def __init__(self, path=DEFAULT_MODEL_PATH):
# TODO Replace this part with SavedModel
g = tf.Graph()
with g.as_default():
model = inference_wrapper.InferenceWrapper()
restore_fn = model.build_graph_from_config(configuration.ModelConfig(),
path)
g.finalize()
self.model = model
sess = tf.Session(graph=g)
# Load the model from checkpoint.
restore_fn(sess)
self.sess = sess
def main(_):
# Build the inference graph.
g = tf.Graph()
FLAGS.checkpoint_path = 'checkpoint/model2.ckpt-2000000'
FLAGS.input_files = '../assets/COCO_val2014_000000224477.jpg'
FLAGS.vocab_file = '../assets/word_counts.txt'
# TODO Replace this part with SavedModel
with g.as_default():
model = inference_wrapper.InferenceWrapper()
restore_fn = model.build_graph_from_config(configuration.ModelConfig(),
FLAGS.checkpoint_path)
g.finalize()
# Create the vocabulary.
vocab = vocabulary.Vocabulary(FLAGS.vocab_file)
filenames = []
for file_pattern in FLAGS.input_files.split(","):
filenames.extend(tf.gfile.Glob(file_pattern))
tf.logging.info("Running caption generation on %d files matching %s",
len(filenames), FLAGS.input_files)
with tf.Session(graph=g) as sess:
# Load the model from checkpoint.
restore_fn(sess)
# Prepare the caption generator. Here we are implicitly using the default
# beam search parameters. See caption_generator.py for a description of the
# available beam search parameters.
generator = caption_generator.CaptionGenerator(model, vocab)
for filename in filenames:
with tf.gfile.GFile(filename, "rb") as f:
image = f.read()
captions = generator.beam_search(sess, image)
print("Captions for image %s:" % os.path.basename(filename))
for i, caption in enumerate(captions):
# Ignore begin and end words.
sentence = [
vocab.id_to_word(w) for w in caption.sentence[1:-1]
]
sentence = " ".join(sentence)
print(" %d) %s (p=%f)" %
(i, sentence, math.exp(caption.logprob)))