Python tensorflow.python.ops.nn.sparse_softmax_cross_entropy_with_logits() Examples

def _softmax_cross_entropy_loss(labels, logits, weights=None):
  with ops.name_scope(
      None, "softmax_cross_entropy_loss", (logits, labels,)) as name:
    labels = ops.convert_to_tensor(labels)
    # Check that we got integer for classification.
    if not labels.dtype.is_integer:
      raise ValueError("Labels dtype should be integer "
                       "Instead got %s." % labels.dtype)

    # sparse_softmax_cross_entropy_with_logits requires [batch_size] labels.
    is_squeezed_labels = False
    # TODO(ptucker): This will break for dynamic shapes.
    if len(labels.get_shape()) == 2:
      labels = array_ops.squeeze(labels, squeeze_dims=(1,))
      is_squeezed_labels = True

    loss = nn.sparse_softmax_cross_entropy_with_logits(
        labels=labels, logits=logits, name=name)

    # Restore squeezed dimension, if necessary, so loss matches weights shape.
    if is_squeezed_labels:
      loss = array_ops.expand_dims(loss, axis=(1,))

    return _compute_weighted_loss(loss, weights) 

def sparse_softmax_cross_entropy(logits, labels, weights=1.0, scope=None):
  """Cross-entropy loss using `tf.nn.sparse_softmax_cross_entropy_with_logits`.

  `weights` acts as a coefficient for the loss. If a scalar is provided,
  then the loss is simply scaled by the given value. If `weights` is a
  tensor of size [`batch_size`], then the loss weights apply to each
  corresponding sample.

  Args:
    logits: [batch_size, num_classes] logits outputs of the network .
    labels: [batch_size, 1] or [batch_size] labels of dtype `int32` or `int64`
      in the range `[0, num_classes)`.
    weights: Coefficients for the loss. The tensor must be a scalar or a tensor
      of shape [batch_size] or [batch_size, 1].
    scope: the scope for the operations performed in computing the loss.

  Returns:
    A scalar `Tensor` representing the mean loss value.

  Raises:
    ValueError: If the shapes of `logits`, `labels`, and `weights` are
      incompatible, or if `weights` is None.
  """
  with ops.name_scope(scope, "sparse_softmax_cross_entropy_loss",
                      [logits, labels, weights]) as scope:
    labels = array_ops.reshape(labels, shape=[array_ops.shape(labels)[0]])

    losses = nn.sparse_softmax_cross_entropy_with_logits(
        labels=labels, logits=logits, name="xentropy")
    return compute_weighted_loss(losses, weights, scope=scope) 

def _softmax_cross_entropy_loss(logits, target):
  # Check that we got integer for classification.
  if not target.dtype.is_integer:
    raise ValueError("Target's dtype should be integer "
                     "Instead got %s." % target.dtype)
  # sparse_softmax_cross_entropy_with_logits requires [batch_size] target.
  if len(target.get_shape()) == 2:
    target = array_ops.squeeze(target, squeeze_dims=[1])
  loss_vec = nn.sparse_softmax_cross_entropy_with_logits(
      labels=target, logits=logits)
  return loss_vec 

def _softmax_cross_entropy_loss(logits, labels):
  with ops.name_scope(None, "softmax_cross_entropy_loss", (
      logits,
      labels,)) as name:
    # Check that we got integer for classification.
    if not labels.dtype.is_integer:
      raise ValueError("Labels dtype should be integer "
                       "Instead got %s." % labels.dtype)
    # sparse_softmax_cross_entropy_with_logits requires [batch_size] labels.
    if len(labels.get_shape()) == 2:
      labels = array_ops.squeeze(labels, squeeze_dims=(1,))
    return nn.sparse_softmax_cross_entropy_with_logits(
        labels=labels, logits=logits, name=name) 

def sparse_softmax_cross_entropy(labels, logits, weights=1.0, scope=None,
                                 loss_collection=ops.GraphKeys.LOSSES):
  """Cross-entropy loss using `tf.nn.sparse_softmax_cross_entropy_with_logits`.

