def testDetectorOmnipresence(self):
assert self.op.has(self.op.NHistogramBins.value, method="svm"), "Detector is untrained after call to train()"
assert not self.op.has(self.op.NHistogramBins.value + 2, method="svm"), "Wrong bin size trained."
op2 = OpDetectMissing(graph=Graph())
assert op2.has(self.op.NHistogramBins.value, method="svm"), "Trained detectors are not global"
self.op.reset()
assert not self.op.has(self.op.NHistogramBins.value, method="svm"), "Detector not reset."
assert not op2.has(self.op.NHistogramBins.value, method="svm"), "Detector not reset globally."
def testDetectorOmnipresence(self):
if not havesklearn:
raise SkipTest
assert self.op.has(self.op.NHistogramBins.value, method='svm'), "Detector is untrained after call to train()"
assert not self.op.has(self.op.NHistogramBins.value+2, method='svm'), "Wrong bin size trained."
op2 = OpDetectMissing(graph=Graph())
assert op2.has(self.op.NHistogramBins.value, method='svm'), "Trained detectors are not global"
self.op.reset()
assert not self.op.has(self.op.NHistogramBins.value, method='svm'), "Detector not reset."
assert not op2.has(self.op.NHistogramBins.value, method='svm'), "Detector not reset globally."
class TestDetection(unittest.TestCase):
def setUp(self):
v = _volume()
self.op = OpDetectMissing(graph=Graph())
self.op.InputVolume.setValue(v)
self.op.PatchSize.setValue(64)
self.op.HaloSize.setValue(0)
self.op.DetectionMethod.setValue('svm')
self.op.train(force=True)
def testDetectorOmnipresence(self):
if not havesklearn:
raise SkipTest
assert self.op.has(self.op.NHistogramBins.value, method='svm'), "Detector is untrained after call to train()"
assert not self.op.has(self.op.NHistogramBins.value+2, method='svm'), "Wrong bin size trained."
op2 = OpDetectMissing(graph=Graph())
assert op2.has(self.op.NHistogramBins.value, method='svm'), "Trained detectors are not global"
self.op.reset()
assert not self.op.has(self.op.NHistogramBins.value, method='svm'), "Detector not reset."
assert not op2.has(self.op.NHistogramBins.value, method='svm'), "Detector not reset globally."
def testDetectorPropagation(self):
if not havesklearn:
raise SkipTest
s = self.op.Detector[:].wait()
self.op.reset()
assert not self.op.has(self.op.NHistogramBins.value, method='svm'), "Detector not reset."
self.op.OverloadDetector.setValue(s)
assert self.op.has(self.op.NHistogramBins.value, method='svm'), "Detector not loaded."
def testClassicDetection(self):
self.op.DetectionMethod.setValue('classic')
self.op.PatchSize.setValue(1)
self.op.HaloSize.setValue(0)
(v,m,_) = _singleMissingLayer(layer=15, nx=1,ny=1,nz=50,method='linear')
self.op.InputVolume.setValue(v)
assert_array_equal(self.op.Output[:].wait().view(type=np.ndarray),\
m.view(type=np.ndarray),\
err_msg="input with single black layer")
def testSVMDetection(self):
if not havesklearn:
raise SkipTest
self.op.DetectionMethod.setValue('svm')
self.op.PatchSize.setValue(1)
self.op.HaloSize.setValue(0)
(v,m,_) = _singleMissingLayer(layer=15, nx=1,ny=1,nz=50,method='linear')
self.op.InputVolume.setValue(v)
assert_array_equal(self.op.Output[:].wait().view(type=np.ndarray),\
m.view(type=np.ndarray),\
err_msg="input with single black layer")
def testSVMDetectionWithHalo(self):
nBlack = 15
if not havesklearn:
raise SkipTest
self.op.DetectionMethod.setValue('svm')
self.op.PatchSize.setValue(5)
self.op.HaloSize.setValue(2)
(v,m,_) = _singleMissingLayer(layer=nBlack, nx=10,ny=15,nz=50,method='linear')
self.op.InputVolume.setValue(v)
assert_array_equal(self.op.Output[:].wait()[...,nBlack].view(type=np.ndarray),\
m[...,nBlack].view(type=np.ndarray),\
err_msg="input with single black layer")
def testSVMWithHalo(self):
if not havesklearn:
raise SkipTest
self.op.DetectionMethod.setValue('svm')
self.op.PatchSize.setValue(2)
self.op.HaloSize.setValue(1)
(v,m,_) = _singleMissingLayer(layer=15, nx=4,ny=4,nz=50,method='linear')
self.op.InputVolume.setValue(v)
