print('Type a seed word or sentence:')
seed = raw_input()
print('Start generating text for the seed "{0}"...'.format(seed))
# write seed to temporary file
out = io.open('tmp', 'w')
out.write(u'{0}'.format(seed))
out.close()
config['predict_next'] = 'tmp'
if 'char' in config:
data = lm_data.charSentenceDataRescore(config, eval_config, TRAIN,
VALID, TEST)
else:
data = lm_data.wordSentenceDataRescore(config, eval_config, TRAIN,
VALID, TEST)
all_data, vocab_size, _ = data.get_data()
# character-level training, in batches (across sentence boundaries)
elif 'char' in config:
print('Character-level data')
if 'per_sentence' in config:
print('Sentence per sentence')
data = lm_data.charSentenceData(config, eval_config, TRAIN, VALID,
TEST)
all_data, vocab_size, total_length, seq_lengths = data.get_data()
config['num_steps'] = total_length
# write maximum sentence length to file
# character-level training, in batches (cross sentence boundaries)
if 'char' in config:
data = lm_data.charData(config, eval_config)
all_data, vocab_size, _ = data.get_data()
# word-level training, on sentence level (sentences are padded until maximum sentence length)
elif 'per_sentence' in config:
if 'rescore' in config:
max_length = int(
open('{0}max_length'.format(
config['trained_model'])).readlines()[0].strip())
# set num_steps = total length of each (padded) sentence
config['num_steps'] = max_length
data = lm_data.wordSentenceDataRescore(config, eval_config)
all_data, vocab_size, _ = data.get_data()
else:
data = lm_data.wordSentenceData(config, eval_config)
all_data, vocab_size, total_length, seq_lengths = data.get_data()
# set num_steps = total length of each (padded) sentence
config['num_steps'] = total_length
print('Write max length of sentence to {0}max_length'.format(
config['save_path']))
# write maximum sentence length to file
max_length_f = open('{0}max_length'.format(config['save_path']),
'w')