label, previous_label)
self.assertEqual(
temp_g.node(point_id).attrs["component"], label)
previous_label = label
def prepare(self, request):
deps = BatchRequest()
deps[self.graph] = request[self.graph].copy()
assert (request[self.graph].roi.get_shape() == self.read_size
), f"Got wrong size graph in request"
return deps
def test_6_neighborhood():
# array keys
graph = GraphKey("GRAPH")
neighborhood = ArrayKey("NEIGHBORHOOD")
neighborhood_mask = ArrayKey("NEIGHBORHOOD_MASK")
distance = 1
pipeline = TestSource(graph) + Neighborhood(
graph,
neighborhood,
neighborhood_mask,
distance,
array_specs={
neighborhood: ArraySpec(voxel_size=Coordinate((1, 1, 1))),
neighborhood_mask: ArraySpec(voxel_size=Coordinate((1, 1, 1))),
},
k=6,
)
request = BatchRequest()
request[neighborhood] = ArraySpec(roi=Roi((0, 0, 0), (10, 10, 10)))
request[neighborhood_mask] = ArraySpec(roi=Roi((0, 0, 0), (10, 10, 10)))
with build(pipeline):
batch = pipeline.request_batch(request)
n_data = batch[neighborhood].data
n_mask = batch[neighborhood_mask].data
masked_ind = list(
set([(0, i, 0) for i in range(10) if i not in [0, 4]] +
[(i, 5, 0)
for i in range(10)] + [(i, 4, 0)
for i in range(10) if i not in [0]]))
assert all(n_mask[tuple(zip(*masked_ind))]
), f"expected {masked_ind} but saw {np.where(n_mask==1)}"
def run_augmentations(
data_providers,
roi,
keys=(),
augmentations=(),
voxel_size=lambda key: None):
request = BatchRequest()
for key in keys:
request[key] = ArraySpec(roi(key).snap_to_grid(voxel_size(key)), voxel_size=voxel_size(key))
logger.debug('Requesting batch with request %s', request)
data_sources = tuple(provider for provider in data_providers)
snapshot = SnapshotAsDict()
pipeline = data_sources + RandomProvider() + snapshot
for augmentation in augmentations:
pipeline += augmentation
with build(pipeline) as b:
logging.info("submitting request %s", request)
batch = b.request_batch(request)
logger.debug("Got snapshots from request %s: %s", request, snapshot.snapshots)
return batch, snapshot.snapshots[0]
def test_relabel_components(self):
path = Path(self.path_to("test_swc_source.swc"))
# write test swc
self._write_swc(path, self._toy_swc_points())
# read arrays
swc = PointsKey("SWC")
source = SwcFileSource(path, swc)
with build(source):
batch = source.request_batch(
BatchRequest(
{swc: PointsSpec(roi=Roi((0, 1, 0), (11, 10, 1)))}))
temp_g = nx.DiGraph()
for point_id, point in batch.points[swc].data.items():
temp_g.add_node(point.point_id, label_id=point.label_id)
if (point.parent_id != -1 and point.parent_id != point.point_id
and point.parent_id in batch.points[swc].data):
temp_g.add_edge(point.point_id, point.parent_id)
previous_label = None
ccs = list(nx.weakly_connected_components(temp_g))
self.assertEqual(len(ccs), 3)
for cc in ccs:
self.assertEqual(len(cc), 10)
label = None
for point_id in cc:
if label is None:
label = temp_g.nodes[point_id]["label_id"]
self.assertNotEqual(label, previous_label)
self.assertEqual(temp_g.nodes[point_id]["label_id"], label)
previous_label = label
def test_with_edge(self):
graph_with_edge = GraphKey("TEST_GRAPH_WITH_EDGE")
array_with_edge = ArrayKey("RASTERIZED_EDGE")
pipeline = GraphTestSourceWithEdge() + RasterizeGraph(
GraphKeys.TEST_GRAPH_WITH_EDGE,
ArrayKeys.RASTERIZED_EDGE,
ArraySpec(voxel_size=(1, 1, 1)),
settings=RasterizationSettings(0.5),
)
with build(pipeline):
request = BatchRequest()
roi = Roi((0, 0, 0), (10, 10, 10))
request[GraphKeys.TEST_GRAPH_WITH_EDGE] = GraphSpec(roi=roi)
request[ArrayKeys.RASTERIZED_EDGE] = ArraySpec(roi=roi)
batch = pipeline.request_batch(request)
rasterized = batch.arrays[ArrayKeys.RASTERIZED_EDGE].data
assert (
rasterized.sum() == 10
), f"rasterized has ones at: {np.where(rasterized==1)}"
def test_mirror(self):
test_graph = GraphKey("TEST_GRAPH")
