def createTrainingSupervisedDataSet(self,msrcImages , scale , keepClassDistTrain):
print "\tSplitting MSRC data into train, test, valid data sets."
splitData = pomio.splitInputDataset_msrcData(msrcImages, scale, keepClassDistTrain)
print "\tNow generating features for each training image."
trainData = FeatureGenerator.processLabeledImageData(splitData[0], ignoreVoid=True)
features = trainData[0]
numDataPoints = np.shape(features)[0]
numFeatures = np.shape(features)[1]
labels = trainData[1]
numLabels = np.size(labels) #!!error! nb unique labels, or max label
assert numDataPoints == numLabels , "Number of feature data points and number of labels not equal!"
dataSetTrain = ClassificationDataSet(numFeatures , numClasses)
print "\tNow adding all data points to the ClassificationDataSet..."
for idx in range(0,numDataPoints):
feature = trainData[0][idx]
label = trainData[1][idx]
binaryLabels = np.zeros(numClasses)
# to cope with the removal of void class (idx 13)
if label < voidClass:
binaryLabels[label] = 1
else:
binaryLabels[label-1] = 1
dataSetTrain.addSample(feature , binaryLabels)
print "\tAdded" , np.size(trainData) , " labeled data points to DataSet."
return dataSetTrain
def createTrainingSupervisedDataSet(self, msrcImages, scale,
keepClassDistTrain):
print "\tSplitting MSRC data into train, test, valid data sets."
splitData = pomio.splitInputDataset_msrcData(msrcImages, scale,
keepClassDistTrain)
print "\tNow generating features for each training image."
trainData = FeatureGenerator.processLabeledImageData(splitData[0],
ignoreVoid=True)
features = trainData[0]
numDataPoints = np.shape(features)[0]
numFeatures = np.shape(features)[1]
labels = trainData[1]
numLabels = np.size(labels) #!!error! nb unique labels, or max label
assert numDataPoints == numLabels, "Number of feature data points and number of labels not equal!"
dataSetTrain = ClassificationDataSet(numFeatures, numClasses)
print "\tNow adding all data points to the ClassificationDataSet..."
for idx in range(0, numDataPoints):
feature = trainData[0][idx]
label = trainData[1][idx]
binaryLabels = np.zeros(numClasses)
# to cope with the removal of void class (idx 13)
if label < voidClass:
binaryLabels[label] = 1
else:
binaryLabels[label - 1] = 1
dataSetTrain.addSample(feature, binaryLabels)
print "\tAdded", np.size(trainData), " labeled data points to DataSet."
return dataSetTrain
def getSuperPixelTrainingData(msrcDataDirectory,
nbSuperPixels,
superPixelCompactness,
scale,
trainSplit=0.6,
validationSplit=0.2,
testSplit=0.2):
# Should probably make this a call to pomio in case the ordering changes in the future...
voidClassLabel = pomio.getVoidIdx()
# These could be user-specified
if scale == None:
scale = 0.05 # default to 10% of data
msrcData = pomio.msrc_loadImages(msrcDataDirectory, None)
print "Now generating superpixel classifier for MSRC data"
# splitData = pomio.splitInputDataset_msrcData(msrcData, datasetScale=scale, keepClassDistForTraining=True, trainSplit, validationSplit, testSplit )
splitData = pomio.splitInputDataset_msrcData(msrcData, scale, True,
trainSplit, validationSplit,
testSplit)
# prepare superpixel training data
trainingMsrcImages = splitData[0]
# Just use the above function to get superpixel features and labels for training data
return SuperPixelClassifier.getSuperPixelData(trainingMsrcImages,
nbSuperPixels,
superPixelCompactness)
def getSuperPixelTrainingData(msrcDataDirectory, nbSuperPixels,superPixelCompactness, scale, trainSplit=0.6, validationSplit=0.2, testSplit=0.2):
# Should probably make this a call to pomio in case the ordering changes in the future...
voidClassLabel = pomio.getVoidIdx()
# These could be user-specified
if scale == None:
scale = 0.05 # default to 10% of data
msrcData = pomio.msrc_loadImages(msrcDataDirectory, None)
print "Now generating superpixel classifier for MSRC data"
# splitData = pomio.splitInputDataset_msrcData(msrcData, datasetScale=scale, keepClassDistForTraining=True, trainSplit, validationSplit, testSplit )
splitData = pomio.splitInputDataset_msrcData(msrcData, scale, True, trainSplit, validationSplit, testSplit )
# prepare superpixel training data
trainingMsrcImages = splitData[0]
# Just use the above function to get superpixel features and labels for training data
return SuperPixelClassifier.getSuperPixelData(trainingMsrcImages,nbSuperPixels,superPixelCompactness)
else:
# we get here if we have non-default splits
writeDataType = True
# Do the expected thing if we have a non-default split
if args.v:
print "Loading data"
if writeDataType == True:
# Get train, test and cv datasets
print "\nSplitting data into sets: train =", trainSplit, "test =", testSplit, "cvSplit =", cvSplit
keepClassDistForTraining = False #!!
