def testVqaAttentionBaseline(self):
batch_size = 3
image_size = 448
vocab_size = 100
num_classes = 10
question_length = 5
answer_length = 10
x = 2 * np.random.rand(batch_size, image_size, image_size, 3) - 1
q = np.random.randint(1,
high=vocab_size,
size=(batch_size, question_length, 1, 1))
a = np.random.randint(num_classes + 1,
size=(batch_size, answer_length, 1, 1))
hparams = vqa_attention.vqa_attention_base()
p_hparams = problem_hparams.test_problem_hparams(
vocab_size, num_classes + 1, hparams)
p_hparams.modality["inputs"] = modalities.ModalityType.IMAGE
p_hparams.modality["targets"] = modalities.ModalityType.MULTI_LABEL
p_hparams.modality["question"] = modalities.ModalityType.SYMBOL
p_hparams.vocab_size["question"] = vocab_size
with self.test_session() as session:
features = {
"inputs": tf.constant(x, dtype=tf.float32),
"question": tf.constant(q, dtype=tf.int32),
"targets": tf.constant(a, dtype=tf.int32),
}
model = vqa_attention.VqaAttentionBaseline(
hparams, tf.estimator.ModeKeys.TRAIN, p_hparams)
logits, losses = model(features)
session.run(tf.global_variables_initializer())
logits_, losses_ = session.run([logits, losses])
self.assertEqual(logits_.shape, (batch_size, 1, 1, 1, num_classes + 1))
self.assertEqual(losses_["training"].shape, ())
def testVqaAttentionBaseline(self):
batch_size = 3
image_size = 448
vocab_size = 100
num_classes = 10
question_length = 5
answer_length = 10
x = 2 * np.random.rand(batch_size, image_size, image_size, 3) - 1
q = np.random.random_integers(
1, high=vocab_size - 1, size=(batch_size, question_length, 1, 1))
a = np.random.random_integers(
0, high=num_classes, size=(batch_size, answer_length, 1, 1))
hparams = vqa_attention.vqa_attention_base()
p_hparams = problem_hparams.test_problem_hparams(vocab_size, vocab_size)
p_hparams.input_modality["inputs"] = (registry.Modalities.IMAGE, None)
p_hparams.input_modality["question"] = (registry.Modalities.SYMBOL,
vocab_size)
p_hparams.target_modality = (registry.Modalities.CLASS_LABEL
+ ":multi_label", num_classes + 1)
with self.test_session() as session:
features = {
"inputs": tf.constant(x, dtype=tf.float32),
"question": tf.constant(q, dtype=tf.int32),
"targets": tf.constant(a, dtype=tf.int32),
}
model = vqa_attention.VqaAttentionBaseline(
hparams, tf.estimator.ModeKeys.TRAIN, p_hparams)
logits, losses = model(features)
session.run(tf.global_variables_initializer())
logits_, losses_ = session.run([logits, losses])
self.assertEqual(logits_.shape, (batch_size, 1, 1, 1, num_classes + 1))
self.assertEqual(losses_["training"].shape, ())
def testVqaAttentionBaseline(self):
batch_size = 3
image_size = 448
vocab_size = 100
num_classes = 10
question_length = 5
answer_length = 10
x = 2 * np.random.rand(batch_size, image_size, image_size, 3) - 1
q = np.random.random_integers(
1, high=vocab_size - 1, size=(batch_size, question_length, 1, 1))
a = np.random.random_integers(
0, high=num_classes, size=(batch_size, answer_length, 1, 1))
hparams = vqa_attention.vqa_attention_base()
p_hparams = problem_hparams.test_problem_hparams(vocab_size,
vocab_size,
hparams)
p_hparams.modality["inputs"] = modalities.ImageModality(hparams)
p_hparams.modality["question"] = modalities.SymbolModality(
hparams, vocab_size)
p_hparams.modality["targets"] = modalities.MultiLabelModality(
hparams, num_classes + 1)
with self.test_session() as session:
features = {
"inputs": tf.constant(x, dtype=tf.float32),
"question": tf.constant(q, dtype=tf.int32),
"targets": tf.constant(a, dtype=tf.int32),
}
model = vqa_attention.VqaAttentionBaseline(
hparams, tf.estimator.ModeKeys.TRAIN, p_hparams)
logits, losses = model(features)
session.run(tf.global_variables_initializer())
logits_, losses_ = session.run([logits, losses])
self.assertEqual(logits_.shape, (batch_size, 1, 1, 1, num_classes + 1))
self.assertEqual(losses_["training"].shape, ())