def testComputeMovingVars(self):
height, width = 3, 3
with self.test_session() as sess:
image_shape = (10, height, width, 3)
image_values = np.random.rand(*image_shape)
expected_mean = np.mean(image_values, axis=(0, 1, 2))
expected_var = np.var(image_values, axis=(0, 1, 2))
images = tf.constant(image_values,
shape=image_shape,
dtype=tf.float32)
output = ops.batch_norm(images, decay=0.1)
update_ops = tf.get_collection(ops.UPDATE_OPS_COLLECTION)
with tf.control_dependencies(update_ops):
output = tf.identity(output)
# Initialize all variables
sess.run(tf.global_variables_initializer())
moving_mean = variables.get_variables('BatchNorm/moving_mean')[0]
moving_variance = variables.get_variables(
'BatchNorm/moving_variance')[0]
mean, variance = sess.run([moving_mean, moving_variance])
# After initialization moving_mean == 0 and moving_variance == 1.
self.assertAllClose(mean, [0] * 3)
self.assertAllClose(variance, [1] * 3)
for _ in range(10):
sess.run([output])
mean = moving_mean.eval()
variance = moving_variance.eval()
# After 10 updates with decay 0.1 moving_mean == expected_mean and
# moving_variance == expected_var.
self.assertAllClose(mean, expected_mean)
self.assertAllClose(variance, expected_var)
def testNonReuseVars(self):
height, width = 3, 3
inputs = tf.random_uniform((5, height * width * 3), seed=1)
with self.test_session():
ops.fc(inputs, 32)
self.assertEquals(len(variables.get_variables('FC')), 2)
ops.fc(inputs, 32)
self.assertEquals(len(variables.get_variables('FC')), 4)
def testNonReuseVars(self):
height, width = 3, 3
with self.test_session():
images = tf.random_uniform((5, height, width, 3), seed=1)
ops.conv2d(images, 32, [3, 3])
self.assertEquals(len(variables.get_variables()), 2)
ops.conv2d(images, 32, [3, 3])
self.assertEquals(len(variables.get_variables()), 4)
def testReuseVars(self):
height, width = 3, 3
inputs = tf.random_uniform((5, height * width * 3), seed=1)
with self.test_session():
ops.fc(inputs, 32, scope='fc1')
self.assertEquals(len(variables.get_variables('fc1')), 2)
ops.fc(inputs, 32, scope='fc1', reuse=True)
self.assertEquals(len(variables.get_variables('fc1')), 2)
def testGetVariablesSuffix(self):
with self.test_session():
with tf.variable_scope('A'):
a = variables.variable('a', [5])
with tf.variable_scope('A'):
b = variables.variable('b', [5])
self.assertEquals([a], variables.get_variables(suffix='a'))
self.assertEquals([b], variables.get_variables(suffix='b'))
def testCreateConvCreatesWeightsAndBiasesVars(self):
height, width = 3, 3
images = tf.random_uniform((5, height, width, 3), seed=1)
with self.test_session():
self.assertFalse(variables.get_variables('conv1/weights'))
self.assertFalse(variables.get_variables('conv1/biases'))
ops.conv2d(images, 32, [3, 3], scope='conv1')
self.assertTrue(variables.get_variables('conv1/weights'))
self.assertTrue(variables.get_variables('conv1/biases'))
def testReuseFCWithBatchNorm(self):
height, width = 3, 3
with self.test_session():
images = tf.random_uniform((5, height * width * 3), seed=1)
with scopes.arg_scope([ops.fc], batch_norm_params={'decay': 0.9}):
net = ops.fc(images, 27, scope='fc1')
net = ops.fc(net, 27, scope='fc1', reuse=True)
self.assertEquals(len(variables.get_variables()), 4)
self.assertEquals(len(variables.get_variables('fc1/BatchNorm')), 3)
def testCreateFcCreatesWeightsAndBiasesVars(self):
height, width = 3, 3
inputs = tf.random_uniform((5, height * width * 3), seed=1)
with self.test_session():
self.assertFalse(variables.get_variables('fc1/weights'))
self.assertFalse(variables.get_variables('fc1/biases'))
ops.fc(inputs, 32, scope='fc1')
self.assertTrue(variables.get_variables('fc1/weights'))
self.assertTrue(variables.get_variables('fc1/biases'))
def testFCWithBatchNorm(self):
height, width = 3, 3
with self.test_session():
images = tf.random_uniform((5, height * width * 3), seed=1)
with scopes.arg_scope([ops.fc], batch_norm_params={}):
net = ops.fc(images, 27)
net = ops.fc(net, 27)
self.assertEquals(len(variables.get_variables()), 8)
self.assertEquals(len(variables.get_variables('FC/BatchNorm')), 3)