  `weights` acts as a coefficient for the loss. If a scalar is provided,
  then the loss is simply scaled by the given value. If `weights` is a
  tensor of shape [`batch_size`], then the loss weights apply to each
  corresponding sample.

  Args:
    labels: `Tensor` of shape `[d_0, d_1, ..., d_{r-1}]` (where `r` is rank of
      `labels` and result) and dtype `int32` or `int64`. Each entry in `labels`
      must be an index in `[0, num_classes)`. Other values will raise an
      exception when this op is run on CPU, and return `NaN` for corresponding
      loss and gradient rows on GPU.
    logits: Unscaled log probabilities of shape
      `[d_0, d_1, ..., d_{r-1}, num_classes]` and dtype `float32` or `float64`.
    weights: Coefficients for the loss. This must be scalar or of same rank as
      `labels`
    scope: the scope for the operations performed in computing the loss.
    loss_collection: collection to which the loss will be added.

  Returns:
    A scalar `Tensor` representing the mean loss value.

  Raises:
    ValueError: If the shapes of logits, labels, and weight are incompatible, or
      if `weights` is None.
  """
  with ops.name_scope(scope, "sparse_softmax_cross_entropy_loss",
                      (logits, labels, weights)) as scope:
    # As documented above in Args, labels contain class IDs and logits contains
    # 1 probability per class ID, so we expect rank(logits) - rank(labels) == 1;
    # therefore, expected_rank_diff=1.
    labels, logits, weights = _remove_squeezable_dimensions(
        labels, logits, weights, expected_rank_diff=1)
    losses = nn.sparse_softmax_cross_entropy_with_logits(labels=labels,
                                                         logits=logits,
                                                         name="xentropy")
    return compute_weighted_loss(losses, weights, scope, loss_collection) 

def sparse_categorical_crossentropy(target, output, from_logits=False):
  """Categorical crossentropy with integer targets.

  Arguments:
      target: An integer tensor.
      output: A tensor resulting from a softmax
          (unless `from_logits` is True, in which
          case `output` is expected to be the logits).
      from_logits: Boolean, whether `output` is the
          result of a softmax, or is a tensor of logits.

  Returns:
      Output tensor.
  """
  # Note: nn.sparse_softmax_cross_entropy_with_logits
  # expects logits, Keras expects probabilities.
  if not from_logits:
    epsilon_ = _to_tensor(epsilon(), output.dtype.base_dtype)
    output = clip_ops.clip_by_value(output, epsilon_, 1 - epsilon_)
    output = math_ops.log(output)

  output_shape = output.get_shape()
  targets = cast(flatten(target), 'int64')
  logits = array_ops.reshape(output, [-1, int(output_shape[-1])])
  res = nn.sparse_softmax_cross_entropy_with_logits(
      labels=targets, logits=logits)
  if len(output_shape) == 3:
    # if our output includes timesteps we need to reshape
    return array_ops.reshape(res, array_ops.shape(output)[:-1])
  else:
    return res 

def sparse_softmax_cross_entropy(
    logits, labels, weights=_WEIGHT_SENTINEL, scope=None,
    weight=_WEIGHT_SENTINEL):
  """Cross-entropy loss using `tf.nn.sparse_softmax_cross_entropy_with_logits`.

  `weight` acts as a coefficient for the loss. If a scalar is provided,
  then the loss is simply scaled by the given value. If `weight` is a
  tensor of size [`batch_size`], then the loss weights apply to each
  corresponding sample.

  Args:
    logits: [batch_size, num_classes] logits outputs of the network .
    labels: [batch_size, 1] or [batch_size] target labels of dtype `int32` or
      `int64` in the range `[0, num_classes)`.
    weights: Coefficients for the loss. The tensor must be a scalar or a tensor
      of shape [batch_size] or [batch_size, 1].
    scope: the scope for the operations performed in computing the loss.
    weight: Deprecated alias for `weights`.

