def test_label_to_boundary_with_ignore(self):
size = 20
label = _diagonal_label_volume(size, init=-1)
transform = LabelToBoundary(offsets=(2, 4), ignore_index=-1)
result = transform(label)
assert result.shape == (2, ) + label.shape
assert np.array_equal(np.unique(result), [-1, 0, 1])
def test_average_precision_real_data(self):
l_file = 'resources/sample_patch.h5'
with h5py.File(l_file, 'r') as f:
label = f['big_label'][...]
ltb = LabelToBoundary((2, 4, 6, 8))
pred = ltb(label)
ap = AveragePrecision(min_instance_size=20000)
assert ap(pred, label) > 0.2
def test_label_to_boundary(self):
size = 20
label = _diagonal_label_volume(size)
# this transform will produce 2 channels
transform = LabelToBoundary(offsets=(2, 4))
result = transform(label)
assert result.shape == (2, ) + label.shape
assert np.array_equal(np.unique(result), [0, 1])
def test_label_to_boundary_no_aggregate(self):
size = 20
label = _diagonal_label_volume(size)
# this transform will produce 6 channels
transform = LabelToBoundary(offsets=(2, 4), aggregate_affinities=False)
result = transform(label)
assert result.shape == (6,) + label.shape
assert np.array_equal(np.unique(result), [0, 1])
def test_average_precision_real_data(self):
l_file = 'resources/sample_patch.h5'
with h5py.File(l_file, 'r') as f:
label = f['big_label'][...]
ltb = LabelToBoundary((1, 2, 4, 6), aggregate_affinities=True)
pred = ltb(label)
# don't compare instances smaller than 25K voxels
ap = AveragePrecision(min_instance_size=25000)
assert ap(pred, label) > 0.5