def testInvalidLabel(self):
features = [
[1., 1., 1., 1.],
[1., 1., 1., 1.],
[1., 2., 3., 4.],
[1., 2., 3., 4.]]
labels = [4, 3, 0, -1]
if tf.test.is_built_with_cuda() and tf.test.is_gpu_available():
with self.test_session(use_gpu=True) as sess:
loss, backprop = (
gen_nn_ops._sparse_softmax_cross_entropy_with_logits(
features, labels))
tf_loss, tf_backprop = sess.run([loss, backprop])
self.assertAllClose(
[[np.nan] * 4,
[0.25, 0.25, 0.25, -0.75],
[-0.968, 0.087, 0.237, 0.6439],
[np.nan] * 4],
tf_backprop, rtol=1e-3, atol=1e-3)
self.assertAllClose(
[np.nan, 1.3862, 3.4420, np.nan], tf_loss, rtol=1e-3, atol=1e-3)
with self.test_session(use_gpu=False) as sess:
loss, backprop = (
gen_nn_ops._sparse_softmax_cross_entropy_with_logits(
features, labels))
with self.assertRaisesOpError("Received a label value of"):
sess.run([loss, backprop])
def testInvalidLabel(self):
features = [[1., 1., 1., 1.], [1., 1., 1., 1.], [1., 2., 3., 4.],
[1., 2., 3., 4.]]
labels = [4, 3, 0, -1]
if test.is_built_with_cuda() and test.is_gpu_available():
with self.test_session(use_gpu=True) as sess:
loss, backprop = (
gen_nn_ops._sparse_softmax_cross_entropy_with_logits(
features, labels))
tf_loss, tf_backprop = sess.run([loss, backprop])
self.assertAllClose(
[[np.nan] * 4, [0.25, 0.25, 0.25, -0.75],
[-0.968, 0.087, 0.237, 0.6439], [np.nan] * 4],
tf_backprop,
rtol=1e-3,
atol=1e-3)
self.assertAllClose([np.nan, 1.3862, 3.4420, np.nan],
tf_loss,
rtol=1e-3,
atol=1e-3)
with self.test_session(use_gpu=False) as sess:
loss, backprop = (
gen_nn_ops._sparse_softmax_cross_entropy_with_logits(
features, labels))
with self.assertRaisesOpError("Received a label value of"):
sess.run([loss, backprop])
def _testXent(self, np_features, np_labels):
np_loss, np_backprop = self._npXent(np_features, np_labels)
with self.test_session(use_gpu=True) as sess:
loss, backprop = gen_nn_ops._sparse_softmax_cross_entropy_with_logits(np_features, np_labels)
tf_loss, tf_backprop = sess.run([loss, backprop])
self.assertAllCloseAccordingToType(np_loss, tf_loss)
self.assertAllCloseAccordingToType(np_backprop, tf_backprop)
def _testXent(self, np_features, np_labels):
np_loss, np_backprop = self._npXent(np_features, np_labels)
with self.test_session(use_gpu=True) as sess:
loss, backprop = gen_nn_ops._sparse_softmax_cross_entropy_with_logits(
np_features, np_labels)
tf_loss, tf_backprop = sess.run([loss, backprop])
self.assertAllCloseAccordingToType(np_loss, tf_loss)
self.assertAllCloseAccordingToType(np_backprop, tf_backprop)
def testSingleClass(self):
for label_dtype in np.int32, np.int64:
with self.test_session(use_gpu=True) as sess:
loss, backprop = gen_nn_ops._sparse_softmax_cross_entropy_with_logits(
np.array([[1.], [-1.], [0.]]).astype(np.float32),
np.array([0, 0, 0]).astype(label_dtype))
tf_loss, tf_backprop = sess.run([loss, backprop])
self.assertAllClose([0.0, 0.0, 0.0], tf_loss)
self.assertAllClose([[0.0], [0.0], [0.0]], tf_backprop)
def testSingleClass(self):
for label_dtype in np.int32, np.int64:
with self.test_session(use_gpu=True) as sess:
loss, backprop = gen_nn_ops._sparse_softmax_cross_entropy_with_logits(
np.array([[1.], [-1.], [0.]]).astype(np.float32),
np.array([0, 0, 0]).astype(label_dtype))
tf_loss, tf_backprop = sess.run([loss, backprop])
self.assertAllClose([0.0, 0.0, 0.0], tf_loss)
self.assertAllClose([[0.0], [0.0], [0.0]], tf_backprop)
def testInvalidLabel(self):
features = [[1., 1., 1., 1.], [1., 1., 1., 1.], [1., 2., 3., 4.],
[1., 2., 3., 4.]]
labels = [4, 3, 0, -1]
with self.test_session(use_gpu=True) as sess:
loss, backprop = gen_nn_ops._sparse_softmax_cross_entropy_with_logits(
features, labels)
tf_loss, tf_backprop = sess.run([loss, backprop])
self.assertAllClose([[np.nan] * 4, [0.25, 0.25, 0.25, -0.75],
[-0.968, 0.087, 0.237, 0.6439], [np.nan] * 4],
tf_backprop,
rtol=1e-3,
atol=1e-3)
self.assertAllClose([np.nan, 1.3862, 3.4420, np.nan],
tf_loss,
rtol=1e-3,
atol=1e-3)
def sparse_softmax_cross_entropy_with_logits(logits, labels, name=None):
"""Computes sparse softmax cross entropy between `logits` and `labels`.
