def aaaNumpyFile(self):
g =graph.Graph()
npfile = "/home/akreshuk/data/synapse_small_4d.npy"
reader = OpInputDataReader(graph=g)
reader.FilePath.setValue(npfile)
#out = reader.Output[:].wait()
#print out.shape
opFeatures = OpPixelFeaturesPresmoothed(graph=g)
opFeatures.Scales.setValue(self.scales)
opFeatures.FeatureIds.setValue(self.featureIds)
opFeatures.Input.connect(reader.Output)
opFeatures.Matrix.setValue(self.selectedFeatures[5])
out = opFeatures.Output[:].wait()
print out.shape
opFeaturesInterp = OpPixelFeaturesInterpPresmoothed(graph=g)
opFeaturesInterp.Scales.setValue(self.scales)
opFeaturesInterp.FeatureIds.setValue(self.featureIds)
opFeaturesInterp.Input.connect(reader.Output)
opFeaturesInterp.Matrix.setValue(self.selectedFeatures[5])
opFeaturesInterp.InterpolationScaleZ.setValue(2)
out = opFeaturesInterp.Output[:].wait()
print out.shape
def test_compute_in_2d(self):
op = OpPixelFeaturesPresmoothed(graph=Graph())
op.Scales.setValue([0.7, 1, 1.6])
op.FeatureIds.setValue([
"GaussianSmoothing",
"LaplacianOfGaussian",
"StructureTensorEigenvalues",
"HessianOfGaussianEigenvalues",
"GaussianGradientMagnitude",
"DifferenceOfGaussians",
])
op.SelectionMatrix.setValue(
numpy.array([
[True, False, True],
[False, True, False],
[False, False, True],
[True, False, False],
[False, True, False],
[False, False, True],
]))
# compute result over whole volume in 2d
op.ComputeIn2d.setValue([True] * 3)
op.Input.setValue(self.data)
computed_whole = op.Output[:].wait()
# compute result for every z slice independently
z_slices = []
for z in range(self.data.shape[2]):
op.Input.setValue(self.data[:, :, z:z + 1])
z_slices.append(op.Output[:].wait())
computed_per_slice = numpy.concatenate(z_slices, axis=2)
assert computed_per_slice.shape == computed_whole.shape
if DEBUG:
check_channel = 6
plt.figure(figsize=(5, 20))
for z in range(self.data.shape[2]):
plt.subplot(self.data.shape[2], 2, 2 * z + 1)
plt.imshow(computed_whole[0, check_channel, z])
plt.title("whole")
plt.subplot(self.data.shape[2], 2, 2 * z + 2)
plt.imshow(computed_per_slice[0, check_channel, z])
plt.title("per slice")
plt.show()
assert computed_whole.shape == computed_per_slice.shape
assert numpy.allclose(
computed_whole, computed_per_slice), abs(computed_whole -
computed_per_slice).max()
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
# Create the operator that actually generates the features
self.opPixelFeatures = OpPixelFeaturesPresmoothed(parent=self)
# Connect our internal operators to our external inputs
self.opPixelFeatures.Scales.connect(self.Scales)
self.opPixelFeatures.FeatureIds.connect(self.FeatureIds)
self.opPixelFeatures.SelectionMatrix.connect(self.SelectionMatrix)
self.opPixelFeatures.ComputeIn2d.connect(self.ComputeIn2d)
self.opReorderIn = OpReorderAxes(parent=self)
self.opReorderIn.AxisOrder.setValue('tczyx')
self.opReorderIn.Input.connect(self.InputImage)
self.opPixelFeatures.Input.connect(self.opReorderIn.Output)
self.opReorderOut = OpReorderAxes(parent=self)
self.opReorderOut.Input.connect(self.opPixelFeatures.Output)
self.opReorderLayers = OperatorWrapper(
OpReorderAxes, parent=self, broadcastingSlotNames=["AxisOrder"])
self.opReorderLayers.Input.connect(self.opPixelFeatures.Features)
self.WINDOW_SIZE = self.opPixelFeatures.WINDOW_SIZE
def __init__(self, *args, **kwargs):
super(OpFeatureSelectionNoCache, self).__init__(*args, **kwargs)
# Create the operator that actually generates the features
self.opPixelFeatures = OpPixelFeaturesPresmoothed(parent=self)
# Connect our internal operators to our external inputs
self.opPixelFeatures.Scales.connect(self.Scales)
self.opPixelFeatures.FeatureIds.connect(self.FeatureIds)
self.opReorderIn = OpReorderAxes(parent=self)
self.opReorderIn.Input.connect(self.InputImage)
self.opPixelFeatures.Input.connect(self.opReorderIn.Output)
self.opReorderOut = OpReorderAxes(parent=self)
self.opReorderOut.Input.connect(self.opPixelFeatures.Output)
self.opReorderLayers = OperatorWrapper(
OpReorderAxes, parent=self, broadcastingSlotNames=["AxisOrder"])
self.opReorderLayers.Input.connect(self.opPixelFeatures.Features)
# We don't connect SelectionMatrix here because we want to
# check it for errors (See setupOutputs)
# self.opPixelFeatures.SelectionMatrix.connect( self.SelectionMatrix )
self.WINDOW_SIZE = self.opPixelFeatures.WINDOW_SIZE
