def create_model(session, vocab_size, forward_only): model = NLCModel( vocab_size, FLAGS.size, FLAGS.num_layers, FLAGS.max_gradient_norm, FLAGS.batch_size, FLAGS.learning_rate, FLAGS.learning_rate_decay_factor, FLAGS.dropout, forward_only=forward_only) checkpoint_file = tf.train.latest_checkpoint(FLAGS.train_dir) print("checkpoint file", checkpoint_file) if checkpoint_file: print("Reading model parameters from %s" % checkpoint_file) model.saver.restore(session, checkpoint_file) else: print("Created model with fresh parameters.") session.run(tf.global_variables_initializer()) return model
def create_model(session, vocab_size, forward_only): model = NLCModel( vocab_size, FLAGS.size, FLAGS.num_layers, FLAGS.max_gradient_norm, FLAGS.batch_size, FLAGS.learning_rate, FLAGS.learning_rate_decay_factor, FLAGS.dropout, forward_only=forward_only, optimizer=FLAGS.optimizer) checkpoint_file = tf.train.latest_checkpoint(FLAGS.train_dir) if checkpoint_file: logging.info("Reading model parameters from %s" % checkpoint_file) model.saver.restore(session, checkpoint_file) else: logging.info("Created model with fresh parameters.") session.run(tf.global_variables_initializer()) logging.info('Num params: %d' % sum(v.get_shape().num_elements() for v in tf.trainable_variables())) return model
def create_model(session, vocab_size, forward_only): model = NLCModel( vocab_size, FLAGS.size, FLAGS.num_layers, FLAGS.max_gradient_norm, FLAGS.batch_size, FLAGS.learning_rate, FLAGS.learning_rate_decay_factor, FLAGS.dropout, forward_only=forward_only) ckpt_paths = [f for f in os.listdir(FLAGS.train_dir) if (re.search(r"best\.ckpt-\d+", f) \ and not f.endswith("meta"))] assert (len(ckpt_paths) > 0) ckpt_paths = sorted(ckpt_paths, key=lambda x: int(x.split("-")[-1])) ckpt_path = os.path.join(FLAGS.train_dir, ckpt_paths[-1]) if tf.gfile.Exists(ckpt_path): print("Reading model parameters from %s" % ckpt_path) model.saver.restore(session, ckpt_path) else: assert (False) return model