def test_return_non_default_batch_norm_params_keras_override(self):
conv_hyperparams_text_proto = """
regularizer {
l2_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
batch_norm {
decay: 0.7
center: false
scale: true
epsilon: 0.03
}
"""
conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
keras_config = hyperparams_builder.KerasLayerHyperparams(
conv_hyperparams_proto)
self.assertTrue(keras_config.use_batch_norm())
batch_norm_params = keras_config.batch_norm_params(momentum=0.4)
self.assertAlmostEqual(batch_norm_params['momentum'], 0.4)
self.assertAlmostEqual(batch_norm_params['epsilon'], 0.03)
self.assertFalse(batch_norm_params['center'])
self.assertTrue(batch_norm_params['scale'])
def test_return_batch_norm_params_with_notrain_when_train_is_false(self):
conv_hyperparams_text_proto = """
regularizer {
l2_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
batch_norm {
decay: 0.7
center: false
scale: true
epsilon: 0.03
train: false
}
"""
conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
scope_fn = hyperparams_builder.build(conv_hyperparams_proto,
is_training=True)
scope = scope_fn()
conv_scope_arguments = scope[_get_scope_key(slim.conv2d)]
self.assertEqual(conv_scope_arguments['normalizer_fn'],
slim.batch_norm)
batch_norm_params = scope[_get_scope_key(slim.batch_norm)]
self.assertAlmostEqual(batch_norm_params['decay'], 0.7)
self.assertAlmostEqual(batch_norm_params['epsilon'], 0.03)
self.assertFalse(batch_norm_params['center'])
self.assertTrue(batch_norm_params['scale'])
self.assertFalse(batch_norm_params['is_training'])
def _build_arg_scope_with_conv_hyperparams(self):
conv_hyperparams = hyperparams_pb2.Hyperparams()
conv_hyperparams_text_proto = """
regularizer {
l2_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
"""
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams)
return hyperparams_builder.build(conv_hyperparams, is_training=True)
def _build_conv_hyperparams(self):
conv_hyperparams = hyperparams_pb2.Hyperparams()
conv_hyperparams_text_proto = """
regularizer {
l2_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
"""
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams)
return hyperparams_builder.KerasLayerHyperparams(conv_hyperparams)
def _build_fc_hyperparams(self, op_type=hyperparams_pb2.Hyperparams.FC):
hyperparams = hyperparams_pb2.Hyperparams()
hyperparams_text_proto = """
activation: NONE
regularizer {
l2_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
"""
text_format.Merge(hyperparams_text_proto, hyperparams)
hyperparams.op = op_type
return hyperparams_builder.KerasLayerHyperparams(hyperparams)
def test_default_arg_scope_has_conv2d_transpose_op(self):
conv_hyperparams_text_proto = """
regularizer {
l1_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
"""
conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
scope_fn = hyperparams_builder.build(conv_hyperparams_proto,
is_training=True)
scope = scope_fn()
self.assertTrue(_get_scope_key(slim.conv2d_transpose) in scope)
def _build_conv_arg_scope_no_batch_norm(self):
conv_hyperparams = hyperparams_pb2.Hyperparams()
conv_hyperparams_text_proto = """
activation: RELU_6
regularizer {
l2_regularizer {
}
}
initializer {
random_normal_initializer {
stddev: 0.01
mean: 0.0
}
}
"""
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams)
return hyperparams_builder.build(conv_hyperparams, is_training=True)
def _build_arg_scope_with_hyperparams(
self, op_type=hyperparams_pb2.Hyperparams.FC):
hyperparams = hyperparams_pb2.Hyperparams()
hyperparams_text_proto = """
activation: NONE
regularizer {
l2_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
"""
text_format.Merge(hyperparams_text_proto, hyperparams)
