def _test_resnet(self, img_size, output_size):
vocab_size = 9
batch_size = 2
x = np.random.random_integers(0,
high=255,
size=(batch_size, img_size, img_size, 3))
y = np.random.random_integers(1,
high=vocab_size - 1,
size=(batch_size, 1, 1, 1))
hparams = resnet_tiny_cpu()
p_hparams = problem_hparams.test_problem_hparams(
vocab_size, vocab_size, hparams)
p_hparams.input_modality["inputs"] = modalities.ImageModality(hparams)
p_hparams.target_modality = modalities.ClassLabelModality(
hparams, vocab_size)
with self.test_session() as session:
features = {
"inputs": tf.constant(x, dtype=tf.int32),
"targets": tf.constant(y, dtype=tf.int32),
}
model = resnet.Resnet(hparams, tf.estimator.ModeKeys.TRAIN,
p_hparams)
logits, _ = model(features)
session.run(tf.global_variables_initializer())
res = session.run(logits)
self.assertEqual(res.shape,
(batch_size, ) + output_size + (1, vocab_size))
def _test_resnet(self, img_size, output_size):
vocab_size = 1
batch_size = 1
x = np.random.random_integers(0,
high=255,
size=(batch_size, img_size, img_size, 3))
y = np.random.random_integers(1,
high=vocab_size,
size=(batch_size, 1, 1, 1))
#hparams = resnet_tiny_cpu()
#hparams = resnet_50()
hparams = resnet_32()
p_hparams = problem_hparams.test_problem_hparams(
vocab_size, vocab_size, hparams)
p_hparams.input_modality["inputs"] = modalities.ImageModality(hparams)
p_hparams.target_modality = modalities.ClassLabelModality(
hparams, vocab_size)
run_meta = tf.RunMetadata()
with self.test_session() as session:
features = {
"inputs": tf.constant(x, dtype=tf.int32),
"targets": tf.constant(y, dtype=tf.int32),
}
#model = resnet.Resnet(hparams, tf.estimator.ModeKeys.TRAIN, p_hparams)
model = shake_shake.ShakeShake(hparams,
tf.estimator.ModeKeys.TRAIN,
p_hparams)
logits, _ = model(features)
print(logits.get_shape())
#opts = tf.profiler.ProfileOptionBuilder.float_operation()
#flops = tf.profiler.profile(tf.get_default_graph(), run_meta=run_meta, options=opts)
#print(flops.total_float_ops)
session.run(tf.global_variables_initializer())
#res = session.run(logits)
tf.get_variable_scope().set_initializer(
optimize.get_variable_initializer(hparams))
loss = tf.losses.sparse_softmax_cross_entropy(labels=tf.constant(
0, dtype=tf.int32, shape=[1, 1, 1, 1, 1]),
logits=logits)
train_op = optimize.optimize(loss, 0.1, hparams)
session.run(loss)
opts = tf.profiler.ProfileOptionBuilder.float_operation()
flops = tf.profiler.profile(tf.get_default_graph(),
run_meta=run_meta,
options=opts)
print(flops.total_float_ops)
def _test_xception(self, img_size):
vocab_size = 9
batch_size = 3
x = np.random.randint(256, size=(batch_size, img_size, img_size, 3))
y = np.random.randint(1, high=vocab_size, size=(batch_size, 1, 1, 1))
hparams = xception.xception_tiny()
p_hparams = problem_hparams.test_problem_hparams(
vocab_size, vocab_size, hparams)
p_hparams.modality["inputs"] = modalities.ImageModality(hparams)
p_hparams.modality["targets"] = modalities.ClassLabelModality(
hparams, vocab_size)
with self.test_session() as session:
features = {
"inputs": tf.constant(x, dtype=tf.int32),
"targets": tf.constant(y, dtype=tf.int32),
}
model = xception.Xception(hparams, tf.estimator.ModeKeys.TRAIN,
p_hparams)
logits, _ = model(features)
session.run(tf.global_variables_initializer())
res = session.run(logits)
self.assertEqual(res.shape, (batch_size, 1, 1, 1, vocab_size))
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, ())