  Returns:
    A scalar `Tensor` representing the loss value.

  Raises:
    ValueError: If the shapes of logits, labels, and weight are incompatible, or
      if `weight` is None.
  """
  weights = _weights(weights, weight)
  with ops.name_scope(scope, "sparse_softmax_cross_entropy_loss",
                      [logits, labels, weights]):
    labels = array_ops.reshape(labels, shape=[array_ops.shape(labels)[0]])
    weights = array_ops.squeeze(weights)

    losses = nn.sparse_softmax_cross_entropy_with_logits(logits, labels,
                                                         name="xentropy")
    return compute_weighted_loss(losses, weights) 

def _softmax_cross_entropy_loss(logits, target):
  # Check that we got integer for classification.
  if not target.dtype.is_integer:
    raise ValueError("Target's dtype should be integer "
                     "Instead got %s." % target.dtype)
  # sparse_softmax_cross_entropy_with_logits requires [batch_size] target.
  if len(target.get_shape()) == 2:
    target = array_ops.squeeze(target, squeeze_dims=[1])
  loss_vec = nn.sparse_softmax_cross_entropy_with_logits(logits, target)
  return loss_vec 

def _softmax_cross_entropy_loss(logits, labels):
  # Check that we got integer for classification.
  if not labels.dtype.is_integer:
    raise ValueError("Labels dtype should be integer "
                     "Instead got %s." % labels.dtype)
  # sparse_softmax_cross_entropy_with_logits requires [batch_size] labels.
  if len(labels.get_shape()) == 2:
    labels = array_ops.squeeze(labels, squeeze_dims=[1])
  loss_vec = nn.sparse_softmax_cross_entropy_with_logits(logits, labels)
  return loss_vec 

def _softmax_cross_entropy_loss(logits, target):
  # Check that we got integer for classification.
  if not target.dtype.is_integer:
    raise ValueError("Target's dtype should be integer "
                     "Instead got %s." % target.dtype)
  # sparse_softmax_cross_entropy_with_logits requires [batch_size] target.
  if len(target.get_shape()) == 2:
    target = array_ops.squeeze(target, squeeze_dims=[1])
  loss_vec = nn.sparse_softmax_cross_entropy_with_logits(
      labels=target, logits=logits)
  return loss_vec 

def _softmax_cross_entropy_loss(logits, labels):
  with ops.name_scope(None, "softmax_cross_entropy_loss", (
      logits,
      labels,)) as name:
    # Check that we got integer for classification.
    if not labels.dtype.is_integer:
      raise ValueError("Labels dtype should be integer "
                       "Instead got %s." % labels.dtype)
    # sparse_softmax_cross_entropy_with_logits requires [batch_size] labels.
    if len(labels.get_shape()) == 2:
      labels = array_ops.squeeze(labels, squeeze_dims=(1,))
    return nn.sparse_softmax_cross_entropy_with_logits(
        labels=labels, logits=logits, name=name) 

def sparse_softmax_cross_entropy(labels, logits, weights=1.0, scope=None,
                                 loss_collection=ops.GraphKeys.LOSSES):
  """Cross-entropy loss using `tf.nn.sparse_softmax_cross_entropy_with_logits`.

  `weights` acts as a coefficient for the loss. If a scalar is provided,
  then the loss is simply scaled by the given value. If `weights` is a
  tensor of shape [`batch_size`], then the loss weights apply to each
  corresponding sample.

  Args:
    labels: `Tensor` of shape `[d_0, d_1, ..., d_{r-1}]` (where `r` is rank of
      `labels` and result) and dtype `int32` or `int64`. Each entry in `labels`
      must be an index in `[0, num_classes)`. Other values will raise an
      exception when this op is run on CPU, and return `NaN` for corresponding
      loss and gradient rows on GPU.
    logits: Unscaled log probabilities of shape
      `[d_0, d_1, ..., d_{r-1}, num_classes]` and dtype `float32` or `float64`.
    weights: Coefficients for the loss. This must be scalar or of same rank as
      `labels`
    scope: the scope for the operations performed in computing the loss.
    loss_collection: collection to which the loss will be added.

