def runTests(activationsPath, indexLabelMappingPath, sourcePath):
labels = utility.getLabelStrings(indexLabelMappingPath)
activations = utility.arrayFromFile(activationsPath)
if sourcePath.endswith('/') == False:
sourcePath += '/'
clusterGroups = loadClusters(sourcePath) # returns list with all previously generated cluster groups
mixedClusterResultsSimple = []
perLabelClusterResultsSimple = []
for clusters in clusterGroups:
logger.info("Evaluating clusters at " + clusters['path'])
if(clusters['type'] == 'perLabel'):
[confusionMatrix, meanAveragePrecision, overallCorrect, overallWrong] = runTest(clusters['data'], activations, labels True) # (clusters, activations, labels)
perLabelClusterResultsSimple.append([clusters['k'], meanAveragePrecision, overallCorrect, overallWrong])
saveConfusionMatrix(confusionMatrix, clusters['path'] + "confusion_test.npy")
utility.plotConfusionMatrix(confusionMatrix, labels, clusters['path'] + "confusion_test.pdf")
else:
[confusionMatrix, meanAveragePrecision, overallCorrect, overallWrong] = runTest(clusters['data'], activations, labels False) # (clusters, activations, labels)
mixedClusterResultsSimple.append([clusters['k'], meanAveragePrecision, overallCorrect, overallWrong])
saveConfusionMatrix(confusionMatrix, clusters['path'] + "confusion_test.npy")
utility.plotConfusionMatrix(confusionMatrix, labels, clusters['path'] + "confusion_test.pdf")
overviewPerLabel = np.array(perLabelClusterResultsSimple)
overviewMixed = np.array(mixedClusterResultsSimple)
saveOverview(overviewPerLabel, sourcePath + 'perLabel_')
saveOverview(overviewMixed, sourcePath + 'result_mixed_')
utility.plotKMeansOverview(overviewPerLabel, sourcePath + 'perLabel_result.pdf', True)
utility.plotKMeansOverview(overviewMixed, sourcePath + 'result_mixed_result.pdf', True)
def generateKMeansSeries(activationsPath, labelIndexMappingPath, targetFolder):
if targetFolder.endswith('/') == False:
targetFolder += '/'
activations = utility.arrayFromFile(activationsPath)
labels = utility.getLabelStrings(labelIndexMappingPath)
neurons = activations.shape[1] - len(labels)
# test per label k-means
k = PER_LABEL_START
while k <= PER_LABEL_END:
runCounter = 0
while runCounter < RUNS_PER_TYPE:
logger.info("Calculating per label KMeans with k = " + str(k) +
".")
currentTarget = targetFolder + "perLabel_" + str(
k) + "/run_" + str(runCounter) + "/"
if not os.path.exists(os.path.dirname(currentTarget)):
os.makedirs(os.path.dirname(currentTarget))
c, i = kMeans_per_label.findKMeansPerLabel(activations, k,
len(labels),
currentTarget,
labelIndexMappingPath)
plot_cluster.plotClusters(kMeans_core.cleanUp(c), i, neurons,
currentTarget, labels[:len(labels)])
runCounter += 1
k += 1
# test mixed k-means
k = MIXED_START
while k <= MIXED_END:
runCounter = 0
while runCounter < RUNS_PER_TYPE:
logger.info("Calculating mixed KMeans with k = " + str(k) + ".")
currentTarget = targetFolder + "mixed_" + str(k) + "/run_" + str(
runCounter) + "/"
if not os.path.exists(os.path.dirname(currentTarget)):
os.makedirs(os.path.dirname(currentTarget))
[c, i] = kMeans_mixed.findKMeans(activations, k, len(labels),
currentTarget)
plot_cluster.plotClusters(kMeans_core.cleanUp(c), i,
activations.shape[1] - len(labels),
currentTarget, labels[:len(labels)])
runCounter += 1
k += MIXED_STEP
def loadClusters(sourcePath):
clusterSets = []
for rootPath, subdirs, files in os.walk(sourcePath):
for f in files:
if f.endswith('clusters.npy'):
split = rootPath.split('/')[::-1][1].split('_')
splitLength = len(split)
k = split[splitLength - 1]
clusteringType = split[splitLength - 2]
clusterSets.append({'file': f,'path':rootPath + '/', 'data':utility.arrayFromFile(rootPath + '/' + f), 'k':int(k), 'type':clusteringType})
return clusterSets
def generateKMeansSeries(activationsPath, labelIndexMappingPath, targetFolder):
if targetFolder.endswith("/") == False:
targetFolder += "/"
activations = utility.arrayFromFile(activationsPath)
labels = utility.getLabelStrings(labelIndexMappingPath)
neurons = activations.shape[1] - len(labels)
# test per label k-means
k = PER_LABEL_START
while k <= PER_LABEL_END:
runCounter = 0
while runCounter < RUNS_PER_TYPE:
logger.info("Calculating per label KMeans with k = " + str(k) + ".")
currentTarget = targetFolder + "perLabel_" + str(k) + "/run_" + str(runCounter) + "/"
if not os.path.exists(os.path.dirname(currentTarget)):
os.makedirs(os.path.dirname(currentTarget))
c, i = kMeans_per_label.findKMeansPerLabel(
activations, k, len(labels), currentTarget, labelIndexMappingPath
)
plot_cluster.plotClusters(kMeans_core.cleanUp(c), i, neurons, currentTarget, labels[: len(labels)])
runCounter += 1
k += 1
# test mixed k-means
k = MIXED_START
while k <= MIXED_END:
runCounter = 0
while runCounter < RUNS_PER_TYPE:
logger.info("Calculating mixed KMeans with k = " + str(k) + ".")