hyperparams.op = op_type
return hyperparams_builder.build(hyperparams, is_training=True)
def test_do_not_use_batch_norm_if_default(self):
conv_hyperparams_text_proto = """
regularizer {
l2_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
"""
conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
scope_fn = hyperparams_builder.build(conv_hyperparams_proto,
is_training=True)
scope = scope_fn()
conv_scope_arguments = scope[_get_scope_key(slim.conv2d)]
self.assertEqual(conv_scope_arguments['normalizer_fn'], None)
def test_explicit_fc_op_arg_scope_has_fully_connected_op(self):
conv_hyperparams_text_proto = """
op: FC
regularizer {
l1_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
"""
conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
scope_fn = hyperparams_builder.build(conv_hyperparams_proto,
is_training=True)
scope = scope_fn()
self.assertTrue(_get_scope_key(slim.fully_connected) in scope)
def test_override_activation_keras(self):
conv_hyperparams_text_proto = """
regularizer {
l2_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
activation: RELU_6
"""
conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
keras_config = hyperparams_builder.KerasLayerHyperparams(
conv_hyperparams_proto)
new_params = keras_config.params(activation=tf.nn.relu)
self.assertEqual(new_params['activation'], tf.nn.relu)
def test_use_relu_6_activation(self):
conv_hyperparams_text_proto = """
regularizer {
l2_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
activation: RELU_6
"""
conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
scope_fn = hyperparams_builder.build(conv_hyperparams_proto,
is_training=True)
scope = scope_fn()
conv_scope_arguments = scope[_get_scope_key(slim.conv2d)]
self.assertEqual(conv_scope_arguments['activation_fn'], tf.nn.relu6)
def test_separable_conv2d_and_conv2d_and_transpose_have_same_parameters(
self):
conv_hyperparams_text_proto = """
regularizer {
l1_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
"""
conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
scope_fn = hyperparams_builder.build(conv_hyperparams_proto,
is_training=True)
scope = scope_fn()
kwargs_1, kwargs_2, kwargs_3 = scope.values()
self.assertDictEqual(kwargs_1, kwargs_2)
self.assertDictEqual(kwargs_1, kwargs_3)
def test_do_not_use_batch_norm_if_default_keras(self):
conv_hyperparams_text_proto = """
regularizer {
l2_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
"""
conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
keras_config = hyperparams_builder.KerasLayerHyperparams(
conv_hyperparams_proto)
self.assertFalse(keras_config.use_batch_norm())
self.assertEqual(keras_config.batch_norm_params(), {})
# The batch norm builder should build an identity Lambda layer
identity_layer = keras_config.build_batch_norm()
self.assertTrue(isinstance(identity_layer, tf.keras.layers.Lambda))
def _build_conv_hyperparams(self):
conv_hyperparams = hyperparams_pb2.Hyperparams()
conv_hyperparams_text_proto = """
activation: RELU_6
regularizer {
l2_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
batch_norm {
train: true,
scale: false,
center: true,
decay: 0.2,
epsilon: 0.1,
}
"""
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams)
return hyperparams_builder.KerasLayerHyperparams(conv_hyperparams)
def test_return_l2_regularizer_weights_keras(self):
conv_hyperparams_text_proto = """
regularizer {
l2_regularizer {
weight: 0.42
}
}
initializer {
truncated_normal_initializer {
}
}
"""
conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
keras_config = hyperparams_builder.KerasLayerHyperparams(
conv_hyperparams_proto)
regularizer = keras_config.params()['kernel_regularizer']
weights = np.array([1., -1, 4., 2.])