  Returns:
    A scalar `Tensor` representing the mean loss value.

  Raises:
    ValueError: If the shapes of logits, labels, and weight are incompatible, or
      if `weights` is None.
  """
  with ops.name_scope(scope, "sparse_softmax_cross_entropy_loss",
                      (logits, labels, weights)) as scope:
    # As documented above in Args, labels contain class IDs and logits contains
    # 1 probability per class ID, so we expect rank(logits) - rank(labels) == 1;
    # therefore, expected_rank_diff=1.
    labels, logits, weights = _remove_squeezable_dimensions(
        labels, logits, weights, expected_rank_diff=1)
    losses = nn.sparse_softmax_cross_entropy_with_logits(labels=labels,
                                                         logits=logits,
                                                         name="xentropy")
    return compute_weighted_loss(losses, weights, scope, loss_collection) 

def sparse_softmax_cross_entropy(logits, labels, weights=1.0, scope=None):
  """Cross-entropy loss using `tf.nn.sparse_softmax_cross_entropy_with_logits`.

  `weights` acts as a coefficient for the loss. If a scalar is provided,
  then the loss is simply scaled by the given value. If `weights` is a
  tensor of size [`batch_size`], then the loss weights apply to each
  corresponding sample.

  Args:
    logits: [batch_size, num_classes] logits outputs of the network .
    labels: [batch_size, 1] or [batch_size] labels of dtype `int32` or `int64`
      in the range `[0, num_classes)`.
    weights: Coefficients for the loss. The tensor must be a scalar or a tensor
      of shape [batch_size] or [batch_size, 1].
    scope: the scope for the operations performed in computing the loss.

  Returns:
    A scalar `Tensor` representing the mean loss value.

  Raises:
    ValueError: If the shapes of `logits`, `labels`, and `weights` are
      incompatible, or if `weights` is None.
  """
  with ops.name_scope(scope, "sparse_softmax_cross_entropy_loss",
                      [logits, labels, weights]) as scope:
    labels = array_ops.reshape(labels, shape=[array_ops.shape(labels)[0]])

    losses = nn.sparse_softmax_cross_entropy_with_logits(labels=labels,
                                                         logits=logits,
                                                         name="xentropy")
    return compute_weighted_loss(losses, weights, scope=scope) 

def sparse_categorical_crossentropy(output, target, from_logits=False):
  """Categorical crossentropy with integer targets.

  Arguments:
      output: A tensor resulting from a softmax
          (unless `from_logits` is True, in which
          case `output` is expected to be the logits).
      target: An integer tensor.
      from_logits: Boolean, whether `output` is the
          result of a softmax, or is a tensor of logits.

  Returns:
      Output tensor.
  """
  # Note: nn.softmax_cross_entropy_with_logits
  # expects logits, Keras expects probabilities.
  if not from_logits:
    epsilon = _to_tensor(_EPSILON, output.dtype.base_dtype)
    output = clip_ops.clip_by_value(output, epsilon, 1 - epsilon)
    output = math_ops.log(output)

  output_shape = output.get_shape()
  targets = cast(flatten(target), 'int64')
  logits = array_ops.reshape(output, [-1, int(output_shape[-1])])
  res = nn.sparse_softmax_cross_entropy_with_logits(
      labels=targets, logits=logits)
  if len(output_shape) == 3:
    # if our output includes timesteps we need to reshape
    return array_ops.reshape(res, array_ops.shape(output)[:-1])
  else:
    return res 

def sparse_softmax_cross_entropy(
    labels, logits, weights=1.0, scope=None,
    loss_collection=ops.GraphKeys.LOSSES,
    reduction=Reduction.SUM_BY_NONZERO_WEIGHTS):
  """Cross-entropy loss using `tf.nn.sparse_softmax_cross_entropy_with_logits`.