Measures the probability error in discrete classification tasks in which the
classes are mutually exclusive (each entry is in exactly one class). For
example, each CIFAR-10 image is labeled with one and only one label: an image
can be a dog or a truck, but not both.
**NOTE:** For this operation, the probability of a given label is considered
exclusive. That is, soft classes are not allowed, and the `labels` vector
must provide a single specific index for the true class for each row of
`logits` (each minibatch entry). For soft softmax classification with
a probability distribution for each entry, see
`softmax_cross_entropy_with_logits`.
**WARNING:** This op expects unscaled logits, since it performs a softmax
on `logits` internally for efficiency. Do not call this op with the
output of `softmax`, as it will produce incorrect results.
`logits` must have the shape `[batch_size, num_classes]`
and dtype `float32` or `float64`.
`labels` must have the shape `[batch_size]` and dtype `int32` or `int64`.
Args:
logits: Unscaled log probabilities.
labels: Each entry `labels[i]` must be an index in `[0, num_classes)`. Other
values will result in a loss of 0, but incorrect gradient computations.
name: A name for the operation (optional).
Returns:
A 1-D `Tensor` of length `batch_size` of the same type as `logits` with the
softmax cross entropy loss.
"""
# TODO(pcmurray) Raise an error when the label is not an index in
# [0, num_classes). Note: This could break users who call this with bad
# labels, but disregard the bad results.
# The second output tensor contains the gradients. We use it in
# _CrossEntropyGrad() in nn_grad but not here.
cost, unused_backprop = gen_nn_ops._sparse_softmax_cross_entropy_with_logits(
logits, labels, name=name)
return cost
def sparse_softmax_cross_entropy_with_logits(logits, labels, name=None):
"""Computes sparse softmax cross entropy between `logits` and `labels`.
Measures the probability error in discrete classification tasks in which the
classes are mutually exclusive (each entry is in exactly one class). For
example, each CIFAR-10 image is labeled with one and only one label: an image
can be a dog or a truck, but not both.
**NOTE:** For this operation, the probability of a given label is considered
exclusive. That is, soft classes are not allowed, and the `labels` vector
must provide a single specific index for the true class for each row of
`logits` (each minibatch entry). For soft softmax classification with
a probability distribution for each entry, see
`softmax_cross_entropy_with_logits`.
**WARNING:** This op expects unscaled logits, since it performs a softmax
on `logits` internally for efficiency. Do not call this op with the
output of `softmax`, as it will produce incorrect results.
`logits` must have the shape `[batch_size, num_classes]`
and dtype `float32` or `float64`.
`labels` must have the shape `[batch_size]` and dtype `int32` or `int64`.
Args:
logits: Unscaled log probabilities.
labels: Each entry `labels[i]` must be an index in `[0, num_classes)`. Other
values will result in a loss of 0, but incorrect gradient computations.
name: A name for the operation (optional).
Returns:
A 1-D `Tensor` of length `batch_size` of the same type as `logits` with the
softmax cross entropy loss.
"""
# TODO(pcmurray) Raise an error when the label is not an index in
# [0, num_classes). Note: This could break users who call this with bad
# labels, but disregard the bad results.
# The second output tensor contains the gradients. We use it in
# _CrossEntropyGrad() in nn_grad but not here.
cost, unused_backprop = gen_nn_ops._sparse_softmax_cross_entropy_with_logits(
logits, labels, name=name)
return cost
def _testInvalidLabel(self, use_gpu):
features = [
[1., 1., 1., 1.],
[1., 1., 1., 1.],
[1., 2., 3., 4.],
[1., 2., 3., 4.]]
labels = [4, 3, 0, -1]
with self.test_session(use_gpu=use_gpu) as sess:
loss, backprop = gen_nn_ops._sparse_softmax_cross_entropy_with_logits(
features, labels)
tf_loss, tf_backprop = sess.run([loss, backprop])
self.assertAllClose(
[[np.nan] * 4,
[0.25, 0.25, 0.25, -0.75],
[-0.968, 0.087, 0.237, 0.6439],
[np.nan] * 4],
tf_backprop, rtol=1e-3, atol=1e-3)
self.assertAllClose(
[np.nan, 1.3862, 3.4420, np.nan], tf_loss, rtol=1e-3, atol=1e-3)