def runFeatures(self, data, dataInterp):
g = graph.Graph()
opFeatures = OpPixelFeaturesPresmoothed(graph=g)
opFeaturesInterp = OpPixelFeaturesInterpPresmoothed(graph=g)
opFeatures.Input.setValue(dataInterp)
opFeaturesInterp.Input.setValue(data)
opFeatures.Scales.setValue(self.scales)
opFeaturesInterp.Scales.setValue(self.scales)
opFeatures.FeatureIds.setValue(self.featureIds)
opFeaturesInterp.FeatureIds.setValue(self.featureIds)
opFeaturesInterp.InterpolationScaleZ.setValue(self.scaleZ)
#for i, imatrix in enumerate(self.selectedFeatures[0:1]):
for i, imatrix in enumerate(self.selectedFeatures):
opFeatures.Matrix.setValue(imatrix)
opFeaturesInterp.Matrix.setValue(imatrix)
outputInterpData = opFeatures.Output[:].wait()
outputInterpFeatures = opFeaturesInterp.Output[:].wait()
for iz in range(self.nz):
#for iz in range(2, 3):
#print iz, iz*self.scaleZ
try:
outputInterpDataSlice = opFeatures.Output[:, :, iz*self.scaleZ:iz*self.scaleZ+1, :].wait()
outputInterpFeaturesSlice = opFeaturesInterp.Output[:, :, iz, :].wait()
assert_array_almost_equal(outputInterpDataSlice, outputInterpFeaturesSlice, 1)
assert_array_almost_equal(outputInterpData[:, :, iz*self.scaleZ, 0], outputInterpFeatures[:, :, iz, 0], 1)
#assert_array_almost_equal(outputInterpDataSlice[:, :, 0, :], outputInterpData[:, :, iz*self.scaleZ, :], 3)
assert_array_almost_equal(outputInterpFeatures[:, :, iz, :], outputInterpFeaturesSlice[:, :, 0, :], 1)
except AssertionError:
print "failed for feature:", imatrix, i
print "failed for slice:", iz
print "inter data:", outputInterpData[:, :, iz*self.scaleZ, 0]
print "inter features:", outputInterpFeatures[:, :, iz, 0]
print "inter data slice:", outputInterpDataSlice[:, :, 0, 0]
print "inter features:", outputInterpFeaturesSlice[:, :, 0, 0]
raise AssertionError
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
# Create the operator that actually generates the features
self.opPixelFeatures = OpPixelFeaturesPresmoothed(parent=self)
# Connect our internal operators to our external inputs
self.opPixelFeatures.Scales.connect(self.Scales)
self.opPixelFeatures.FeatureIds.connect(self.FeatureIds)
self.opPixelFeatures.SelectionMatrix.connect(self.SelectionMatrix)
self.opPixelFeatures.ComputeIn2d.connect(self.ComputeIn2d)
self.opReorderIn = OpReorderAxes(parent=self)
self.opReorderIn.AxisOrder.setValue('tczyx')
self.opReorderIn.Input.connect(self.InputImage)
self.opPixelFeatures.Input.connect(self.opReorderIn.Output)
self.opReorderOut = OpReorderAxes(parent=self)
self.opReorderOut.Input.connect(self.opPixelFeatures.Output)
self.opReorderLayers = OperatorWrapper(OpReorderAxes, parent=self,
broadcastingSlotNames=["AxisOrder"])
self.opReorderLayers.Input.connect(self.opPixelFeatures.Features)
self.WINDOW_SIZE = self.opPixelFeatures.WINDOW_SIZE
def __init__(self, *args, **kwargs):
super(OpFeatureSelection, self).__init__(*args, **kwargs)
# Two internal operators: features and cache
self.opPixelFeatures = OpPixelFeaturesPresmoothed(parent=self)
self.opPixelFeatureCache = OpSlicedBlockedArrayCache(parent=self)
self.opPixelFeatureCache.name = "opPixelFeatureCache"
# Connect the cache to the feature output
self.opPixelFeatureCache.Input.connect(self.opPixelFeatures.Output)
self.opPixelFeatureCache.fixAtCurrent.setValue(False)
# Connect our internal operators to our external inputs
self.opPixelFeatures.Scales.connect( self.Scales )
self.opPixelFeatures.FeatureIds.connect( self.FeatureIds )
self.opPixelFeatures.Matrix.connect( self.SelectionMatrix )
self.opPixelFeatures.Input.connect( self.InputImage )
# Connect our external outputs to our internal operators
self.OutputImage.connect( self.opPixelFeatures.Output )
self.CachedOutputImage.connect( self.opPixelFeatureCache.Output )
self.FeatureLayers.connect( self.opPixelFeatures.Features )
def aaaSlices(self):
g = graph.Graph()
opFeatures = OpPixelFeaturesPresmoothed(graph=g)
opFeatures.Scales.setValue(self.scales)
opFeatures.FeatureIds.setValue(self.featureIds)
opFeatures.Input.setValue(self.dataNoChannels)
for i, imatrix in enumerate(self.selectedFeatures):
opFeatures.Matrix.setValue(imatrix)
#compute in one piece
dataOne = opFeatures.Output[:].wait()
#compute slice-wise
for z in range(self.nz):
dataSlice = opFeatures.Output[:, :, z:z+1].wait()
try:
assert_array_almost_equal(dataOne[:, :, z:z+1], dataSlice, 2)