  `weights` acts as a coefficient for the loss. If a scalar is provided,
  then the loss is simply scaled by the given value. If `weights` is a
  tensor of shape [`batch_size`], then the loss weights apply to each
  corresponding sample.

  Args:
    labels: `Tensor` of shape `[d_0, d_1, ..., d_{r-1}]` (where `r` is rank of
      `labels` and result) and dtype `int32` or `int64`. Each entry in `labels`
      must be an index in `[0, num_classes)`. Other values will raise an
      exception when this op is run on CPU, and return `NaN` for corresponding
      loss and gradient rows on GPU.
    logits: Unscaled log probabilities of shape
      `[d_0, d_1, ..., d_{r-1}, num_classes]` and dtype `float32` or `float64`.
    weights: Coefficients for the loss. This must be scalar or of same rank as
      `labels`
    scope: the scope for the operations performed in computing the loss.
    loss_collection: collection to which the loss will be added.
    reduction: Type of reduction to apply to loss.

  Returns:
    Weighted loss `Tensor` of the same type as `logits`. If `reduction` is
    `NONE`, this has the same shape as `labels`; otherwise, it is scalar.

  Raises:
    ValueError: If the shapes of logits, labels, and weight are incompatible, or
      if `weights` is None.
  """
  with ops.name_scope(scope, "sparse_softmax_cross_entropy_loss",
                      (logits, labels, weights)) as scope:
    # As documented above in Args, labels contain class IDs and logits contains
    # 1 probability per class ID, so we expect rank(logits) - rank(labels) == 1;
    # therefore, expected_rank_diff=1.
    labels, logits, weights = _remove_squeezable_dimensions(
        labels, logits, weights, expected_rank_diff=1)
    losses = nn.sparse_softmax_cross_entropy_with_logits(labels=labels,
                                                         logits=logits,
                                                         name="xentropy")
    return compute_weighted_loss(
        losses, weights, scope, loss_collection, reduction=reduction) 

def deprecated_flipped_sparse_softmax_cross_entropy_with_logits(logits,
                                                                labels,
                                                                name=None):
  """Computes sparse softmax cross entropy between `logits` and `labels`.

  This function diffs from tf.nn.sparse_softmax_cross_entropy_with_logits only
  in the argument order.

  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.

  A common use case is to have logits of shape `[batch_size, num_classes]` and
  labels of shape `[batch_size]`. But higher dimensions are supported.

  Args:

    logits: Unscaled log probabilities of rank `r` and shape
      `[d_0, d_1, ..., d_{r-2}, num_classes]` and dtype `float32` or `float64`.
    labels: `Tensor` of shape `[d_0, d_1, ..., d_{r-2}]` and dtype `int32` or
      `int64`. Each entry in `labels` must be an index in `[0, num_classes)`.
      Other values will raise an exception when this op is run on CPU, and
      return `NaN` for corresponding corresponding loss and gradient rows
      on GPU.
    name: A name for the operation (optional).

  Returns:
    A `Tensor` of the same shape as `labels` and of the same type as `logits`
    with the softmax cross entropy loss.

  Raises:
    ValueError: If logits are scalars (need to have rank >= 1) or if the rank
      of the labels is not equal to the rank of the labels minus one.
  """
  return nn.sparse_softmax_cross_entropy_with_logits(
      labels=labels, logits=logits, name=name)


# TODO(b/33392402): Formally deprecate this API.
# After LSC (see b/33392402#comment1), this API will be deprecated and callers
# will be suggested to use the (updated version of)
# tf.nn.sigmoid_cross_entropy_with_logits. 

def deprecated_flipped_softmax_cross_entropy_with_logits(logits,
                                                         labels,
                                                         dim=-1,
                                                         name=None):
  """Computes softmax cross entropy between `logits` and `labels`.

  This function diffs from tf.nn.softmax_cross_entropy_with_logits only in the
  argument order.

  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:**  While the classes are mutually exclusive, their probabilities
  need not be.  All that is required is that each row of `labels` is
  a valid probability distribution.  If they are not, the computation of the
  gradient will be incorrect.

