def testNeuralGPU(self):
hparams = common_hparams.basic_params1()
batch_size = 3
input_length = 5
target_length = input_length
input_vocab_size = 9
target_vocab_size = 11
p_hparams = problem_hparams.test_problem_hparams(
input_vocab_size, target_vocab_size)
inputs = -1 + np.random.random_integers(
input_vocab_size, size=(batch_size, input_length, 1, 1))
targets = -1 + np.random.random_integers(
target_vocab_size, size=(batch_size, target_length, 1, 1))
with self.test_session() as session:
features = {
"inputs": tf.constant(inputs, dtype=tf.int32),
"targets": tf.constant(targets, dtype=tf.int32)
}
model = neural_gpu.NeuralGPU(hparams, tf.estimator.ModeKeys.TRAIN,
p_hparams)
shadred_logits, _ = model.model_fn(features)
logits = tf.concat(shadred_logits, 0)
session.run(tf.global_variables_initializer())
res = session.run(logits)
self.assertEqual(res.shape,
(batch_size, target_length, 1, 1, target_vocab_size))
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 testTransformer(self):
batch_size = 3
input_length = 5
target_length = 7
vocab_size = 9
hparams = transformer_revnet_test()
p_hparams = problem_hparams.test_problem_hparams(vocab_size, vocab_size)
hparams.problems = [p_hparams]
inputs = -1 + np.random.random_integers(
vocab_size, size=(batch_size, input_length, 1, 1))
targets = -1 + np.random.random_integers(
vocab_size, size=(batch_size, target_length, 1, 1))
features = {
"inputs": tf.constant(inputs, dtype=tf.int32),
"targets": tf.constant(targets, dtype=tf.int32),
"target_space_id": tf.constant(1, dtype=tf.int32),
}
model = transformer_revnet.TransformerRevnet(
hparams, tf.estimator.ModeKeys.TRAIN, p_hparams)
sharded_logits, _ = model.model_fn(features)
logits = tf.concat(sharded_logits, 0)
grads = tf.gradients(
tf.reduce_mean(logits), [features["inputs"]] + tf.global_variables())
grads = [g for g in grads if g is not None]
with self.test_session() as session:
session.run(tf.global_variables_initializer())
logits_val, _ = session.run([logits, grads])
self.assertEqual(logits_val.shape, (batch_size, target_length, 1, 1,
vocab_size))
def testByteNet(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 = bytenet.bytenet_base()
p_hparams = problem_hparams.test_problem_hparams(vocab_size, vocab_size)
with self.test_session() as session:
features = {
"inputs": tf.constant(x, dtype=tf.int32),
"targets": tf.constant(y, dtype=tf.int32),
}
model = bytenet.ByteNet(
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, 50, 1, 1, vocab_size))
def getModel(self, hparams, mode=tf.estimator.ModeKeys.TRAIN):
hparams.hidden_size = 8
hparams.filter_size = 32
hparams.num_heads = 1
hparams.layer_prepostprocess_dropout = 0.0
p_hparams = problem_hparams.test_problem_hparams(
VOCAB_SIZE, VOCAB_SIZE)
hparams.problems = [p_hparams]
inputs = -1 + np.random.random_integers(
VOCAB_SIZE, size=(BATCH_SIZE, INPUT_LENGTH, 1, 1))
targets = -1 + np.random.random_integers(
VOCAB_SIZE, size=(BATCH_SIZE, TARGET_LENGTH, 1, 1))
features = {
"inputs": tf.constant(inputs, dtype=tf.int32),
"targets": tf.constant(targets, dtype=tf.int32),
"target_space_id": tf.constant(1, dtype=tf.int32),
}
return transformer.Transformer(hparams, tf.estimator.ModeKeys.PREDICT,
p_hparams), features