def _build_localization_loss(loss_config):
"""Builds a localization loss based on the loss config.
Args:
loss_config: A losses_pb2.LocalizationLoss object.
Returns:
Loss based on the config.
Raises:
ValueError: On invalid loss_config.
"""
if not isinstance(loss_config, losses_pb2.LocalizationLoss):
raise ValueError('loss_config not of type losses_pb2.LocalizationLoss.')
loss_type = loss_config.WhichOneof('localization_loss')
if loss_type == 'weighted_l2':
return losses.WeightedL2LocalizationLoss()
if loss_type == 'weighted_smooth_l1':
return losses.WeightedSmoothL1LocalizationLoss(
loss_config.weighted_smooth_l1.delta)
if loss_type == 'weighted_iou':
return losses.WeightedIOULocalizationLoss()
raise ValueError('Empty loss config.')
def testReturnsCorrectAnchorwiseLoss(self):
batch_size = 3
num_anchors = 16
code_size = 4
prediction_tensor = tf.ones([batch_size, num_anchors, code_size])
target_tensor = tf.zeros([batch_size, num_anchors, code_size])
weights = tf.ones([batch_size, num_anchors])
loss_op = losses.WeightedL2LocalizationLoss(anchorwise_output=True)
loss = loss_op(prediction_tensor, target_tensor, weights=weights)
expected_loss = np.ones((batch_size, num_anchors)) * 2
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, expected_loss)
def testReturnsCorrectLoss(self):
batch_size = 3
num_anchors = 10
code_size = 4
prediction_tensor = tf.ones([batch_size, num_anchors, code_size])
target_tensor = tf.zeros([batch_size, num_anchors, code_size])
weights = tf.constant(
[[1, 1, 1, 1, 1, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 1, 0, 0, 0, 0, 0]], tf.float32)
loss_op = losses.WeightedL2LocalizationLoss()
loss = loss_op(prediction_tensor, target_tensor, weights=weights)
expected_loss = (3 * 5 * 4) / 2.0
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, expected_loss)
def _build_classification_loss(loss_config):
"""Builds a classification loss based on the loss config.
Args:
loss_config: A losses_pb2.ClassificationLoss object.
Returns:
Loss based on the config.
Raises:
ValueError: On invalid loss_config.
"""
if not isinstance(loss_config, losses_pb2.ClassificationLoss):
raise ValueError(
'loss_config not of type losses_pb2.ClassificationLoss.')
loss_type = loss_config.WhichOneof('classification_loss')
if loss_type == 'weighted_sigmoid':
config = loss_config.weighted_sigmoid
return losses.WeightedSigmoidClassificationLoss(
anchorwise_output=config.anchorwise_output)
if loss_type == 'weighted_softmax':
config = loss_config.weighted_softmax
return losses.WeightedSoftmaxClassificationLoss(
anchorwise_output=config.anchorwise_output)
if loss_type == 'bootstrapped_sigmoid':
config = loss_config.bootstrapped_sigmoid
return losses.BootstrappedSigmoidClassificationLoss(
alpha=config.alpha,
bootstrap_type=('hard' if config.hard_bootstrap else 'soft'),
anchorwise_output=config.anchorwise_output)
if loss_type == 'weighted_l2':
config = loss_config.weighted_l2
return losses.WeightedL2LocalizationLoss(
anchorwise_output=config.anchorwise_output)
if loss_type == 'weighted_smooth_l1':
config = loss_config.weighted_smooth_l1
return losses.WeightedSmoothL1LocalizationLoss(
anchorwise_output=config.anchorwise_output)
raise ValueError('Empty loss config.')
def testReturnsCorrectNanLoss(self):
batch_size = 3
num_anchors = 10
code_size = 4
prediction_tensor = tf.ones([batch_size, num_anchors, code_size])
target_tensor = tf.concat([
tf.zeros([batch_size, num_anchors, code_size / 2]),
tf.ones([batch_size, num_anchors, code_size / 2]) * np.nan
], axis=2)
weights = tf.ones([batch_size, num_anchors])
loss_op = losses.WeightedL2LocalizationLoss()
loss = loss_op(prediction_tensor, target_tensor, weights=weights,
ignore_nan_targets=True)
expected_loss = (3 * 5 * 4) / 2.0
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, expected_loss)
