def process_folder(folder,
rules=large_train,
negativeMultiplicator=3,
interestingWindowsFolder=None,
datasetCreator=None,
onlyFirstTagSymbol=False,
positiveWindowNeighboursAmount=7):
files = []
acceptableExtensions = ('jpg', 'jpeg', 'png')
for filename in os.listdir(folder):
if filename.lower().endswith(acceptableExtensions):
files.append(os.path.join(folder, filename))
trainAmount = 0
for c in rules:
if c.cond_function(len(files)):
if c.train >= 1:
trainAmount = c.train
else:
trainAmount = int(len(files) * c.train)
break
# testAmount = len(files) - trainAmount
# if testAmount <= 0:
# testAmount = 0
random.shuffle(files)
trainFiles = set(files[:trainAmount])
testFiles = set(files[trainAmount:])
tagPosition = getTagCoordinates(folder)
if onlyFirstTagSymbol:
tp = tagPosition
tagPosition = [tp[0], tp[1], tp[2], tp[1] + (tp[2] - tp[0])]
if datasetCreator is None:
datasetCreator = DatasetCreator()
datasetCreator.prepareImageProcessing(trainFiles,
testFiles,
tagPosition,
negativeMultiplicator,
interestingWindowsFolder,
positiveWindowNeighboursAmount
)
return datasetCreator
