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)
raise ValueError('Empty loss config.')
def testReturnsCorrectAnchorWiseLoss(self):
prediction_tensor = tf.constant([[[-100, 100, -100],
[100, -100, -100],
[100, 0, -100],
[-100, -100, 100]],
[[-100, 0, 100],
[-100, 100, -100],
[100, 100, 100],
[0, 0, -1]]], tf.float32)
target_tensor = tf.constant([[[0, 1, 0],
[1, 0, 0],
[1, 0, 0],
[0, 0, 1]],
[[0, 0, 1],
[0, 1, 0],
[1, 1, 1],
[1, 0, 0]]], tf.float32)
weights = tf.constant([[1, 1, 1, 1],
[1, 1, 1, 0]], tf.float32)
alpha = tf.constant(.5, tf.float32)
loss_op = losses.BootstrappedSigmoidClassificationLoss(
alpha, bootstrap_type='hard')
loss = loss_op(prediction_tensor, target_tensor, weights=weights)
loss = tf.reduce_sum(loss, axis=2)
exp_loss = np.matrix([[0, 0, -math.log(.5), 0],
[-math.log(.5), 0, 0, 0]])
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, exp_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':
return losses.WeightedSigmoidClassificationLoss()
if loss_type == 'weighted_sigmoid_focal':
config = loss_config.weighted_sigmoid_focal
# alpha = None
# if config.HasField('alpha'):
# alpha = config.alpha
if config.alpha > 0:
alpha = config.alpha
else:
alpha = None
return losses.SigmoidFocalClassificationLoss(gamma=config.gamma,
alpha=alpha)
if loss_type == 'weighted_softmax_focal':
config = loss_config.weighted_softmax_focal
# alpha = None
# if config.HasField('alpha'):
# alpha = config.alpha
if config.alpha > 0:
alpha = config.alpha
else:
alpha = None
return losses.SoftmaxFocalClassificationLoss(gamma=config.gamma,
alpha=alpha)
if loss_type == 'weighted_softmax':
config = loss_config.weighted_softmax
return losses.WeightedSoftmaxClassificationLoss(
logit_scale=config.logit_scale)
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'))
raise ValueError('Empty loss config.')
def _build_classification_loss(loss_config):
"""Builds a classification loss based on the loss config.
Args:
loss_config: A yaml.ClassificationLoss object.
Returns:
Loss based on the config.
Raises:
ValueError: On invalid loss_config.
"""
if 'weighted_sigmoid' in loss_config:
return losses.WeightedSigmoidClassificationLoss()
if 'weighted_sigmoid_focal' in loss_config:
config = loss_config.weighted_sigmoid_focal
# alpha = None
# if config.HasField('alpha'):
# alpha = config.alpha
if config.alpha > 0:
alpha = config.alpha
else:
alpha = None
return losses.SigmoidFocalClassificationLoss(gamma=config.gamma,
alpha=alpha)
if 'weighted_softmax_focal' in loss_config:
config = loss_config.weighted_softmax_focal
# alpha = None
# if config.HasField('alpha'):
# alpha = config.alpha
if config.alpha > 0:
alpha = config.alpha
else:
alpha = None
return losses.SoftmaxFocalClassificationLoss(gamma=config.gamma,
alpha=alpha)
if 'weighted_softmax' in loss_config:
config = loss_config.weighted_softmax
return losses.WeightedSoftmaxClassificationLoss(
logit_scale=config.logit_scale)
if 'bootstrapped_sigmoid' in loss_config:
config = loss_config.bootstrapped_sigmoid
return losses.BootstrappedSigmoidClassificationLoss(
alpha=config.alpha,
bootstrap_type=('hard' if config.hard_bootstrap else 'soft'))
else:
raise ValueError('Empty loss config.')
def testReturnsCorrectLossSoftBootstrapping(self):
prediction_tensor = tf.constant(
[[[-100, 100, 0], [100, -100, -100], [100, -100, -100],
[-100, -100, 100]],
[[-100, -100, 100], [-100, 100, -100], [100, 100, 100],
[0, 0, -1]]], tf.float32)
target_tensor = tf.constant(
[[[0, 1, 0], [1, 0, 0], [1, 0, 0], [0, 0, 1]],
[[0, 0, 1], [0, 1, 0], [1, 1, 1], [1, 0, 0]]], tf.float32)
weights = tf.constant([[1, 1, 1, 1], [1, 1, 1, 0]], tf.float32)
alpha = tf.constant(.5, tf.float32)
loss_op = losses.BootstrappedSigmoidClassificationLoss(
alpha, bootstrap_type='soft')
loss = loss_op(prediction_tensor, target_tensor, weights=weights)
exp_loss = -math.log(.5)
with self.test_session() as sess:
loss_output = sess.run(loss)
self.assertAllClose(loss_output, exp_loss)