pipeline = TestSource() + SimpleAugment(
mirror_only=[0, 1, 2], transpose_only=[]
)
request = BatchRequest()
request[GraphKeys.TEST_GRAPH] = GraphSpec(roi=Roi((0, 20, 33), (100, 100, 120)))
possible_loc = [[50, 49], [70, 29], [100, 86]]
with build(pipeline):
seen_mirrored = False
for i in range(100):
batch = pipeline.request_batch(request)
assert len(list(batch[GraphKeys.TEST_GRAPH].nodes)) == 1
node = list(batch[GraphKeys.TEST_GRAPH].nodes)[0]
logging.debug(node.location)
assert all(
[
node.location[dim] in possible_loc[dim]
for dim in range(3)
]
)
seen_mirrored = seen_mirrored or any(
[node.location[dim] == possible_loc[dim][1] for dim in range(3)]
)
assert Roi((0, 20, 33), (100, 100, 120)).contains(batch[GraphKeys.TEST_GRAPH].spec.roi)
assert batch[GraphKeys.TEST_GRAPH].spec.roi.contains(node.location)
assert seen_mirrored
def test_square(self):
test_graph = GraphKey("TEST_GRAPH")
test_array1 = ArrayKey("TEST_ARRAY1")
test_array2 = ArrayKey("TEST_ARRAY2")
pipeline = ((ArrayTestSource(), TestSource()) + MergeProvider() +
Pad(test_array1, None) + Pad(test_array2, None) + Pad(test_graph, None)
+ SimpleAugment(
mirror_only=[1,2], transpose_only=[1,2]
))
request = BatchRequest()
request[GraphKeys.TEST_GRAPH] = GraphSpec(roi=Roi((0, 50, 65), (100, 100, 100)))
request[ArrayKeys.TEST_ARRAY1] = ArraySpec(roi=Roi((0, 0, 15), (100, 200, 200)))
request[ArrayKeys.TEST_ARRAY2] = ArraySpec(roi=Roi((0, 50, 65), (100, 100, 100)))
with build(pipeline):
for i in range(100):
batch = pipeline.request_batch(request)
assert len(list(batch[GraphKeys.TEST_GRAPH].nodes)) == 1
for (array_key, array) in batch.arrays.items():
assert batch.arrays[array_key].data.shape == batch.arrays[array_key].spec.roi.get_shape()
def prepare(self, request):
deps = BatchRequest()
deps[self.dense_mst] = request[self.mst].copy()
deps[self.mst] = request[self.mst].copy()
deps[self.embeddings] = ArraySpec(roi=request[self.mst].roi)
return deps
def prepare(self, request):
deps = BatchRequest()
deps[self.msts[0]] = request[self.msts[1]].copy()
if (self.msts_dense is not None) and (self.msts_dense[1] in request):
deps[self.msts_dense[0]] = request[self.msts_dense[1]].copy()
return deps
def test_prepare1(self):
key = ArrayKey("TEST_ARRAY")
spec = ArraySpec(voxel_size=Coordinate((1, 1)), interpolatable=True)
hdf5_source = Hdf5Source(self.fake_data_file, {key: "testdata"},
array_specs={key: spec})
request = BatchRequest()
shape = Coordinate((3, 3))
request.add(key, shape, voxel_size=Coordinate((1, 1)))
shift_node = ShiftAugment(sigma=1, shift_axis=0)
with build((hdf5_source + shift_node)):
shift_node.prepare(request)
self.assertTrue(shift_node.ndim == 2)
self.assertTrue(shift_node.shift_sigmas == tuple([0.0, 1.0]))
def prepare(self, request):
assert ArrayKeys.C in request
dependencies = BatchRequest()
dependencies[ArrayKeys.B] = ArraySpec(request[ArrayKeys.C].roi.grow(
self.context, self.context))
return dependencies
def prepare(self, request: BatchRequest):
deps = BatchRequest()
if self.output is not None:
deps[self.array] = request[self.output].copy()
else:
deps[self.array] = request[self.array].copy()
return deps
def test_pipeline2(self):
key = ArrayKey("TEST_ARRAY")
spec = ArraySpec(voxel_size=Coordinate((3, 1)), interpolatable=True)
hdf5_source = Hdf5Source(self.fake_data_file, {key: "testdata"},
array_specs={key: spec})
request = BatchRequest()
shape = Coordinate((3, 3))
request.add(key, shape, voxel_size=Coordinate((3, 1)))
shift_node = ShiftAugment(prob_slip=0.2,
prob_shift=0.2,
sigma=1,
shift_axis=0)
with build((hdf5_source + shift_node)) as b:
b.request_batch(request)
def prepare(self, request: BatchRequest, seed: int,
direction: Coordinate) -> Tuple[BatchRequest, int]:
"""
Only request everything with the given seed
"""