except AssertionError:
print "wrong for matrix:", imatrix
print "wrong for slice:", z
print dataOne[:, :, z:z+1]
print dataSlice
raise AssertionError
def __init__(self, *args, **kwargs):
super(OpFeatureSelectionNoCache, self).__init__(*args, **kwargs)
# Create the operator that actually generates the features
self.opPixelFeatures = OpPixelFeaturesPresmoothed(parent=self)
# Connect our internal operators to our external inputs
self.opPixelFeatures.Scales.connect( self.Scales )
self.opPixelFeatures.FeatureIds.connect( self.FeatureIds )
self.opReorderIn = OpReorderAxes(parent=self)
self.opReorderIn.Input.connect(self.InputImage)
self.opPixelFeatures.Input.connect(self.opReorderIn.Output)
self.opReorderOut = OpReorderAxes(parent=self)
self.opReorderOut.Input.connect(self.opPixelFeatures.Output)
self.opReorderLayers = OperatorWrapper(OpReorderAxes, parent=self,
broadcastingSlotNames=["AxisOrder"])
self.opReorderLayers.Input.connect(self.opPixelFeatures.Features)
# We don't connect SelectionMatrix here because we want to
# check it for errors (See setupOutputs)
# self.opPixelFeatures.SelectionMatrix.connect( self.SelectionMatrix )
self.WINDOW_SIZE = self.opPixelFeatures.WINDOW_SIZE
class OpFeatureSelectionNoCache(Operator):
"""
The top-level operator for the feature selection applet for headless workflows.
"""
name = "OpFeatureSelection"
category = "Top-level"
FeatureGroups = FeatureGroups
FeatureNames = FeatureNames
MinimalFeatures = numpy.zeros((len(FeatureNames), len(defaultScales)),
dtype=bool)
MinimalFeatures[0, 0] = True
# Multiple input images
InputImage = InputSlot()
# The following input slots are applied uniformly to all input images
FeatureIds = InputSlot(
value=getFeatureIdOrder()) # The list of features to compute
Scales = InputSlot(value=defaultScales
) # The list of scales to use when computing features
SelectionMatrix = InputSlot(
value=MinimalFeatures
) # A matrix of bools indicating which features to output
# A list of flags to indicate weather to use a 2d (xy) or a 3d filter for each scale in Scales
ComputeIn2d = InputSlot(value=[])
# The SelectionMatrix rows correspond to feature types in the order specified by the FeatureIds input.
# (See OpPixelFeaturesPresmoothed for the available feature types.)
# The SelectionMatrix columns correspond to the scales provided in the Scales input,
# which requires that the number of matrix columns must match len(Scales.value)
FeatureListFilename = InputSlot(stype="str", optional=True)
# Features are presented in the channels of the output image
# Output can be optionally accessed via an internal cache.
# (Training a classifier benefits from caching, but predicting with an existing classifier does not.)
OutputImage = OutputSlot()
# For the GUI, we also provide each feature as a separate slot in this multislot
FeatureLayers = OutputSlot(level=1)
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
# Create the operator that actually generates the features
self.opPixelFeatures = OpPixelFeaturesPresmoothed(parent=self)
# Connect our internal operators to our external inputs
self.opPixelFeatures.Scales.connect(self.Scales)
self.opPixelFeatures.FeatureIds.connect(self.FeatureIds)
self.opPixelFeatures.SelectionMatrix.connect(self.SelectionMatrix)
self.opPixelFeatures.ComputeIn2d.connect(self.ComputeIn2d)
self.opReorderIn = OpReorderAxes(parent=self)
self.opReorderIn.AxisOrder.setValue('tczyx')
self.opReorderIn.Input.connect(self.InputImage)
self.opPixelFeatures.Input.connect(self.opReorderIn.Output)
self.opReorderOut = OpReorderAxes(parent=self)
self.opReorderOut.Input.connect(self.opPixelFeatures.Output)
self.opReorderLayers = OperatorWrapper(
OpReorderAxes, parent=self, broadcastingSlotNames=["AxisOrder"])
self.opReorderLayers.Input.connect(self.opPixelFeatures.Features)
self.WINDOW_SIZE = self.opPixelFeatures.WINDOW_SIZE
def setupOutputs(self):
# drop non-channel singleton axes
oldAxes = self.InputImage.meta.getAxisKeys()
# make sure channel axis is present
if 'c' not in oldAxes:
oldAxes.append('c')
self.opReorderOut.AxisOrder.setValue(oldAxes)
self.opReorderLayers.AxisOrder.setValue(oldAxes)
# Get features from external file
if self.FeatureListFilename.ready() and len(
self.FeatureListFilename.value) > 0:
raise NotImplementedError('Not simplified yet!')
