nbatch=int(args.nelementsperfile)
randomise = args.randomise
dc = DataCollection(infile)
dc2 = DataCollection(infile)
samples = dc.samples
dir = dc.dataDir
if len(dir)<1:
dir='.'
insamples = [dir+'/'+s for s in samples]
gen = TrainDataGenerator()
gen.setBatchSize(nbatch)
gen.setSkipTooLargeBatches(False)
gen.setFileList(insamples)
if randomise:
gen.shuffleFileList()
nbatches = gen.getNBatches()
newsamples=[]
for i in range(nbatches):
newname = str(samples[0][:-6]+"_n_"+str(i)+".djctd")
newsamples.append(newname)
ntd = gen.getBatch()
print(newname)
ntd.writeToFile(newname)
print('..written')
def invokeGenerator(self):
generator = TrainDataGenerator()
generator.setBatchSize(self.__batchsize)
generator.setSquaredElementsLimit(self.batch_uses_sum_of_squares)
generator.setFileList([self.dataDir + "/" + s for s in self.samples])
return generator