def call(self,
logits=None,
input_length=None,
labels=None,
label_length=None,
soft_labels=None,
**kwargs):
loss_standard = cross_entropy(
logits=logits,
input_length=input_length,
labels=labels,
label_length=label_length,
smoothing=self.smoothing)
loss_soft = cross_entropy(
logits=logits / self.T,
input_length=input_length,
labels=soft_labels,
label_length=label_length,
smoothing=self.smoothing)
# Since the magnitudes of the gradients produced by the soft targets
# scale as 1/T2 , it is important to multiply them by T2 when using
# both hard and soft targets
total_loss = self.alpha * tf.square(
self.T) * loss_soft + (1 - self.alpha) * loss_standard
return total_loss
def test_cross_entropy(self):
''' test cross entropy'''
with self.cached_session():
loss = loss_utils.cross_entropy(logits=tf.constant(self.logits),
input_length=None,
labels=tf.constant(self.labels),
label_length=None)
self.assertAllClose(loss.eval(), 0.0, rtol=1e-06, atol=1.5e-6)
loss = loss_utils.cross_entropy(
logits=tf.constant(self.seq_logits),
input_length=tf.constant(self.input_length),
labels=tf.constant(self.seq_labels),
label_length=tf.constant(self.label_length),
reduction=tf.losses.Reduction.NONE)
self.assertEqual(loss.eval().shape, (2, 3))
self.assertAllClose(loss.eval(),
np.zeros((2, 3), dtype=np.float32),
rtol=1e-06,
atol=1.5e-6)
loss = loss_utils.cross_entropy(
logits=tf.constant(self.seq_logits),
input_length=tf.constant(self.input_length),
labels=tf.constant(self.seq_labels),
label_length=tf.constant(self.label_length),
reduction=tf.losses.Reduction.SUM_BY_NONZERO_WEIGHTS)
self.assertEqual(loss.eval().shape, ())
self.assertAllClose(loss.eval(), 0.0, rtol=1e-06, atol=1.5e-6)
def test_focal_loss(self):
with self.cached_session():
logits = np.array([[22, 23, 24]], dtype=np.float32)
labels = np.array([2], dtype=np.int32)
ce_loss = loss_utils.cross_entropy(
logits=tf.constant(logits),
input_length=None,
labels=tf.constant(labels),
label_length=None)
fl_loss0 = loss_utils.focal_loss(
logits=tf.constant(logits),
labels=tf.constant(labels),
gamma = 0)
self.assertAllClose(fl_loss0.eval(), 0.407606, rtol=1e-06, atol=1e-6)
self.assertAllClose(fl_loss0.eval(), ce_loss.eval(), rtol=1e-07, atol=1e-7)
fl_loss2 = loss_utils.focal_loss(
logits=tf.constant(logits),
labels=tf.constant(labels),
gamma = 2)
fl_loss5 = loss_utils.focal_loss(
logits=tf.constant(logits),
labels=tf.constant(labels),
gamma = 5)
self.assertAllClose(fl_loss2.eval(), 0.045677, rtol=1e-06, atol=1e-6)
self.assertAllClose(fl_loss5.eval(), 0.001713, rtol=1e-06, atol=1e-6)
def call(self,
logits=None,
input_length=None,
labels=None,
label_length=None,
**kwargs):
loss = cross_entropy(logits=logits,
input_length=input_length,
labels=labels,
label_length=label_length,
smoothing=self.smoothing)
return loss
def call(self,
logits=None,
input_length=None,
labels=None,
label_length=None,
soft_labels=None):
del soft_labels
loss = cross_entropy(logits=logits,
input_length=input_length,
labels=labels,
label_length=label_length,
smoothing=self.smoothing)
return loss