self.OutputImage.disconnect()
self.FeatureLayers.disconnect()
axistags = self.InputImage.meta.axistags
with h5py.File(self.FeatureListFilename.value, 'r') as f:
dset_names = []
f.visit(dset_names.append)
if len(dset_names) != 1:
sys.stderr.write(
"Input external features HDF5 file should have exactly 1 dataset.\n"
)
sys.exit(1)
dset = f[dset_names[0]]
chnum = dset.shape[-1]
shape = dset.shape
dtype = dset.dtype.type
# Set the metadata for FeatureLayers. Unlike OutputImage and CachedOutputImage,
# FeatureLayers has one slot per channel and therefore the channel dimension must be 1.
self.FeatureLayers.resize(chnum)
for i in range(chnum):
self.FeatureLayers[i].meta.shape = shape[:-1] + (1, )
self.FeatureLayers[i].meta.dtype = dtype
self.FeatureLayers[i].meta.axistags = axistags
self.FeatureLayers[i].meta.display_mode = 'default'
self.FeatureLayers[
i].meta.description = "feature_channel_" + str(i)
self.OutputImage.meta.shape = shape
self.OutputImage.meta.dtype = dtype
self.OutputImage.meta.axistags = axistags
else:
invalid_scales, invalid_z_scales = self.opPixelFeatures.getInvalidScales(
)
if invalid_scales or invalid_z_scales:
invalid_z_scales = [
s for s in invalid_z_scales if s not in invalid_scales
] # 'do not complain twice'
msg = 'Some of your selected feature scales are too large for your dataset.\n'
if invalid_scales:
msg += f'Reduce or remove these scales:\n{invalid_scales}\n\n'
if invalid_z_scales:
msg += f'Reduce, remove or switch to 2D computation for these scales:\n{invalid_z_scales}\n\n'
msg += 'Alternatively use another dataset.'
if self.parent.parent.featureSelectionApplet._gui is None:
# headless
fix_dlgs = []
else:
fix_dlgs = [
self.parent.parent.featureSelectionApplet._gui.
currentGui(
fallback_on_lane_0=True).onFeatureButtonClicked
]
raise DatasetConstraintError("Feature Selection",
msg,
fixing_dialogs=fix_dlgs)
# Connect our external outputs to our internal operators
self.OutputImage.connect(self.opReorderOut.Output)
self.FeatureLayers.connect(self.opReorderLayers.Output)
def propagateDirty(self, slot, subindex, roi):
# Output slots are directly connected to internal operators
pass
def execute(self, slot, subindex, rroi, result):
if len(self.FeatureListFilename.value) == 0:
return
# Set the channel corresponding to the slot(subindex) of the feature layers
if slot == self.FeatureLayers:
rroi.start[-1] = subindex[0]
rroi.stop[-1] = subindex[0] + 1
key = roiToSlice(rroi.start, rroi.stop)
# Read features from external file
with h5py.File(self.FeatureListFilename.value, 'r') as f:
dset_names = []
f.visit(dset_names.append)
if len(dset_names) != 1:
sys.stderr.write(
"Input external features HDF5 file should have exactly 1 dataset."
)
return
dset = f[dset_names[0]]
result[...] = dset[key]
return result
def test(self):
graph = Graph()
testVolumePath = 'tinyfib_volume.h5'
# Unzip the data if necessary
if not os.path.exists(testVolumePath):
zippedTestVolumePath = testVolumePath + ".gz"
assert os.path.exists(zippedTestVolumePath)
os.system("gzip -d " + zippedTestVolumePath)
assert os.path.exists(testVolumePath)
f = h5py.File(testVolumePath, 'r')
data = f['data'][...]
data = data.view(vigra.VigraArray)
data.axistags = vigra.defaultAxistags('txyzc')
labels = f['labels'][...]
assert data.shape[:-1] == labels.shape[:-1]
assert labels.shape[-1] == 1
assert len(data.shape) == 5
f.close()
scales = [0.3, 0.7, 1, 1.6, 3.5, 5.0, 10.0]
featureIds = OpPixelFeaturesPresmoothed.DefaultFeatureIds
# The following conditions cause this test to *usually* fail, but *sometimes* pass:
# When using Structure Tensor EVs at sigma >= 3.5 (NaNs in feature matrix)
# When using Gaussian Gradient Mag at sigma >= 3.5 (inf in feature matrix)
# When using *any feature* at sigma == 10.0 (NaNs in feature matrix)
# sigma: 0.3 0.7 1.0 1.6 3.5 5.0 10.0
selections = numpy.array([
[False, False, False, False, False, False, False],
[False, False, False, False, False, False, False],
[False, False, False, False, True, False, False], # ST EVs
[False, False, False, False, False, False, False],
[False, False, False, False, False, False, False], # GGM
[False, False, False, False, False, False, False]
])
opFeatures = OpPixelFeaturesPresmoothed(graph=graph)
opFeatures.Input.setValue(data)
opFeatures.Scales.setValue(scales)
opFeatures.FeatureIds.setValue(featureIds)
opFeatures.Matrix.setValue(selections)
opTrain = OpTrainRandomForestBlocked(graph=graph)
opTrain.Images.resize(1)
opTrain.Images[0].connect(opFeatures.Output)
opTrain.Labels.resize(1)
opTrain.nonzeroLabelBlocks.resize(1)