currentTarget = targetFolder + "mixed_" + str(k) + "/run_" + str(runCounter) + "/"
if not os.path.exists(os.path.dirname(currentTarget)):
os.makedirs(os.path.dirname(currentTarget))
[c, i] = kMeans_mixed.findKMeans(activations, k, len(labels), currentTarget)
plot_cluster.plotClusters(
kMeans_core.cleanUp(c), i, activations.shape[1] - len(labels), currentTarget, labels[: len(labels)]
)
runCounter += 1
k += MIXED_STEP
utility.plotConfusionMatrix(confusionMatrix, labels, currentTargetPath + "confusion.pdf")
kCounter += 1
results = np.array(results)
logger.info('Writing file ' + targetPath + "overview.csv")
np.savetxt( targetPath + "overview.csv", results, delimiter=',')
utility.plotKMeansOverview(results, targetPath + "overview.pdf", False)
if __name__ == '__main__':
if len(sys.argv) != 5 and len(sys.argv) != 6:
logger.info("Please provide as argument:")
logger.info("1) Path to training activations (*.npy).")
logger.info("2) Path to test activations (*.npy).")
logger.info("3) Path to label mapping.")
logger.info("4) Path for target folder.")
logger.info("5) Neighbour relations (optional)")
sys.exit();
trainingActivations = utility.arrayFromFile(sys.argv[1])
testActivations = utility.arrayFromFile(sys.argv[2])
labels = utility.getLabelStrings(sys.argv[3])
nn = None
if len(sys.argv) == 6:
nn = utility.arrayFromFile(sys.argv[5])
runTests(trainingActivations, testActivations, labels, sys.argv[4], nn)
with open(sys.argv[2], "r") as result:
for line in result.readlines():
split = line.strip().split(' ')
imagePaths.append(split[0])
# for rootPath, subdirs, files in os.walk(sys.argv[2]):
# for f in files:
# if f.endswith('.jpg'):
# imagePaths.append(rootPath + f)
clusters = None
if len(sys.argv) == 5:
clusters = pickle.load(sys.argv[4])
activations = utility.arrayFromFile(sys.argv[1])
if clusters == None:
[clusters, iterations] = kMeans.findKMeans(activations, K, 0,
targetPath)
for clusterIndex, cluster in enumerate(clusters):
for index in cluster['memberIndices']:
currentTarget = targetPath + str(clusterIndex) + "/"
if not os.path.exists(os.path.dirname(currentTarget)):
os.makedirs(os.path.dirname(currentTarget))
copyfile(imagePaths[index],
currentTarget + os.path.basename(imagePaths[index]))
currentTargetPath + "confusion.pdf")
kCounter += 1
results = np.array(results)
logger.info('Writing file ' + targetPath + "overview.csv")
np.savetxt(targetPath + "overview.csv", results, delimiter=',')
utility.plotKMeansOverview(results, targetPath + "overview.pdf", False)
if __name__ == '__main__':
if len(sys.argv) != 5 and len(sys.argv) != 6:
logger.info("Please provide as argument:")
logger.info("1) Path to training activations (*.npy).")
logger.info("2) Path to test activations (*.npy).")
logger.info("3) Path to label mapping.")
logger.info("4) Path for target folder.")
logger.info("5) Neighbour relations (optional)")
sys.exit()
trainingActivations = utility.arrayFromFile(sys.argv[1])
testActivations = utility.arrayFromFile(sys.argv[2])
labels = utility.getLabelStrings(sys.argv[3])
nn = None
if len(sys.argv) == 6:
nn = utility.arrayFromFile(sys.argv[5])
runTests(trainingActivations, testActivations, labels, sys.argv[4], nn)
if __name__ == '__main__':
indexLabelMappingPath = None
activationsPath = ""
if len(sys.argv) != 4 and len(sys.argv) != 5:
logger.info("Please provide as argument:")
logger.info("1) npy-file with activations.")
logger.info("2) The the number of neurons.")
logger.info("3) The target path.")
logger.info("3) The path to the index label mapping (optional).")
sys.exit()
activationsPath = sys.argv[1]
neurons = int(sys.argv[2])
targetPath = sys.argv[3]
if len(sys.argv) == 5:
indexLabelMappingPath = sys.argv[4]
activations = utility.arrayFromFile(activationsPath)
if targetPath.endswith('/') == False:
targetPath += '/'
if not os.path.exists(os.path.dirname(targetPath)):
os.makedirs(os.path.dirname(targetPath))
labelCount = activations[0,neurons:].shape[0]
plotActivations(activations, labelCount, targetPath, indexLabelMappingPath)
clusterHistograms = clusters[:,neurons:]
plotPositions(positions, additionalRows, targetPath)
plotLabelGrid(clusterHistograms, labelCount, labels, targetPath)
if __name__ == '__main__':
if len(sys.argv) != 5 and len(sys.argv) != 6:
logger.info("Please provide as arguments:")
logger.info("1) Cluster file (*.npy).")
logger.info("2) Iterations file (*.npy)")
logger.info("3) The the number of activation neurons.")
logger.info("4) The target path.")
logger.info("5) The path to the index label mapping (optional).")
sys.exit()
labels = None
if len(sys.argv) == 6:
labels = utility.getLabelStrings(sys.argv[5])
clusters = utility.arrayFromFile(sys.argv[1])
iterations = loadArray(sys.argv[2])
neurons = int(sys.argv[3])
targetPath = sys.argv[4]
if targetPath.endswith('/') == False:
targetPath += '/'
evaluateClusters(clusters, iterations, neurons, targetPath, labels)
