else:
for c in line:
transcript += c.encode('utf-8', 'backslashreplace') + ' '
return transcript.rstrip()
parser = argparse.ArgumentParser(
"Generate NC File for Urdu-1D-NoPos experiments")
parser.add_argument("-l", "--height", default=48, type=int)
parser.add_argument("-t", "--notargets", action="store_true")
parser.add_argument("-o", "--ncFileName", default=None)
parser.add_argument("files", nargs="*")
args = parser.parse_args()
#Read all file names
images = ocrolib.glob_all(args.files)
if len(images) == 0:
parser.print_help()
sys.exit(0)
print "# Input images:", len(images)
# load the OCRopus line normalizer (center)
print '# Loading OCRopus line normalizer'
lnorm = lineest.CenterNormalizer()
lnorm.setHeight(args.height)
counter = 0
print '# Reading %d Text-line images and corresponding transcription' % len(
images)
parser.add_argument("-v","--verbose",action="store_true")
parser.add_argument("-d","--display",type=int,default=0,
help="display output for every nth iteration, where n=DISPLAY, default: %(default)s")
parser.add_argument("-m","--movie",default=None)
parser.add_argument("-M","--moviesample",default=None)
parser.add_argument("-q","--quiet",action="store_true")
parser.add_argument("-Q","--nocheck",action="store_true")
parser.add_argument("-p","--pad",type=int,default=16)
# add file
parser.add_argument("-f","--file",default=None,help="path to file listing input files, one per line")
parser.add_argument("files",nargs="*")
args = parser.parse_args()
inputs = ocrolib.glob_all(args.files)
if args.file is not None:
print("getting training data from file")
with open(args.file) as file:
for l in file:
inputs.append(l.rstrip())
if len(inputs)==0:
parser.print_help()
sys.exit(0)
print("# inputs", len(inputs))
# pre-execute any python commands
if ncomps < lo: return "too few connected components (got %d, wanted >=%d)" % (ncomps, lo)
if ncomps > hi * ratio: return "too many connected components (got %d, wanted <=%d)" % (ncomps, hi)
return None
# compute the list of files to be classified
if len(args.files) < 1:
parser.print_help()
sys.exit(0)
print_info("")
print_info("#" * 10, (" ".join(sys.argv))[:60])
print_info("")
inputs = ocrolib.glob_all(args.files)
if not args.quiet: print_info("#inputs" + str(len(inputs)))
# disable parallelism when anything is being displayed
if args.show >= 0 or args.save is not None:
args.parallel = 1
# load the network used for classification
try:
network = ocrolib.load_object(args.model, verbose=1)
for x in network.walk(): x.postLoad()
for x in network.walk():
if isinstance(x, lstm.LSTM):
x.allocate(5000)