# This test only fails when this flag is True.
use_sparse_label_storage = True
if use_sparse_label_storage:
opLabelArray = OpBlockedSparseLabelArray(graph=graph)
opLabelArray.inputs["shape"].setValue(labels.shape)
opLabelArray.inputs["blockShape"].setValue((1, 32, 32, 32, 1))
opLabelArray.inputs["eraser"].setValue(100)
opTrain.nonzeroLabelBlocks[0].connect(opLabelArray.nonzeroBlocks)
# Slice the label data into the sparse array storage
opLabelArray.Input[...] = labels[...]
opTrain.Labels[0].connect(opLabelArray.Output)
else:
# Skip the sparse storage operator and provide labels as one big block
opTrain.Labels[0].setValue(labels)
# One big block
opTrain.nonzeroLabelBlocks.resize(1)
opTrain.nonzeroLabelBlocks[0].setValue([[slice(None, None, None)] *
5])
# Sanity check: Make sure we configured the training operator correctly.
readySlots = [slot.ready() for slot in opTrain.inputs.values()]
assert all(readySlots)
# Generate the classifier
classifier = opTrain.Classifier.value
class OpFeatureSelectionNoCache(Operator):
"""
The top-level operator for the feature selection applet for headless workflows.
"""
name = "OpFeatureSelection"
category = "Top-level"
FeatureGroups = FeatureGroups
FeatureNames = FeatureNames
MinimalFeatures = numpy.zeros((len(FeatureNames), len(defaultScales)), dtype=bool)
# Multiple input images
InputImage = InputSlot()
# The following input slots are applied uniformly to all input images
SelectionMatrix = InputSlot() # A matrix of bools indicating which features to output
FeatureIds = InputSlot(value=getFeatureIdOrder()) # The list of features to compute
Scales = InputSlot(value=defaultScales) # The list of scales to use when computing features
# A list of flags to indicate weather to use a 2d (xy) or a 3d filter for each scale in Scales
ComputeIn2d = InputSlot(value=[])
# The SelectionMatrix rows correspond to feature types in the order specified by the FeatureIds input.
# (See OpPixelFeaturesPresmoothed for the available feature types.)
# The SelectionMatrix columns correspond to the scales provided in the Scales input,
# which requires that the number of matrix columns must match len(Scales.value)
FeatureListFilename = InputSlot(stype="str", optional=True)
# Features are presented in the channels of the output image
# Output can be optionally accessed via an internal cache.
# (Training a classifier benefits from caching, but predicting with an existing classifier does not.)
OutputImage = OutputSlot()
# For the GUI, we also provide each feature as a separate slot in this multislot
FeatureLayers = OutputSlot(level=1)
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
# Create the operator that actually generates the features
self.opPixelFeatures = OpPixelFeaturesPresmoothed(parent=self)
# Connect our internal operators to our external inputs
self.opPixelFeatures.Scales.connect(self.Scales)
self.opPixelFeatures.FeatureIds.connect(self.FeatureIds)
self.opPixelFeatures.SelectionMatrix.connect(self.SelectionMatrix)
self.opPixelFeatures.ComputeIn2d.connect(self.ComputeIn2d)
self.opReorderIn = OpReorderAxes(parent=self)
self.opReorderIn.AxisOrder.setValue('tczyx')
self.opReorderIn.Input.connect(self.InputImage)
self.opPixelFeatures.Input.connect(self.opReorderIn.Output)
self.opReorderOut = OpReorderAxes(parent=self)
self.opReorderOut.Input.connect(self.opPixelFeatures.Output)
self.opReorderLayers = OperatorWrapper(OpReorderAxes, parent=self,
broadcastingSlotNames=["AxisOrder"])
self.opReorderLayers.Input.connect(self.opPixelFeatures.Features)
self.WINDOW_SIZE = self.opPixelFeatures.WINDOW_SIZE
def setupOutputs(self):
# drop non-channel singleton axes
oldAxes = self.InputImage.meta.getAxisKeys()
assert 'c' in oldAxes
self.opReorderOut.AxisOrder.setValue(oldAxes)
self.opReorderLayers.AxisOrder.setValue(oldAxes)
# Get features from external file
if self.FeatureListFilename.ready() and len(self.FeatureListFilename.value) > 0:
raise NotImplementedError('Not simplified yet!')
