num = 0
count = 0
for line in sys.stdin:
if num % 1000 == 0:
print(num, file=sys.stderr)
num += 1
l = line.rstrip().split('\t')
img = l[0]
img_end = IMAGE_FEATURE_LEN + 1
img_feature = [float(x) for x in l[1:img_end]]
texts = [x.split('\x01')[0] for x in l[img_end:]]
for text in texts:
words = segmentor.Segment(text, FLAGS.seg_method)
word_ids = [
vocabulary.id(word) for word in words
if vocabulary.has(word) or ENCODE_UNK
]
word_ids_length = len(word_ids)
if num % 1000 == 0:
#print(libgezi.gbk2utf8('\t'.join(words)), file=sys.stderr)
print('\t'.join(words), file=sys.stderr)
print(word_ids, file=sys.stderr)
if len(word_ids) == 0:
continue
word_ids = word_ids[:TEXT_MAX_WORDS]
if FLAGS.pad:
word_ids = gezi.pad(word_ids, TEXT_MAX_WORDS, 0)
if writer is not None:
example = tf.train.Example(features=tf.train.Features(
feature={
predictor = melt.Predictor('./model.ckpt-12000')
#vocabulary.init()
#vocab = vocabulary.vocab
vocab = Vocabulary(FLAGS.vocab, NUM_RESERVED_IDS)
ids_list = []
text_list = []
for line in open('./test.txt'):
text = line.strip().split('\t')[-1]
text_list.append(text)
words = line.split()
ids = [
vocab.id(word) for word in text.split(WORDS_SEP)
if vocab.has(word) or ENCODE_UNK
]
ids = gezi.pad(ids, TEXT_MAX_WORDS)
ids_list.append(ids)
ids_list = np.array(ids_list)
def bulk_predict(predictor, images, texts):
scores = predictor.inference(
'score', {
'%s/%s' % (FLAGS.algo, FLAGS.image_feature_place): images,
'%s/%s' % (FLAGS.algo, FLAGS.text_place): texts
})
return scores
