def gen_lyric():
batch_size = 1
poems_vector, word_int_map, vocabularies = process_lyrics(FLAGS.file_path)
input_data = tf.placeholder(tf.int32, [batch_size, None])
end_points = rnn_model(model='lstm', input_data=input_data, output_data=None, vocab_size=len(
vocabularies), rnn_size=128, num_layers=2, batch_size=64, learning_rate=FLAGS.learning_rate)
saver = tf.train.Saver(tf.global_variables())
init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer())
with tf.Session() as sess:
sess.run(init_op)
checkpoint = tf.train.latest_checkpoint(FLAGS.checkpoints_dir)
saver.restore(sess, checkpoint)
x = np.array([list(map(word_int_map.get, start_token))])
[predict, last_state] = sess.run([end_points['prediction'], end_points['last_state']],
feed_dict={input_data: x})
word = to_word(predict, vocabularies)
print(word)
lyric = ''
while word != end_token:
lyric += word
x = np.zeros((1, 1))
x[0, 0] = word_int_map[word]
[predict, last_state] = sess.run([end_points['prediction'], end_points['last_state']],
feed_dict={input_data: x, end_points['initial_state']: last_state})
word = to_word(predict, vocabularies)
# word = words[np.argmax(probs_)]
return lyric
def run_training():
if not os.path.exists(os.path.dirname(FLAGS.checkpoints_dir)):
os.mkdir(os.path.dirname(FLAGS.checkpoints_dir))
if not os.path.exists(FLAGS.checkpoints_dir):
os.mkdir(FLAGS.checkpoints_dir)
poems_vector, word_to_int, vocabularies = process_lyrics(FLAGS.file_path)
batches_inputs, batches_outputs = generate_batch(FLAGS.batch_size, poems_vector, word_to_int)
input_data = tf.placeholder(tf.int32, [FLAGS.batch_size, None])
output_targets = tf.placeholder(tf.int32, [FLAGS.batch_size, None])
end_points = rnn_model(model='lstm', input_data=input_data, output_data=output_targets, vocab_size=len(
vocabularies), rnn_size=128, num_layers=2, batch_size=FLAGS.batch_size, learning_rate=FLAGS.learning_rate)
saver = tf.train.Saver(tf.global_variables())
init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer())
with tf.Session() as sess:
# sess = tf_debug.LocalCLIDebugWrapperSession(sess=sess)
# sess.add_tensor_filter("has_inf_or_nan", tf_debug.has_inf_or_nan)
sess.run(init_op)
start_epoch = 0
checkpoint = tf.train.latest_checkpoint(FLAGS.checkpoints_dir)
if checkpoint:
saver.restore(sess, checkpoint)
print("[INFO] restore from the checkpoint {0}".format(checkpoint))
start_epoch += int(checkpoint.split('-')[-1])
print('[INFO] start training...')
try:
for epoch in range(start_epoch, FLAGS.epochs):
n = 0
n_chunk = len(poems_vector) // FLAGS.batch_size
for batch in range(n_chunk):
loss, _, _ = sess.run([
end_points['total_loss'],
end_points['last_state'],
end_points['train_op']
], feed_dict={input_data: batches_inputs[n], output_targets: batches_outputs[n]})
n += 1
print('[INFO] Epoch: %d , batch: %d , training loss: %.6f' % (epoch, batch, loss))
if epoch % 20 == 0:
saver.save(sess, os.path.join(FLAGS.checkpoints_dir, FLAGS.model_prefix), global_step=epoch)
except KeyboardInterrupt:
print('[INFO] Interrupt manually, try saving checkpoint for now...')
saver.save(sess, os.path.join(FLAGS.checkpoints_dir, FLAGS.model_prefix), global_step=epoch)
print('[INFO] Last epoch were saved, next time will start from epoch {}.'.format(epoch))