def hack_image_features(image_features):
try:
if len(image_features[0]) == IMAGE_FEATURE_LEN and len(
image_features[1]) == IMAGE_FEATURE_LEN:
return image_features
else:
return np.array(
[gezi.nppad(x, TEXT_MAX_WORDS) for x in image_features])
except Exception:
return np.array(
[gezi.nppad(x, TEXT_MAX_WORDS) for x in image_features])
def init():
#for evaluation without train will also use evaluator so only set log path in train.py
#logging.set_logging_path(FLAGS.model_dir)
test_dir = FLAGS.valid_resource_dir
global all_distinct_texts, all_distinct_text_strs
global vocab, vocab_size
if all_distinct_texts is None:
print('loading valid resorce from:', test_dir)
vocabulary.init()
vocab = vocabulary.vocab
vocab_size = vocabulary.vocab_size
if os.path.exists(test_dir + '/distinct_texts.npy'):
all_distinct_texts = np.load(test_dir + '/distinct_texts.npy')
else:
all_distinct_texts = []
#to avoid outof gpu mem
all_distinct_texts = all_distinct_texts[:FLAGS.max_texts]
print('all_distinct_texts len:',
len(all_distinct_texts),
file=sys.stderr)
#--padd it as test data set might be smaller in shape[1]
all_distinct_texts = np.array(
[gezi.nppad(text, TEXT_MAX_WORDS) for text in all_distinct_texts])
if FLAGS.feed_dict:
all_distinct_texts = texts2ids(evaluator.all_distinct_text_strs)
if os.path.exists(test_dir + '/distinct_text_strs.npy'):
all_distinct_text_strs = np.load(test_dir +
'/distinct_text_strs.npy')
else:
all_distinct_text_strs = []
def run():
m = {}
files = glob.glob(FLAGS.image_feature_pattern)
for file in files:
for line in open(file):
l = line.strip().split('\t')
m[l[0]] = l[-1]
for i, line in enumerate(open(FLAGS.image_file)):
image = line.strip()
if image not in m:
print('image not find in ', FLAGS.image_feature_pattern)
exit(0)
image_feature = m[image].split('\x01')
image_feature = [float(x) for x in image_feature]
timer = gezi.Timer()
word_ids_list = np.load(FLAGS.all_texts)
word_ids_list = np.array(
[gezi.nppad(text, TEXT_MAX_WORDS) for text in word_ids_list])
all_text_strs = np.load(FLAGS.all_text_strs)
scores = predicts([image_feature], word_ids_list)
print(img_html.format(image))
topn = 50
indexes = (-scores).argsort()[:topn]
for i, index in enumerate(indexes):
print(i, all_text_strs[index], scores[index])
print('<br>')
print(i, image, timer.elapsed(), file=sys.stderr)
def init(image_model_=None):
global inited
if inited:
return
test_dir = FLAGS.valid_resource_dir
global all_distinct_texts, all_distinct_text_strs
global vocab, vocab_size
if all_distinct_texts is None:
print('loading valid resource from:', test_dir)
#vocabulary.init()
text2ids.init()
vocab = vocabulary.vocab
vocab_size = vocabulary.vocab_size
if os.path.exists(test_dir + '/distinct_texts.npy'):
all_distinct_texts = np.load(test_dir + '/distinct_texts.npy')
else:
all_distinct_texts = []
#to avoid outof gpu mem
#all_distinct_texts = all_distinct_texts[:FLAGS.max_texts]
print('all_distinct_texts len:', len(all_distinct_texts), file=sys.stderr)
#--padd it as test data set might be smaller in shape[1]
all_distinct_texts = np.array([gezi.nppad(text, TEXT_MAX_WORDS) for text in all_distinct_texts])
if FLAGS.feed_dict:
all_distinct_texts = texts2ids(evaluator.all_distinct_text_strs)
if os.path.exists(test_dir + '/distinct_text_strs.npy'):
all_distinct_text_strs = np.load(test_dir + '/distinct_text_strs.npy')
else:
all_distinct_text_strs = []
init_labels()
#for evaluation without train will also use evaluator so only set log path in train.py
#logging.set_logging_path(FLAGS.model_dir)
if FLAGS.assistant_model_dir:
global assistant_predictor
#use another session different from main graph, otherwise variable will be destroy/re initailized in melt.flow
#by default now Predictor using tf.Session already, here for safe, if use same session then not work
#NOTICE must use seperate sess!!
if is_raw_image(image_features) and not melt.varname_in_checkpoint(FLAGS.image_model_name, FLAGS.assistant_model_dir):
print('assist predictor use deepiu.util.sim_predictor.SimPredictor as is raw image as input')
global image_model
if image_model_ is not None:
image_model = image_model_
else:
image_model = melt.image.ImageModel(FLAGS.image_checkpoint_file,
FLAGS.image_model_name,
feature_name=None)
assistant_predictor = deepiu.util.sim_predictor.SimPredictor(FLAGS.assistant_model_dir, image_model=image_model)
print('assistant predictor init ok')
else:
assistant_predictor = melt.SimPredictor(FLAGS.assistant_model_dir)
print('assistant_predictor', assistant_predictor)
inited = True
def hack_image_features(image_features):
"""
the hack is for textsim use ltext as image(similar), so hack for it
"""
#first for real image but not dump feature, use original encoded image since big, we assume
#pre save binary pics and can refer to pic in disk by pic name and pic dir
assert len(image_features) > 0
if isinstance(image_features[0], np.string_):
#return np.array([melt.read_image(pic_path) for pic_path in image_features])
return image_features
try:
if len(image_features[0]) == IMAGE_FEATURE_LEN and len(image_features[1]) == IMAGE_FEATURE_LEN:
return image_features
else:
return np.array([gezi.nppad(x, TEXT_MAX_WORDS) for x in image_features])
except Exception:
return np.array([gezi.nppad(x, TEXT_MAX_WORDS) for x in image_features])