self.OutputImage.disconnect()
self.FeatureLayers.disconnect()
axistags = self.InputImage.meta.axistags
with h5py.File(self.FeatureListFilename.value, 'r') as f:
dset_names = []
f.visit(dset_names.append)
if len(dset_names) != 1:
sys.stderr.write("Input external features HDF5 file should have exactly 1 dataset.\n")
sys.exit(1)
dset = f[dset_names[0]]
chnum = dset.shape[-1]
shape = dset.shape
dtype = dset.dtype.type
# Set the metadata for FeatureLayers. Unlike OutputImage and CachedOutputImage,
# FeatureLayers has one slot per channel and therefore the channel dimension must be 1.
self.FeatureLayers.resize(chnum)
for i in range(chnum):
self.FeatureLayers[i].meta.shape = shape[:-1] + (1,)
self.FeatureLayers[i].meta.dtype = dtype
self.FeatureLayers[i].meta.axistags = axistags
self.FeatureLayers[i].meta.display_mode = 'default'
self.FeatureLayers[i].meta.description = "feature_channel_" + str(i)
self.OutputImage.meta.shape = shape
self.OutputImage.meta.dtype = dtype
self.OutputImage.meta.axistags = axistags
else:
invalid_scales, invalid_z_scales = self.opPixelFeatures.getInvalidScales()
if invalid_scales or invalid_z_scales:
invalid_z_scales = [s for s in invalid_z_scales if s not in invalid_scales] # 'do not complain twice'
msg = 'Some of your selected feature scales are too large for your dataset.\n'
if invalid_scales:
msg += f'Reduce or remove these scales:\n{invalid_scales}\n\n'
if invalid_z_scales:
msg += f'Reduce, remove or switch to 2D computation for these scales:\n{invalid_z_scales}\n\n'
msg += 'Alternatively use another dataset.'
if self.parent.parent.featureSelectionApplet._gui is None:
# headless
fix_dlgs = []
else:
fix_dlgs = [self.parent.parent.featureSelectionApplet._gui.currentGui(
fallback_on_lane_0=True).onFeatureButtonClicked]
raise DatasetConstraintError("Feature Selection", msg, fixing_dialogs=fix_dlgs)
# Connect our external outputs to our internal operators
self.OutputImage.connect(self.opReorderOut.Output)
self.FeatureLayers.connect(self.opReorderLayers.Output)
def propagateDirty(self, slot, subindex, roi):
# Output slots are directly connected to internal operators
pass
def execute(self, slot, subindex, rroi, result):
if len(self.FeatureListFilename.value) == 0:
return
# Set the channel corresponding to the slot(subindex) of the feature layers
if slot == self.FeatureLayers:
rroi.start[-1] = subindex[0]
rroi.stop[-1] = subindex[0] + 1
key = roiToSlice(rroi.start, rroi.stop)
# Read features from external file
with h5py.File(self.FeatureListFilename.value, 'r') as f:
dset_names = []
f.visit(dset_names.append)
if len(dset_names) != 1:
sys.stderr.write("Input external features HDF5 file should have exactly 1 dataset.")
return
dset = f[dset_names[0]]
result[...] = dset[key]
return result
class OpFeatureSelectionNoCache(Operator):
"""
The top-level operator for the feature selection applet for headless workflows.
"""
name = "OpFeatureSelection"
category = "Top-level"
ScalesList = ScalesList
FeatureGroups = FeatureGroups
FeatureNames = FeatureNames
MinimalFeatures = numpy.zeros((len(FeatureNames), len(ScalesList)),
dtype=bool)
MinimalFeatures[0, 0] = True
# Multiple input images
InputImage = InputSlot()
# The following input slots are applied uniformly to all input images
Scales = InputSlot(
value=ScalesList
) # The list of possible scales to use when computing features
FeatureIds = InputSlot(
value=getFeatureIdOrder()) # The list of features to compute
SelectionMatrix = InputSlot(
value=MinimalFeatures
) # A matrix of bools indicating which features to output.
# The matrix rows correspond to feature types in the order specified by the FeatureIds input.
# (See OpPixelFeaturesPresmoothed for the available feature types.)
# The matrix columns correspond to the scales provided in the Scales input,
# which requires that the number of matrix columns must match len(Scales.value)
FeatureListFilename = InputSlot(stype="str", optional=True)