dps = BatchRequest(random_seed=seed)
if self.nonempty_placeholder is not None:
# request nonempty placeholder of size request total roi
# grow such that it can be cropped down to two different locations
growth = self._get_growth()
total_roi = request.get_total_roi()
grown_roi = total_roi.grow(growth, growth)
dps[self.nonempty_placeholder] = GraphSpec(roi=grown_roi,
placeholder=True)
# handle smaller requests
array_keys = list(request.array_specs.keys())
voxel_size = self.spec.get_lcm_voxel_size(array_keys)
direction = Coordinate(direction)
direction -= Coordinate(
tuple(np.array(direction) % np.array(voxel_size)))
if any([points in request for points in self.points]):
dps[self.point_source] = copy.deepcopy(request[self.points[0]])
dps[self.point_source].roi = dps[self.point_source].roi.shift(
direction)
if any([array in request for array in self.arrays]):
dps[self.array_source] = copy.deepcopy(request[self.arrays[0]])
dps[self.array_source].roi = dps[self.array_source].roi.shift(
direction)
if any([labels in request for labels in self.labels]):
dps[self.label_source] = copy.deepcopy(request[self.labels[0]])
dps[self.label_source].roi = dps[self.label_source].roi.shift(
direction)
for source, targets in self.extra_keys.items():
if targets[0] in request:
dps[source] = copy.deepcopy(request[targets[0]])
dps[source].roi = dps[source].roi.shift(direction)
return dps
def test_transpose():
voxel_size = Coordinate((20, 20))
graph_key = GraphKey("GRAPH")
array_key = ArrayKey("ARRAY")
graph = Graph(
[Node(id=1, location=np.array([450, 550]))],
[],
GraphSpec(roi=Roi((100, 200), (800, 600))),
)
data = np.zeros([40, 30])
data[17, 17] = 1
array = Array(
data, ArraySpec(roi=Roi((100, 200), (800, 600)),
voxel_size=voxel_size))
default_pipeline = (
(GraphSource(graph_key, graph), ArraySource(array_key, array)) +
MergeProvider() + SimpleAugment(
mirror_only=[], transpose_only=[0, 1], transpose_probs=[0, 0]))
transpose_pipeline = (
(GraphSource(graph_key, graph), ArraySource(array_key, array)) +
MergeProvider() + SimpleAugment(
mirror_only=[], transpose_only=[0, 1], transpose_probs=[1, 1]))
request = BatchRequest()
request[graph_key] = GraphSpec(roi=Roi((400, 500), (200, 300)))
request[array_key] = ArraySpec(roi=Roi((400, 500), (200, 300)))
with build(default_pipeline):
expected_location = [450, 550]
batch = default_pipeline.request_batch(request)
assert len(list(batch[graph_key].nodes)) == 1
node = list(batch[graph_key].nodes)[0]
assert all(np.isclose(node.location, expected_location))
node_voxel_index = Coordinate(
(node.location - batch[array_key].spec.roi.get_offset()) /
voxel_size)
assert (
batch[array_key].data[node_voxel_index] == 1
), f"Node at {np.where(batch[array_key].data == 1)} not {node_voxel_index}"
with build(transpose_pipeline):
expected_location = [410, 590]
batch = transpose_pipeline.request_batch(request)
assert len(list(batch[graph_key].nodes)) == 1
node = list(batch[graph_key].nodes)[0]
assert all(np.isclose(node.location, expected_location))
node_voxel_index = Coordinate(
(node.location - batch[array_key].spec.roi.get_offset()) /
voxel_size)
assert (
batch[array_key].data[node_voxel_index] == 1
), f"Node at {np.where(batch[array_key].data == 1)} not {node_voxel_index}"
def test_3d_basics(self):
test_labels = ArrayKey("TEST_LABELS")
test_points = GraphKey("TEST_POINTS")
test_raster = ArrayKey("TEST_RASTER")
pipeline = (
PointTestSource3D() + ElasticAugment(
[10, 10, 10],
[0.1, 0.1, 0.1],
# [0, 0, 0], # no jitter
[0, 2.0 * math.pi],
) + RasterizeGraph(
test_points,
test_raster,
settings=RasterizationSettings(radius=2, mode="peak"),
) + Snapshot(
{
test_labels: "volumes/labels",
test_raster: "volumes/raster"
},
dataset_dtypes={test_raster: np.float32},
output_dir=self.path_to(),
