def load_model(self, model_config, vocabulary_file, embedding_matrix_file,
checkpoint_path):
"""Loads a skip-thoughts model.
Args:
model_config: Object containing parameters for building the model.
vocabulary_file: Path to vocabulary file containing a list of newline-
separated words where the word id is the corresponding 0-based index in
the file.
embedding_matrix_file: Path to a serialized numpy array of shape
[vocab_size, embedding_dim].
checkpoint_path: SkipThoughtsModel checkpoint file or a directory
containing a checkpoint file.
"""
tf.logging.info("Reading vocabulary from %s", vocabulary_file)
with tf.gfile.GFile(vocabulary_file, mode="r") as f:
lines = list(f.readlines())
try:
reverse_vocab = [line.decode("utf-8").strip() for line in lines]
except:
reverse_vocab = [line.strip() for line in lines]
tf.logging.info("Loaded vocabulary with %d words.", len(reverse_vocab))
tf.logging.info("Loading embedding matrix from %s",
embedding_matrix_file)
# Note: tf.gfile.GFile doesn't work here because np.load() calls f.seek()
# with 3 arguments.
try:
with open(embedding_matrix_file, "r") as f:
embedding_matrix = np.load(f)
except:
embedding_matrix = np.load(embedding_matrix_file)
tf.logging.info("Loaded embedding matrix with shape %s",
embedding_matrix.shape)
word_embeddings = collections.OrderedDict(
zip(reverse_vocab, embedding_matrix))
g = tf.Graph()
with g.as_default():
encoder = skip_thoughts_encoder.SkipThoughtsEncoder(
word_embeddings)
restore_model = encoder.build_graph_from_config(
model_config, checkpoint_path)
sess = tf.Session(graph=g)
restore_model(sess)
self.encoders.append(encoder)
self.sessions.append(sess)
def load_model(self,model_config,vocab_file, embedding_matrix_file, checkpoint_path):
with open(vocab_file,'r') as f:
lines=list(f.readlines())
#print(lines)
reverse_vocab=[line.strip() for line in lines]
embedding_matrix=np.load(embedding_matrix_file)
word_embeddings = collections.OrderedDict(zip(reverse_vocab,embedding_matrix))
encoder = skip_thoughts_encoder.SkipThoughtsEncoder(word_embeddings)
restore_model = encoder.build_graph_from_config(model_config,
checkpoint_path)
tf_sess = K.get_session()
restore_model(tf_sess)
self.encoders.append(encoder)
self.sessions.append(tf_sess)