# Features are presented in the channels of the output image
# Output can be optionally accessed via an internal cache.
# (Training a classifier benefits from caching, but predicting with an existing classifier does not.)
OutputImage = OutputSlot()
FeatureLayers = OutputSlot(
level=1
) # For the GUI, we also provide each feature as a separate slot in this multislot
def __init__(self, *args, **kwargs):
super(OpFeatureSelectionNoCache, self).__init__(*args, **kwargs)
# Create the operator that actually generates the features
self.opPixelFeatures = OpPixelFeaturesPresmoothed(parent=self)
# Connect our internal operators to our external inputs
self.opPixelFeatures.Scales.connect(self.Scales)
self.opPixelFeatures.FeatureIds.connect(self.FeatureIds)
self.opReorderIn = OpReorderAxes(parent=self)
self.opReorderIn.Input.connect(self.InputImage)
self.opPixelFeatures.Input.connect(self.opReorderIn.Output)
self.opReorderOut = OpReorderAxes(parent=self)
self.opReorderOut.Input.connect(self.opPixelFeatures.Output)
self.opReorderLayers = OperatorWrapper(
OpReorderAxes, parent=self, broadcastingSlotNames=["AxisOrder"])
self.opReorderLayers.Input.connect(self.opPixelFeatures.Features)
# We don't connect SelectionMatrix here because we want to
# check it for errors (See setupOutputs)
# self.opPixelFeatures.SelectionMatrix.connect( self.SelectionMatrix )
self.WINDOW_SIZE = self.opPixelFeatures.WINDOW_SIZE
def setupOutputs(self):
# drop non-channel singleton axes
allAxes = 'txyzc'
ts = self.InputImage.meta.getTaggedShape()
oldAxes = "".join(list(ts.keys()))
newAxes = "".join(
[a for a in allAxes if a in ts and ts[a] > 1 or a == 'c'])
self.opReorderIn.AxisOrder.setValue(newAxes)
self.opReorderOut.AxisOrder.setValue(oldAxes)
self.opReorderLayers.AxisOrder.setValue(oldAxes)
# Get features from external file
if self.FeatureListFilename.ready() and len(
self.FeatureListFilename.value) > 0:
self.OutputImage.disconnect()
self.FeatureLayers.disconnect()
axistags = self.InputImage.meta.axistags
with h5py.File(self.FeatureListFilename.value, 'r') as f:
dset_names = []
f.visit(dset_names.append)
if len(dset_names) != 1:
sys.stderr.write(
"Input external features HDF5 file should have exactly 1 dataset.\n"
)
sys.exit(1)
dset = f[dset_names[0]]
chnum = dset.shape[-1]
shape = dset.shape
dtype = dset.dtype.type
# Set the metadata for FeatureLayers. Unlike OutputImage and CachedOutputImage,
# FeatureLayers has one slot per channel and therefore the channel dimension must be 1.
self.FeatureLayers.resize(chnum)
for i in range(chnum):
self.FeatureLayers[i].meta.shape = shape[:-1] + (1, )
self.FeatureLayers[i].meta.dtype = dtype
self.FeatureLayers[i].meta.axistags = axistags
self.FeatureLayers[i].meta.display_mode = 'default'
self.FeatureLayers[
i].meta.description = "feature_channel_" + str(i)
self.OutputImage.meta.shape = shape
self.OutputImage.meta.dtype = dtype
self.OutputImage.meta.axistags = axistags
else:
# Set the new selection matrix and check if it creates an error.
selections = self.SelectionMatrix.value
self.opPixelFeatures.Matrix.setValue(selections)
invalid_scales = self.opPixelFeatures.getInvalidScales()
if invalid_scales:
msg = "Some of your selected feature scales are too large for your dataset.\n"\
"Choose smaller scales (sigma) or use a larger dataset.\n"\
"The invalid scales are: {}".format( invalid_scales )
raise DatasetConstraintError("Feature Selection", msg)
# Connect our external outputs to our internal operators
self.OutputImage.connect(self.opReorderOut.Output)
self.FeatureLayers.connect(self.opReorderLayers.Output)
def propagateDirty(self, slot, subindex, roi):
# Output slots are directly connected to internal operators
pass
def execute(self, slot, subindex, rroi, result):
if len(self.FeatureListFilename.value) == 0:
return
# Set the channel corresponding to the slot(subindex) of the feature layers
if slot == self.FeatureLayers:
rroi.start[-1] = subindex[0]
rroi.stop[-1] = subindex[0] + 1
key = roiToSlice(rroi.start, rroi.stop)
# Read features from external file
with h5py.File(self.FeatureListFilename.value, 'r') as f:
dset_names = []
f.visit(dset_names.append)
if len(dset_names) != 1:
sys.stderr.write(
"Input external features HDF5 file should have exactly 1 dataset."
)
return
dset = f[dset_names[0]]
result[...] = dset[key]
return result
class OpFeatureSelectionNoCache(Operator):
"""
The top-level operator for the feature selection applet for headless workflows.
"""
name = "OpFeatureSelection"
category = "Top-level"
ScalesList = ScalesList
FeatureGroups = FeatureGroups
FeatureNames = FeatureNames
MinimalFeatures = numpy.zeros( (len(FeatureNames), len(ScalesList)), dtype=bool )
MinimalFeatures[0,0] = True
# Multiple input images
InputImage = InputSlot()
# The following input slots are applied uniformly to all input images
Scales = InputSlot( value=ScalesList ) # The list of possible scales to use when computing features
FeatureIds = InputSlot( value=getFeatureIdOrder() ) # The list of features to compute
SelectionMatrix = InputSlot( value=MinimalFeatures ) # A matrix of bools indicating which features to output.