  If using exclusive `labels` (wherein one and only
  one class is true at a time), see `sparse_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` and `labels` must have the same shape `[batch_size, num_classes]`
  and the same dtype (either `float16`, `float32`, or `float64`).

  Args:
    logits: Unscaled log probabilities.
    labels: Each row `labels[i]` must be a valid probability distribution.
    dim: The class dimension. Defaulted to -1 which is the last dimension.
    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.
  """
  return nn.softmax_cross_entropy_with_logits(
      labels=labels, logits=logits, dim=dim, name=name)


# TODO(b/33392402): Formally deprecate this API.
# After LSC (see b/33392402#comment1), this API will be deprecated and callers
# will be suggested to use the (updated version of)
# tf.nn.sparse_softmax_cross_entropy_with_logits. 

def sparse_softmax_cross_entropy(
    labels, logits, weights=1.0, scope=None,
    loss_collection=ops.GraphKeys.LOSSES,
    reduction=Reduction.SUM_BY_NONZERO_WEIGHTS):
  """Cross-entropy loss using `tf.nn.sparse_softmax_cross_entropy_with_logits`.

  `weights` acts as a coefficient for the loss. If a scalar is provided,
  then the loss is simply scaled by the given value. If `weights` is a
  tensor of shape [`batch_size`], then the loss weights apply to each
  corresponding sample.

  Args:
    labels: `Tensor` of shape `[d_0, d_1, ..., d_{r-1}]` (where `r` is rank of
      `labels` and result) and dtype `int32` or `int64`. Each entry in `labels`
      must be an index in `[0, num_classes)`. Other values will raise an
      exception when this op is run on CPU, and return `NaN` for corresponding
      loss and gradient rows on GPU.
    logits: Unscaled log probabilities of shape
      `[d_0, d_1, ..., d_{r-1}, num_classes]` and dtype `float32` or `float64`.
    weights: Coefficients for the loss. This must be scalar or broadcastable to
      `labels` (i.e. same rank and each dimension is either 1 or the same).
    scope: the scope for the operations performed in computing the loss.
    loss_collection: collection to which the loss will be added.
    reduction: Type of reduction to apply to loss.

  Returns:
    Weighted loss `Tensor` of the same type as `logits`. If `reduction` is
    `NONE`, this has the same shape as `labels`; otherwise, it is scalar.

  Raises:
    ValueError: If the shapes of `logits`, `labels`, and `weights` are
      incompatible, or if any of them are None.
  """
  if labels is None:
    raise ValueError("labels must not be None.")
  if logits is None:
    raise ValueError("logits must not be None.")
  with ops.name_scope(scope, "sparse_softmax_cross_entropy_loss",
                      (logits, labels, weights)) as scope:
    # As documented above in Args, labels contain class IDs and logits contains
    # 1 probability per class ID, so we expect rank(logits) - rank(labels) == 1;
    # therefore, expected_rank_diff=1.
    labels, logits, weights = _remove_squeezable_dimensions(
        labels, logits, weights, expected_rank_diff=1)
    losses = nn.sparse_softmax_cross_entropy_with_logits(labels=labels,
                                                         logits=logits,
                                                         name="xentropy")
    return compute_weighted_loss(
        losses, weights, scope, loss_collection, reduction=reduction) 

def deprecated_flipped_sparse_softmax_cross_entropy_with_logits(logits,
                                                                labels,
                                                                name=None):
  """Computes sparse softmax cross entropy between `logits` and `labels`.

  This function diffs from tf.nn.sparse_softmax_cross_entropy_with_logits only
  in the argument order.

  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.

  A common use case is to have logits of shape `[batch_size, num_classes]` and
  labels of shape `[batch_size]`. But higher dimensions are supported.

