means = np.mean(a, 0)
sds = np.std(a, 0)
U, S, V = numpy.linalg.svd((a[:,:] - means[np.newaxis, :]) / sds[np.newaxis, :],
full_matrices = False)
components = V.T[:, :nkernels]
components = components.transpose()
for i in range(nkernels):
pixels = components[i,:(19*19)].reshape(19,19)
log = components[i,(19*19):(19*19*2)].reshape(19,19)
gauss = components[i,(19*19*2):].reshape(9,9)
pylab.subplot(8, 18, i*3+1).imshow(pixels)
pylab.subplot(8, 18, i*3+2).imshow(log)
pylab.subplot(8, 18, i*3+3).imshow(gauss)
if "components" in h5_file.keys():
del h5_file["components"]
if "feature_means" in h5_file.keys():
del h5_file["feature_means"]
if "feature_sds" in h5_file.keys():
del h5_file["feature_sds"]
h5_file.create_dataset("components", data = components)
h5_file.create_dataset("feature_means", data = means)
h5_file.create_dataset("feature_sds", data = sds)
h5_file.close()
pylab.savefig("../kernels.pdf")
else:
means = h5_file["feature_means"][:]
sds = h5_file["feature_sds"][:]
def normalize(features):
from vigra.learning import RandomForest
import numpy as np
import h5py
import sys
from tiffcvt import h5_file
if __name__=="__main__":
clf = RandomForest(treeCount=40)
training_set = h5_file["training_features"][:,:].astype(np.float32)
training_class = h5_file["training_classification"][:].astype(np.uint32)
if len(sys.argv) > 1 and sys.argv[1] == "eigentexture":
from eigentexture import normalize
training_set = normalize(training_set)
components = h5_file["components"][:,:].transpose()
training_set = np.dot(training_set, components).astype(np.float32)
classifier_name = "etclassifier"
else:
classifier_name = "classifier"
clf.learnRF(training_set, training_class)
if classifier_name in h5_file.keys():
del h5_file[classifier_name]
h5_file.close()
clf.writeHDF5('../challenge.h5', "/"+classifier_name, True)
else:
classifier = RandomForest("../challenge.h5", "/classifier")
et_classifier = RandomForest("../challenge.h5", "/etclassifier")