# The matrix rows correspond to feature types in the order specified by the FeatureIds input.
# (See OpPixelFeaturesPresmoothed for the available feature types.)
# The matrix columns correspond to the scales provided in the Scales input,
# which requires that the number of matrix columns must match len(Scales.value)
FeatureListFilename = InputSlot(stype="str", optional=True)
# Features are presented in the channels of the output image
# Output can be optionally accessed via an internal cache.
# (Training a classifier benefits from caching, but predicting with an existing classifier does not.)
OutputImage = OutputSlot()
FeatureLayers = OutputSlot(level=1) # For the GUI, we also provide each feature as a separate slot in this multislot
def __init__(self, *args, **kwargs):
super(OpFeatureSelectionNoCache, self).__init__(*args, **kwargs)
# Create the operator that actually generates the features
self.opPixelFeatures = OpPixelFeaturesPresmoothed(parent=self)
# Connect our internal operators to our external inputs
self.opPixelFeatures.Scales.connect( self.Scales )
self.opPixelFeatures.FeatureIds.connect( self.FeatureIds )
self.opReorderIn = OpReorderAxes(parent=self)
self.opReorderIn.Input.connect(self.InputImage)
self.opPixelFeatures.Input.connect(self.opReorderIn.Output)
self.opReorderOut = OpReorderAxes(parent=self)
self.opReorderOut.Input.connect(self.opPixelFeatures.Output)
self.opReorderLayers = OperatorWrapper(OpReorderAxes, parent=self,
broadcastingSlotNames=["AxisOrder"])
self.opReorderLayers.Input.connect(self.opPixelFeatures.Features)
# We don't connect SelectionMatrix here because we want to
# check it for errors (See setupOutputs)
# self.opPixelFeatures.SelectionMatrix.connect( self.SelectionMatrix )
self.WINDOW_SIZE = self.opPixelFeatures.WINDOW_SIZE
def setupOutputs(self):
# drop non-channel singleton axes
allAxes = 'txyzc'
ts = self.InputImage.meta.getTaggedShape()
oldAxes = "".join(list(ts.keys()))
newAxes = "".join([a for a in allAxes
if a in ts and ts[a] > 1 or a == 'c'])
self.opReorderIn.AxisOrder.setValue(newAxes)
self.opReorderOut.AxisOrder.setValue(oldAxes)
self.opReorderLayers.AxisOrder.setValue(oldAxes)
# Get features from external file
if self.FeatureListFilename.ready() and len(self.FeatureListFilename.value) > 0:
self.OutputImage.disconnect()
self.FeatureLayers.disconnect()
axistags = self.InputImage.meta.axistags
with h5py.File(self.FeatureListFilename.value,'r') as f:
dset_names = []
f.visit(dset_names.append)
if len(dset_names) != 1:
sys.stderr.write("Input external features HDF5 file should have exactly 1 dataset.\n")
sys.exit(1)
dset = f[dset_names[0]]
chnum = dset.shape[-1]
shape = dset.shape
dtype = dset.dtype.type
# Set the metadata for FeatureLayers. Unlike OutputImage and CachedOutputImage,
# FeatureLayers has one slot per channel and therefore the channel dimension must be 1.
self.FeatureLayers.resize(chnum)
for i in range(chnum):
self.FeatureLayers[i].meta.shape = shape[:-1]+(1,)
self.FeatureLayers[i].meta.dtype = dtype
self.FeatureLayers[i].meta.axistags = axistags
self.FeatureLayers[i].meta.display_mode = 'default'
self.FeatureLayers[i].meta.description = "feature_channel_"+str(i)
self.OutputImage.meta.shape = shape
self.OutputImage.meta.dtype = dtype
self.OutputImage.meta.axistags = axistags
else:
# Set the new selection matrix and check if it creates an error.
selections = self.SelectionMatrix.value
self.opPixelFeatures.Matrix.setValue( selections )
invalid_scales = self.opPixelFeatures.getInvalidScales()
if invalid_scales:
msg = "Some of your selected feature scales are too large for your dataset.\n"\
"Choose smaller scales (sigma) or use a larger dataset.\n"\
"The invalid scales are: {}".format( invalid_scales )
raise DatasetConstraintError( "Feature Selection", msg )
# Connect our external outputs to our internal operators
self.OutputImage.connect( self.opReorderOut.Output )
self.FeatureLayers.connect( self.opReorderLayers.Output )
def propagateDirty(self, slot, subindex, roi):
# Output slots are directly connected to internal operators
pass
def execute(self, slot, subindex, rroi, result):
if len(self.FeatureListFilename.value) == 0:
return
# Set the channel corresponding to the slot(subindex) of the feature layers
if slot == self.FeatureLayers:
rroi.start[-1] = subindex[0]
rroi.stop[-1] = subindex[0] + 1
key = roiToSlice(rroi.start, rroi.stop)
# Read features from external file
with h5py.File(self.FeatureListFilename.value, 'r') as f:
dset_names = []
f.visit(dset_names.append)
if len(dset_names) != 1:
sys.stderr.write("Input external features HDF5 file should have exactly 1 dataset.")
return
dset = f[dset_names[0]]
result[...] = dset[key]
return result