[trainData, cvData, testData] = pomio.splitInputDataset_msrcData(
pomio.msrc_loadImages(msrcDataDirectory, subset=None),
scaleFrac,
keepClassDistForTraining,
trainSplit,
cvSplit,
testSplit,
)
assert trainData != None, "Training data object is null"
assert len(trainData) > 0, "Training data contains no data"
if testData == None or len(testData) == 0:
print "WARNING: Testing data contains no data"
print "Creating training set from %d images, and test set from %d images" % (len(trainData), len(testData))
# Process and persist feature and labels for superpixels in image dataset
print "Create & save training feature and label superpixel data"
createAndSaveFeatureLabelData(
'Images/9_2_s.bmp'])
elif subsetType == 2:
msrcImages = pomio.msrc_loadImages(msrcData, ['Images/7_3_s.bmp'] )
else:
# Load all images
msrcImages = pomio.msrc_loadImages(msrcData)
if doVal or doTest:
scale = 0.1
# Generate data from images and save to file
print "\nProcessing " + str(scale*100) + \
"% of MSRC data on a 60/20/20 split serialised for easier file IO"
splitData = pomio.splitInputDataset_msrcData(
msrcImages,
datasetScale=scale,
keepClassDistForTraining=True,
trainSplit=0.6,
validationSplit=0.2,
testSplit=0.2
)
validationDataset = splitData[1]
testDataset = splitData[2]
if doVal:
print "Processing validation data::"
validationData = FeatureGenerator.processLabeledImageData(validationDataset, ignoreVoid=True)
if doTest:
print "Processing test data::"
testingData = FeatureGenerator.processLabeledImageData(testDataset, ignoreVoid=True)
'Images/9_2_s.bmp'])
elif subsetType == 2:
msrcImages = pomio.msrc_loadImages(msrcData, ['Images/7_3_s.bmp'])
else:
# Load all images
msrcImages = pomio.msrc_loadImages(msrcData)
if doVal or doTest:
scale = 0.1
# Generate data from images and save to file
print "\nProcessing " + str(scale*100) + \
"% of MSRC data on a 60/20/20 split serialised for easier file IO"
splitData = pomio.splitInputDataset_msrcData(
msrcImages,
datasetScale=scale,
keepClassDistForTraining=True,
trainSplit=0.6,
validationSplit=0.2,
testSplit=0.2)
validationDataset = splitData[1]
testDataset = splitData[2]
if doVal:
print "Processing validation data::"
validationData = FeatureGenerator.processLabeledImageData(
validationDataset, ignoreVoid=True)
if doTest:
print "Processing test data::"
testingData = FeatureGenerator.processLabeledImageData(
if (trainSplit == 1.0) and (cvSplit == 0.0 and testSplit == 0.0):
writeDataType = False
else:
# we get here if we have non-default splits
writeDataType = True
# Do the expected thing if we have a non-default split
if args.v:
print 'Loading data'
if writeDataType == True:
# Get train, test and cv datasets
print "\nSplitting data into sets: train =", trainSplit, "test =", testSplit, "cvSplit =", cvSplit
keepClassDistForTraining = False #!!
[trainData, cvData, testData] = pomio.splitInputDataset_msrcData(\
pomio.msrc_loadImages(msrcDataDirectory, subset=None),
scaleFrac, keepClassDistForTraining, trainSplit , cvSplit , testSplit)
assert trainData != None, "Training data object is null"
assert len(trainData) > 0, "Training data contains no data"
if testData == None or len(testData) == 0:
print 'WARNING: Testing data contains no data'
print "Creating training set from %d images, and test set from %d images" % (
len(trainData), len(testData))
# Process and persist feature and labels for superpixels in image dataset
print "Create & save training feature and label superpixel data"
createAndSaveFeatureLabelData(trainData, outfileBase, "train", outfileType,
numberSuperPixels, superPixelCompactness,