assert_array_equal(self.op.Output[:].wait().view(type=np.ndarray),\
m.view(type=np.ndarray),\
err_msg="input with single black layer")
def testSingleMissingLayer(self):
(v,m,_) = _singleMissingLayer(layer=15, nx=64,ny=64,nz=50,method='linear')
self.op.InputVolume.setValue(v)
assert_array_equal(self.op.Output[:].wait().view(type=np.ndarray),\
m.view(type=np.ndarray),\
err_msg="input with single black layer")
def testDoubleMissingLayer(self):
(v,m,_) = _singleMissingLayer(layer=15, nx=64,ny=64,nz=50,method='linear')
(v2,m2,_) = _singleMissingLayer(layer=35, nx=64,ny=64,nz=50,method='linear')
m2[np.where(m2==1)] = 2
self.op.InputVolume.setValue(np.sqrt(v*v2))
assert_array_equal(self.op.Output[:].wait().view(type=np.ndarray)>0,\
(m+m2).view(type=np.ndarray)>0,\
err_msg="input with two black layers")
def test4D(self):
vol = vigra.VigraArray( np.ones((10,64,64,3)), axistags=vigra.defaultAxistags('cxyz') )
self.op.InputVolume.setValue(vol)
self.op.Output[:].wait()
def test5D(self):
vol = vigra.VigraArray( np.ones((15,64,10,3,64)), axistags=vigra.defaultAxistags('cxzty') )
self.op.InputVolume.setValue(vol)
self.op.Output[:].wait()
def testPersistence(self):
dumpedString = self.op.dumps()
self.op.loads(dumpedString)
def testPatchify(self):
from lazyflow.operators.opDetectMissingData import _patchify as patchify
X = np.vander(np.arange(2,5))
''' results in
X = array([[ 4, 2, 1],
[ 9, 3, 1],
[16, 4, 1]])
'''
(patches,slices) = patchify(X,1,1)
expected = [np.array([[4,2],[9,3]]), \
np.array([[4,2,1],[9,3,1]]), \
np.array([[2,1],[3,1]]), \
np.array([[4,2],[9,3],[16,4]]), \
np.array([[4,2,1],[9,3,1],[16,4,1]]), \
np.array([[2,1],[3,1],[4,1]]), \
np.array([[9,3],[16,4]]), \
np.array([[9,3,1],[16,4,1]]), \
np.array([[3,1],[4,1]])]
expSlices = [(slice(0,1),slice(0,1)), \
(slice(0,1), slice(1,2)), \
(slice(0,1), slice(2,3)), \
(slice(1,2), slice(0,1)), \
(slice(1,2), slice(1,2)), \
(slice(1,2), slice(2,3)), \
(slice(2,3), slice(0,1)), \
(slice(2,3), slice(1,2)), \
(slice(2,3), slice(2,3))]
for ep, s in zip(expected,expSlices):
#check if patch is in the result
has = False
for i,p in enumerate(patches):
if np.all(p == ep):
has = True
# check if slice is ok
self.assertEqual(s, slices[i])
assert has, "Mising patch {}".format(ep)
pass
def testPatchDetection(self):
vol = vigra.taggedView(np.ones((5,5), dtype=np.uint8)*128, axistags=vigra.defaultAxistags('xy'))
vol[2:5,2:5] = 0
expected = np.zeros((5,5))
expected[3:5,3:5] = 1
self.op.PatchSize.setValue(2)
self.op.HaloSize.setValue(1)
self.op.DetectionMethod.setValue('classic')
self.op.InputVolume.setValue(vol)
out = self.op.Output[:].wait()
assert_array_equal(expected[3:5,3:5], out[3:5,3:5])
class TestDetection(unittest.TestCase):
def setup_method(self, method):
v = _volume()
self.op = OpDetectMissing(graph=Graph())
self.op.InputVolume.setValue(v)
self.op.PatchSize.setValue(64)
self.op.HaloSize.setValue(0)
self.op.DetectionMethod.setValue("svm")
self.op.train(force=True)
def testDetectorOmnipresence(self):
if not havesklearn:
raise SkipTest
assert self.op.has(self.op.NHistogramBins.value, method="svm"), "Detector is untrained after call to train()"
assert not self.op.has(self.op.NHistogramBins.value + 2, method="svm"), "Wrong bin size trained."
op2 = OpDetectMissing(graph=Graph())
assert op2.has(self.op.NHistogramBins.value, method="svm"), "Trained detectors are not global"
self.op.reset()
assert not self.op.has(self.op.NHistogramBins.value, method="svm"), "Detector not reset."
assert not op2.has(self.op.NHistogramBins.value, method="svm"), "Detector not reset globally."
def testDetectorPropagation(self):
if not havesklearn:
raise SkipTest
s = self.op.Detector[:].wait()
self.op.reset()
assert not self.op.has(self.op.NHistogramBins.value, method="svm"), "Detector not reset."
self.op.OverloadDetector.setValue(s)
assert self.op.has(self.op.NHistogramBins.value, method="svm"), "Detector not loaded."
