def testLSTMSeq2SeqAttention(self): vocab_size = 9 x = np.random.random_integers(1, high=vocab_size - 1, size=(3, 5, 1, 1)) y = np.random.random_integers(1, high=vocab_size - 1, size=(3, 6, 1, 1)) hparams = lstm.lstm_attention() p_hparams = problem_hparams.test_problem_hparams( vocab_size, vocab_size) x = tf.constant(x, dtype=tf.int32) x._shape = tf.TensorShape([None, None, 1, 1]) with self.test_session() as session: features = { "inputs": x, "targets": tf.constant(y, dtype=tf.int32), } model = lstm.LSTMSeq2seqAttention(hparams, tf.estimator.ModeKeys.TRAIN, p_hparams) sharded_logits, _ = model.model_fn(features) logits = tf.concat(sharded_logits, 0) session.run(tf.global_variables_initializer()) res = session.run(logits) self.assertEqual(res.shape, (3, 6, 1, 1, vocab_size))
def testLSTMSeq2SeqAttention(self): vocab_size = 9 x = np.random.randint(1, high=vocab_size, size=(3, 5, 1, 1)) y = np.random.randint(1, high=vocab_size, size=(3, 6, 1, 1)) hparams = lstm.lstm_attention() p_hparams = problem_hparams.test_problem_hparams(vocab_size, vocab_size, hparams) x = tf.constant(x, dtype=tf.int32) x = tf.placeholder_with_default(x, shape=[None, None, 1, 1]) with self.test_session() as session: features = { "inputs": x, "targets": tf.constant(y, dtype=tf.int32), } model = lstm.LSTMSeq2seqAttention( hparams, tf.estimator.ModeKeys.TRAIN, p_hparams) logits, _ = model(features) session.run(tf.global_variables_initializer()) res = session.run(logits) self.assertEqual(res.shape, (3, 6, 1, 1, vocab_size))