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 _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_conv_hyperparams(self):
conv_hyperparams = hyperparams_pb2.Hyperparams()
conv_hyperparams_text_proto = """
activation: RELU_6
regularizer {
l2_regularizer {
}
}
initializer {
truncated_normal_initializer {
}
}
batch_norm {
scale: false
}
"""
text_format.Merge(conv_hyperparams_text_proto, conv_hyperparams)
return hyperparams_builder.KerasLayerHyperparams(conv_hyperparams)
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_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 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 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_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 _build_ssd_feature_extractor(feature_extractor_config,
is_training,
freeze_batchnorm,
reuse_weights=None):
"""Builds a ssd_meta_arch.SSDFeatureExtractor based on config.
Args:
feature_extractor_config: A SSDFeatureExtractor proto config from ssd.proto.
is_training: True if this feature extractor is being built for training.
freeze_batchnorm: Whether to freeze batch norm parameters during
training or not. When training with a small batch size (e.g. 1), it is
desirable to freeze batch norm update and use pretrained batch norm
params.
reuse_weights: if the feature extractor should reuse weights.
Returns:
ssd_meta_arch.SSDFeatureExtractor based on config.
Raises:
ValueError: On invalid feature extractor type.
"""
feature_type = feature_extractor_config.type
is_keras_extractor = feature_type in SSD_KERAS_FEATURE_EXTRACTOR_CLASS_MAP
depth_multiplier = feature_extractor_config.depth_multiplier
min_depth = feature_extractor_config.min_depth
pad_to_multiple = feature_extractor_config.pad_to_multiple
use_explicit_padding = feature_extractor_config.use_explicit_padding
use_depthwise = feature_extractor_config.use_depthwise
if is_keras_extractor:
conv_hyperparams = hyperparams_builder.KerasLayerHyperparams(
feature_extractor_config.conv_hyperparams)
else:
conv_hyperparams = hyperparams_builder.build(
feature_extractor_config.conv_hyperparams, is_training)
override_base_feature_extractor_hyperparams = (
feature_extractor_config.override_base_feature_extractor_hyperparams)
if (feature_type not in SSD_FEATURE_EXTRACTOR_CLASS_MAP) and (
not is_keras_extractor):
raise ValueError(
'Unknown ssd feature_extractor: {}'.format(feature_type))
if is_keras_extractor:
feature_extractor_class = SSD_KERAS_FEATURE_EXTRACTOR_CLASS_MAP[
feature_type]
else:
feature_extractor_class = SSD_FEATURE_EXTRACTOR_CLASS_MAP[feature_type]
kwargs = {
'is_training':
is_training,
'depth_multiplier':
depth_multiplier,
'min_depth':
min_depth,
'pad_to_multiple':
pad_to_multiple,
'use_explicit_padding':
use_explicit_padding,
'use_depthwise':
use_depthwise,
'override_base_feature_extractor_hyperparams':
override_base_feature_extractor_hyperparams
}
if is_keras_extractor:
kwargs.update({
'conv_hyperparams': conv_hyperparams,
'inplace_batchnorm_update': False,
'freeze_batchnorm': freeze_batchnorm
})
else:
kwargs.update({
'conv_hyperparams_fn': conv_hyperparams,
'reuse_weights': reuse_weights,
})
if feature_extractor_config.HasField('fpn'):
kwargs.update({
'fpn_min_level':
feature_extractor_config.fpn.min_level,
'fpn_max_level':
feature_extractor_config.fpn.max_level,
'additional_layer_depth':
feature_extractor_config.fpn.additional_layer_depth,
})
return feature_extractor_class(**kwargs)