output_filename="elastic_augment_test{id}-{iteration}.hdf",
))
for _ in range(5):
with build(pipeline):
request_roi = Roi((-20, -20, -20), (40, 40, 40))
request = BatchRequest()
request[test_labels] = ArraySpec(roi=request_roi)
request[test_points] = GraphSpec(roi=request_roi)
request[test_raster] = ArraySpec(roi=request_roi)
batch = pipeline.request_batch(request)
labels = batch[test_labels]
points = batch[test_points]
# the point at (0, 0, 0) should not have moved
self.assertTrue(points.contains(0))
labels_data_roi = (
labels.spec.roi -
labels.spec.roi.get_begin()) / labels.spec.voxel_size
# points should have moved together with the voxels
for point in points.nodes:
loc = point.location - labels.spec.roi.get_begin()
loc = loc / labels.spec.voxel_size
loc = Coordinate(int(round(x)) for x in loc)
if labels_data_roi.contains(loc):
self.assertEqual(labels.data[loc], point.id)
def test_realistic_valid_examples(example, use_gurobi):
penalty_attr = "penalty"
location_attr = "location"
example_dir = Path(__file__).parent / "mouselight_examples" / "valid" / example
consensus = PointsKey("CONSENSUS")
skeletonization = PointsKey("SKELETONIZATION")
matched = PointsKey("MATCHED")
matched_with_fallback = PointsKey("MATCHED_WITH_FALLBACK")
inf_roi = Roi(Coordinate((None,) * 3), Coordinate((None,) * 3))
request = BatchRequest()
request[matched] = PointsSpec(roi=inf_roi)
request[matched_with_fallback] = PointsSpec(roi=inf_roi)
request[consensus] = PointsSpec(roi=inf_roi)
pipeline = (
(
GraphSource(example_dir / "graph.obj", [skeletonization]),
GraphSource(example_dir / "tree.obj", [consensus]),
)
+ MergeProvider()
+ TopologicalMatcher(
skeletonization,
consensus,
matched,
expected_edge_len=10,
match_distance_threshold=76,
max_gap_crossing=48,
use_gurobi=use_gurobi,
location_attr=location_attr,
penalty_attr=penalty_attr,
)
+ TopologicalMatcher(
skeletonization,
consensus,
matched_with_fallback,
expected_edge_len=10,
match_distance_threshold=76,
max_gap_crossing=48,
use_gurobi=use_gurobi,
location_attr=location_attr,
penalty_attr=penalty_attr,
with_fallback=True,
)
)
with build(pipeline):
batch = pipeline.request_batch(request)
consensus_ccs = list(batch[consensus].connected_components)
matched_with_fallback_ccs = list(batch[matched_with_fallback].connected_components)
matched_ccs = list(batch[matched].connected_components)
assert len(matched_ccs) == len(consensus_ccs)
def test_output(self):
meta_base = self.path_to('tf_graph')
ArrayKey('A')
ArrayKey('B')
ArrayKey('C')
ArrayKey('GRADIENT_A')
# create model meta graph file and get input/output names
(a, b, c, optimizer, loss) = self.create_meta_graph(meta_base)
source = ExampleTensorflowTrainSource()
train = Train(
meta_base,
optimizer=optimizer,
loss=loss,
inputs={a: ArrayKeys.A, b: ArrayKeys.B},
outputs={c: ArrayKeys.C},
gradients={a: ArrayKeys.GRADIENT_A},
save_every=100)
pipeline = source + train
request = BatchRequest({
ArrayKeys.A: ArraySpec(roi=Roi((0, 0), (2, 2))),
ArrayKeys.B: ArraySpec(roi=Roi((0, 0), (2, 2))),
ArrayKeys.C: ArraySpec(roi=Roi((0, 0), (2, 2))),
ArrayKeys.GRADIENT_A: ArraySpec(roi=Roi((0, 0), (2, 2))),
})
# train for a couple of iterations
with build(pipeline):
batch = pipeline.request_batch(request)
self.assertAlmostEqual(batch.loss, 9.8994951)
gradient_a = batch.arrays[ArrayKeys.GRADIENT_A].data
self.assertTrue(gradient_a[0, 0] < gradient_a[0, 1])
self.assertTrue(gradient_a[0, 1] < gradient_a[1, 0])
self.assertTrue(gradient_a[1, 0] < gradient_a[1, 1])
for i in range(200-1):
loss1 = batch.loss
batch = pipeline.request_batch(request)
loss2 = batch.loss
self.assertLess(loss2, loss1)
# resume training
with build(pipeline):
for i in range(100):
loss1 = batch.loss
batch = pipeline.request_batch(request)
loss2 = batch.loss
self.assertLess(loss2, loss1)