def testClassicDetection(self):
self.op.DetectionMethod.setValue("classic")
self.op.PatchSize.setValue(1)
self.op.HaloSize.setValue(0)
(v, m, _) = _singleMissingLayer(layer=15, nx=1, ny=1, nz=50, method="linear")
self.op.InputVolume.setValue(v)
assert_array_equal(
self.op.Output[:].wait().view(type=np.ndarray),
m.view(type=np.ndarray),
err_msg="input with single black layer",
)
def testSVMDetection(self):
if not havesklearn:
raise SkipTest
self.op.DetectionMethod.setValue("svm")
self.op.PatchSize.setValue(1)
self.op.HaloSize.setValue(0)
(v, m, _) = _singleMissingLayer(layer=15, nx=1, ny=1, nz=50, method="linear")
self.op.InputVolume.setValue(v)
assert_array_equal(
self.op.Output[:].wait().view(type=np.ndarray),
m.view(type=np.ndarray),
err_msg="input with single black layer",
)
def testSVMDetectionWithHalo(self):
nBlack = 15
if not havesklearn:
raise SkipTest
self.op.DetectionMethod.setValue("svm")
self.op.PatchSize.setValue(5)
self.op.HaloSize.setValue(2)
(v, m, _) = _singleMissingLayer(layer=nBlack, nx=10, ny=15, nz=50, method="linear")
self.op.InputVolume.setValue(v)
assert_array_equal(
self.op.Output[:].wait()[..., nBlack].view(type=np.ndarray),
m[..., nBlack].view(type=np.ndarray),
err_msg="input with single black layer",
)
def testSVMWithHalo(self):
if not havesklearn:
raise SkipTest
self.op.DetectionMethod.setValue("svm")
self.op.PatchSize.setValue(2)
self.op.HaloSize.setValue(1)
(v, m, _) = _singleMissingLayer(layer=15, nx=4, ny=4, nz=50, method="linear")
self.op.InputVolume.setValue(v)
assert_array_equal(
self.op.Output[:].wait().view(type=np.ndarray),
m.view(type=np.ndarray),
err_msg="input with single black layer",
)
def testSingleMissingLayer(self):
(v, m, _) = _singleMissingLayer(layer=15, nx=64, ny=64, nz=50, method="linear")
self.op.InputVolume.setValue(v)
assert_array_equal(
self.op.Output[:].wait().view(type=np.ndarray),
m.view(type=np.ndarray),
err_msg="input with single black layer",
)
def testDoubleMissingLayer(self):
(v, m, _) = _singleMissingLayer(layer=15, nx=64, ny=64, nz=50, method="linear")
(v2, m2, _) = _singleMissingLayer(layer=35, nx=64, ny=64, nz=50, method="linear")
m2[np.where(m2 == 1)] = 2
self.op.InputVolume.setValue(np.sqrt(v * v2))
assert_array_equal(
self.op.Output[:].wait().view(type=np.ndarray) > 0,
(m + m2).view(type=np.ndarray) > 0,
err_msg="input with two black layers",
)
def test4D(self):
vol = vigra.VigraArray(np.ones((10, 64, 64, 3)), axistags=vigra.defaultAxistags("cxyz"))
self.op.InputVolume.setValue(vol)
self.op.Output[:].wait()
def test5D(self):
vol = vigra.VigraArray(np.ones((15, 64, 10, 3, 64)), axistags=vigra.defaultAxistags("cxzty"))
self.op.InputVolume.setValue(vol)
self.op.Output[:].wait()
def testPersistence(self):
dumpedString = self.op.dumps()
self.op.loads(dumpedString)
def testPatchify(self):
from lazyflow.operators.opDetectMissingData import _patchify as patchify
X = np.vander(np.arange(2, 5))
""" results in
X = array([[ 4, 2, 1],
[ 9, 3, 1],
[16, 4, 1]])
"""
(patches, slices) = patchify(X, 1, 1)
expected = [
np.array([[4, 2], [9, 3]]),
np.array([[4, 2, 1], [9, 3, 1]]),
np.array([[2, 1], [3, 1]]),
np.array([[4, 2], [9, 3], [16, 4]]),
np.array([[4, 2, 1], [9, 3, 1], [16, 4, 1]]),
np.array([[2, 1], [3, 1], [4, 1]]),
np.array([[9, 3], [16, 4]]),
np.array([[9, 3, 1], [16, 4, 1]]),
np.array([[3, 1], [4, 1]]),
]
expSlices = [
(slice(0, 1), slice(0, 1)),
(slice(0, 1), slice(1, 2)),
(slice(0, 1), slice(2, 3)),
(slice(1, 2), slice(0, 1)),
(slice(1, 2), slice(1, 2)),
(slice(1, 2), slice(2, 3)),
(slice(2, 3), slice(0, 1)),
(slice(2, 3), slice(1, 2)),
(slice(2, 3), slice(2, 3)),
]
for ep, s in zip(expected, expSlices):
# check if patch is in the result
has = False
for i, p in enumerate(patches):
if np.array_equal(p, ep):
has = True
# check if slice is ok
self.assertEqual(s, slices[i])
assert has, "Mising patch {}".format(ep)
pass
def testPatchDetection(self):
vol = vigra.taggedView(np.ones((5, 5), dtype=np.uint8) * 128, axistags=vigra.defaultAxistags("xy"))
vol[2:5, 2:5] = 0
expected = np.zeros((5, 5))
expected[3:5, 3:5] = 1
self.op.PatchSize.setValue(2)
self.op.HaloSize.setValue(1)
self.op.DetectionMethod.setValue("classic")
self.op.InputVolume.setValue(vol)
out = self.op.Output[:].wait()
assert_array_equal(expected[3:5, 3:5], out[3:5, 3:5])