with self.test_session() as sess:
result = sess.run(regularizer(tf.constant(weights)))
self.assertAllClose(np.power(weights, 2).sum() / 2.0 * 0.42, result)
def test_variance_in_range_with_random_normal_initializer_keras(self):
conv_hyperparams_text_proto = """
regularizer {
l2_regularizer {
}
}
initializer {
random_normal_initializer {
mean: 0.0
stddev: 0.8
}
}
"""
conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
keras_config = hyperparams_builder.KerasLayerHyperparams(
conv_hyperparams_proto)
initializer = keras_config.params()['kernel_initializer']
self._assert_variance_in_range(initializer,
shape=[100, 40],
variance=0.64,
tol=1e-1)
def test_use_none_activation_keras(self):
conv_hyperparams_text_proto = """
regularizer {
l2_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
activation: NONE
"""
conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
keras_config = hyperparams_builder.KerasLayerHyperparams(
conv_hyperparams_proto)
self.assertEqual(keras_config.params()['activation'], None)
self.assertEqual(
keras_config.params(include_activation=True)['activation'], None)
activation_layer = keras_config.build_activation_layer()
self.assertTrue(isinstance(activation_layer, tf.keras.layers.Lambda))
self.assertEqual(activation_layer.function, tf.identity)
def _build_conv_hyperparams(self, add_batch_norm=True):
conv_hyperparams = hyperparams_pb2.Hyperparams()
conv_hyperparams_text_proto = """
activation: RELU_6
regularizer {
l2_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
"""
if add_batch_norm:
batch_norm_proto = """
batch_norm {
scale: false
}
"""
conv_hyperparams_text_proto += batch_norm_proto
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams)
return hyperparams_builder.KerasLayerHyperparams(conv_hyperparams)
def _build_conv_hyperparams(self):
conv_hyperparams = hyperparams_pb2.Hyperparams()
conv_hyperparams_text_proto = """
activation: RELU_6,
regularizer {
l2_regularizer {
weight: 0.0004
}
}
initializer {
truncated_normal_initializer {
stddev: 0.03
mean: 0.0
}
}
batch_norm {
scale: true,
decay: 0.997,
epsilon: 0.001,
}
"""
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams)
return hyperparams_builder.KerasLayerHyperparams(conv_hyperparams)
def test_return_l1_regularized_weights(self):
conv_hyperparams_text_proto = """
regularizer {
l1_regularizer {
weight: 0.5
}
}
initializer {
truncated_normal_initializer {
}
}
"""
conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
scope_fn = hyperparams_builder.build(conv_hyperparams_proto,
is_training=True)
scope = scope_fn()
conv_scope_arguments = scope.values()[0]
regularizer = conv_scope_arguments['weights_regularizer']
weights = np.array([1., -1, 4., 2.])
with self.test_session() as sess:
result = sess.run(regularizer(tf.constant(weights)))
self.assertAllClose(np.abs(weights).sum() * 0.5, result)
def test_variance_in_range_with_variance_scaling_initializer_uniform_keras(
self):
conv_hyperparams_text_proto = """
regularizer {
l2_regularizer {
}
}
initializer {
variance_scaling_initializer {
factor: 2.0
mode: FAN_IN
uniform: true
}
}
"""
conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
keras_config = hyperparams_builder.KerasLayerHyperparams(
conv_hyperparams_proto)
initializer = keras_config.params()['kernel_initializer']
self._assert_variance_in_range(initializer,
shape=[100, 40],
variance=2. / 100.)
def test_return_l2_regularizer_weights(self):
conv_hyperparams_text_proto = """
regularizer {
l2_regularizer {
weight: 0.42
}
}
initializer {
truncated_normal_initializer {
}
}
"""
conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
scope_fn = hyperparams_builder.build(conv_hyperparams_proto,
is_training=True)
scope = scope_fn()
conv_scope_arguments = scope[_get_scope_key(slim.conv2d)]
regularizer = conv_scope_arguments['weights_regularizer']
weights = np.array([1., -1, 4., 2.])
with self.test_session() as sess:
result = sess.run(regularizer(tf.constant(weights)))
self.assertAllClose(np.power(weights, 2).sum() / 2.0 * 0.42, result)
def test_variance_in_range_with_random_normal_initializer(self):
conv_hyperparams_text_proto = """
regularizer {
l2_regularizer {
}
}
initializer {
random_normal_initializer {
mean: 0.0
stddev: 0.8
}
}
"""
conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
scope_fn = hyperparams_builder.build(conv_hyperparams_proto,
is_training=True)
scope = scope_fn()
conv_scope_arguments = scope[_get_scope_key(slim.conv2d)]
initializer = conv_scope_arguments['weights_initializer']
self._assert_variance_in_range(initializer,
shape=[100, 40],
variance=0.64,
tol=1e-1)
def test_variance_in_range_with_variance_scaling_initializer_uniform(self):
conv_hyperparams_text_proto = """
regularizer {
l2_regularizer {
}
}
initializer {
variance_scaling_initializer {
factor: 2.0
mode: FAN_IN
uniform: true
}
}
"""
conv_hyperparams_proto = hyperparams_pb2.Hyperparams()
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams_proto)
scope_fn = hyperparams_builder.build(conv_hyperparams_proto,
is_training=True)
scope = scope_fn()
conv_scope_arguments = scope[_get_scope_key(slim.conv2d)]
initializer = conv_scope_arguments['weights_initializer']
self._assert_variance_in_range(initializer,
shape=[100, 40],
variance=2. / 100.)