self.assertEquals(len(variables.get_variables('FC_1/BatchNorm')),
3)
def testReuseFCWithWD(self):
height, width = 3, 3
with self.test_session():
inputs = tf.random_uniform((5, height * width * 3), seed=1)
ops.fc(inputs, 32, weight_decay=0.01, scope='fc')
self.assertEquals(len(variables.get_variables()), 2)
self.assertEquals(
len(tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)), 1)
ops.fc(inputs, 32, weight_decay=0.01, scope='fc', reuse=True)
self.assertEquals(len(variables.get_variables()), 2)
self.assertEquals(
len(tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)), 1)
def testReuseConvWithBatchNorm(self):
height, width = 3, 3
with self.test_session():
images = tf.random_uniform((5, height, width, 32), seed=1)
with scopes.arg_scope([ops.conv2d],
batch_norm_params={'decay': 0.9}):
net = ops.conv2d(images, 32, [3, 3], scope='Conv')
net = ops.conv2d(net, 32, [3, 3], scope='Conv', reuse=True)
self.assertEquals(len(variables.get_variables()), 4)
self.assertEquals(len(variables.get_variables('Conv/BatchNorm')),
3)
self.assertEquals(len(variables.get_variables('Conv_1/BatchNorm')),
0)
def testReuseConvWithWD(self):
height, width = 3, 3
with self.test_session():
images = tf.random_uniform((5, height, width, 3), seed=1)
ops.conv2d(images, 32, [3, 3], weight_decay=0.01, scope='conv1')
self.assertEquals(len(variables.get_variables()), 2)
self.assertEquals(
len(tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)), 1)
ops.conv2d(images,
32, [3, 3],
weight_decay=0.01,
scope='conv1',
reuse=True)
self.assertEquals(len(variables.get_variables()), 2)
self.assertEquals(
len(tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)), 1)
def testNoneGetVariablesToRestore(self):
with self.test_session():
with tf.variable_scope('A'):
a = variables.variable('a', [5], restore=False)
with tf.variable_scope('B'):
b = variables.variable('a', [5], restore=False)
self.assertEquals([], variables.get_variables_to_restore())
self.assertEquals([a, b], variables.get_variables())
def testReuseVariable(self):
with self.test_session():
with tf.variable_scope('A'):
a = variables.variable('a', [])
with tf.variable_scope('A', reuse=True):
b = variables.variable('a', [])
self.assertEquals(a, b)
self.assertListEqual([a], variables.get_variables())
def testGetMixedVariablesToRestore(self):
with self.test_session():
with tf.variable_scope('A'):
a = variables.variable('a', [5])
b = variables.variable('b', [5], restore=False)
with tf.variable_scope('B'):
c = variables.variable('c', [5])
d = variables.variable('d', [5], restore=False)
self.assertEquals([a, b, c, d], variables.get_variables())
self.assertEquals([a, c], variables.get_variables_to_restore())
def testReuseVars(self):
height, width = 3, 3
with self.test_session() as sess:
image_shape = (10, height, width, 3)
image_values = np.random.rand(*image_shape)
expected_mean = np.mean(image_values, axis=(0, 1, 2))
expected_var = np.var(image_values, axis=(0, 1, 2))
images = tf.constant(image_values,
shape=image_shape,
dtype=tf.float32)
output = ops.batch_norm(images, decay=0.1, is_training=False)
update_ops = tf.get_collection(ops.UPDATE_OPS_COLLECTION)
with tf.control_dependencies(update_ops):
output = tf.identity(output)
# Initialize all variables
sess.run(tf.global_variables_initializer())
moving_mean = variables.get_variables('BatchNorm/moving_mean')[0]
moving_variance = variables.get_variables(
'BatchNorm/moving_variance')[0]
mean, variance = sess.run([moving_mean, moving_variance])
# After initialization moving_mean == 0 and moving_variance == 1.
self.assertAllClose(mean, [0] * 3)
self.assertAllClose(variance, [1] * 3)
# Simulate assigment from saver restore.
init_assigns = [
tf.assign(moving_mean, expected_mean),
tf.assign(moving_variance, expected_var)
]
sess.run(init_assigns)
for _ in range(10):
sess.run([output], {images: np.random.rand(*image_shape)})
mean = moving_mean.eval()
variance = moving_variance.eval()
# Although we feed different images, the moving_mean and moving_variance
# shouldn't change.
self.assertAllClose(mean, expected_mean)
self.assertAllClose(variance, expected_var)