for key, val in class_options.iteritems():
print(key)
raise Exception('wrong class selection')
if not ".dc" in infile:
raise Exception('wrong input file '+infile)
dir = os.path.dirname(infile)
dcold = DCOld()
dcold.readRawFromFile(infile)
dcnew = DataCollection()
dcnew.dataclass = traind()
dcnew.samples = [s[:-4]+'djctd' for s in dcold.samples]
print(dcnew.samples)
dcnew.sourceList = dcold.originRoots
# leave traindata undefined no way to convert.
dcnew.__nsamples = 0 # determine again, also check
outfile = infile[:-2] +'djcdc'
print("infile: ", infile, " outfile", outfile)
def worker(i):
td = TDOld()
tdnew = TrainData()
print("converting",dcold.samples[i])
td.readIn(dir + dcold.samples[i])
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')
dc2.samples = newsamples
dc2.writeToFile(infile[:-5]+"_n.djcdc")
atexit.register(removeTmp)
#reduce memory footprint here
td.writeFromSourceFile(inputdir + "/" + inputfile,
dc.weighterobjects,
istraining=False,
"pred_tmp.djctd")
x = td.transferFeatureListToNumpy()
y = td.transferWeightListToNumpy()
w = td.transferTruthListToNumpy()
td.clear()
dc.samples = [tmpdir + "/pred_tmp.djctd"]
dc.setBatchSize(batchsize)
dc.invokeGenerator()
nbatches = dc.generator.getNBatches()
print('predicting ' + inputfile)
predicted = model.predict_generator(dc.generatorFunction(),
steps=nbatches,
max_queue_size=1,
use_multiprocessing=False,
verbose=1)
removeTmp()
if not type(
predicted