def classify(img, classifier, class_names, ops=None, distribution_class_index=-1):
""" img: a 2D RandomAccessibleInterval.
classifier: a WEKA Classifier instance, like SMO or FastRandomForest, etc. Any.
If it's a string, interprets it as a file path and attempts to deserialize
a previously saved trained classifier.
class_names: the list of names of each class to learn.
ops: the filter bank of ImgMath ops for the img.
distribution_class_index: defaults to -1, meaning return the class index for each pixel.
When larger than -1, it's interpreted as a class index, and
returns instead the floating-point value of each pixel in
the distribution of that particular class index. """
if type(classifier) == str:
classifier = SerializationHelper.read(classifier)
ops = ops if ops else filterBank(img)
attributes = ArrayList()
for i in xrange(len(ops)):
attributes.add(Attribute("attr-%i" % i))
#for name in classifier.attributeNames()[0][1]:
# attributes.add(Attribute(name))
attributes.add(Attribute("class", class_names))
info = Instances("structure", attributes, 1)
info.setClassIndex(len(attributes) -1)
opImgs = [compute(op).into(ArrayImgs.floats([img.dimension(0), img.dimension(1)])) for op in ops]
cs_opImgs = Views.collapse(Views.stack(opImgs))
result = ArrayImgs.floats([img.dimension(0), img.dimension(1)])
cr = result.cursor()
cop = Views.iterable(cs_opImgs).cursor()
while cr.hasNext():
tc = cop.next()
vector = array((tc.get(i).getRealDouble() for i in xrange(len(opImgs))), 'd')
vector += array([0], 'd')
di = DenseInstance(1.0, vector)
di.setDataset(info) # the list of attributes
if distribution_class_index > -1:
cr.next().setReal(classifier.distributionForInstance(di)[distribution_class_index])
else:
cr.next().setReal(classifier.classifyInstance(di))
return result
def createTrainingData(img, samples, class_names, n_samples=0, ops=None):
""" img: a 2D RandomAccessibleInterval.
samples: a sequence of long[] (or int numeric sequence or Localizable) and class_index pairs; can be a generator.
n_samples: optional, the number of samples (in case samples is e.g. a generator).
class_names: a list of class names, as many as different class_index.
ops: optional, the sequence of ImgMath ops to apply to the img, defaults to filterBank(img)
return an instance of WEKA Instances
"""
ops = ops if ops else filterBank(img)
if 0 == n_samples:
n_samples = len(samples)
# Define a WEKA Attribute for each feature (one for op in the filter bank, plus the class)
attribute_names = ["attr-%i" % (i+1) for i in xrange(len(ops))]
attributes = ArrayList()
for name in attribute_names:
attributes.add(Attribute(name))
# Add an attribute at the end for the classification classes
attributes.add(Attribute("class", class_names))
# Create the training data structure
training_data = Instances("training", attributes, n_samples)
training_data.setClassIndex(len(attributes) -1)
opImgs = [compute(op).into(ArrayImgs.floats([img.dimension(0), img.dimension(1)])) for op in ops]
ra = Views.collapse(Views.stack(opImgs)).randomAccess()
for position, class_index in samples:
ra.setPosition(position)
tc = ra.get()
vector = array((tc.get(i).getRealDouble() for i in xrange(len(opImgs))), 'd')
vector += array([class_index], 'd')
training_data.add(DenseInstance(1.0, vector))
return training_data