  Args:

    logits: Unscaled log probabilities of rank `r` and shape
      `[d_0, d_1, ..., d_{r-2}, num_classes]` and dtype `float32` or `float64`.
    labels: `Tensor` of shape `[d_0, d_1, ..., d_{r-2}]` and dtype `int32` or
      `int64`. Each entry in `labels` must be an index in `[0, num_classes)`.
      Other values will raise an exception when this op is run on CPU, and
      return `NaN` for corresponding corresponding loss and gradient rows
      on GPU.
    name: A name for the operation (optional).

  Returns:
    A `Tensor` of the same shape as `labels` and of the same type as `logits`
    with the softmax cross entropy loss.

  Raises:
    ValueError: If logits are scalars (need to have rank >= 1) or if the rank
      of the labels is not equal to the rank of the labels minus one.
  """
  return nn.sparse_softmax_cross_entropy_with_logits(
      labels=labels, logits=logits, name=name)


# TODO(b/33392402): Formally deprecate this API.
# After LSC (see b/33392402#comment1), this API will be deprecated and callers
# will be suggested to use the (updated version of)
# tf.nn.sigmoid_cross_entropy_with_logits. 

def deprecated_flipped_softmax_cross_entropy_with_logits(logits,
                                                         labels,
                                                         dim=-1,
                                                         name=None):
  """Computes softmax cross entropy between `logits` and `labels`.

  This function diffs from tf.nn.softmax_cross_entropy_with_logits only in the
  argument order.

  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:**  While the classes are mutually exclusive, their probabilities
  need not be.  All that is required is that each row of `labels` is
  a valid probability distribution.  If they are not, the computation of the
  gradient will be incorrect.

  If using exclusive `labels` (wherein one and only
  one class is true at a time), see `sparse_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` and `labels` must have the same shape `[batch_size, num_classes]`
  and the same dtype (either `float16`, `float32`, or `float64`).

  Args:
    logits: Unscaled log probabilities.
    labels: Each row `labels[i]` must be a valid probability distribution.
    dim: The class dimension. Defaulted to -1 which is the last dimension.
    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.
  """
  return nn.softmax_cross_entropy_with_logits(
      labels=labels, logits=logits, dim=dim, name=name)


# TODO(b/33392402): Formally deprecate this API.
# After LSC (see b/33392402#comment1), this API will be deprecated and callers
# will be suggested to use the (updated version of)
# tf.nn.sparse_softmax_cross_entropy_with_logits. 

def deprecated_flipped_sparse_softmax_cross_entropy_with_logits(logits,
                                                                labels,
                                                                name=None):
  """Computes sparse softmax cross entropy between `logits` and `labels`.

  This function diffs from tf.nn.sparse_softmax_cross_entropy_with_logits only
  in the argument order.

  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.

  A common use case is to have logits of shape `[batch_size, num_classes]` and
  labels of shape `[batch_size]`. But higher dimensions are supported.

  Args:

    logits: Unscaled log probabilities of rank `r` and shape
      `[d_0, d_1, ..., d_{r-2}, num_classes]` and dtype `float32` or `float64`.
    labels: `Tensor` of shape `[d_0, d_1, ..., d_{r-2}]` and dtype `int32` or
      `int64`. Each entry in `labels` must be an index in `[0, num_classes)`.
      Other values will raise an exception when this op is run on CPU, and
      return `NaN` for corresponding corresponding loss and gradient rows
      on GPU.
    name: A name for the operation (optional).

  Returns:
    A `Tensor` of the same shape as `labels` and of the same type as `logits`
    with the softmax cross entropy loss.

  Raises:
    ValueError: If logits are scalars (need to have rank >= 1) or if the rank
      of the labels is not equal to the rank of the labels minus one.
  """
  return nn.sparse_softmax_cross_entropy_with_logits(
      labels=labels, logits=logits, name=name)


# TODO(b/33392402): Formally deprecate this API.
# After LSC (see b/33392402#comment1), this API will be deprecated and callers
# will be suggested to use the (updated version of)
# tf.nn.sigmoid_cross_entropy_with_logits. 

def deprecated_flipped_softmax_cross_entropy_with_logits(logits,
                                                         labels,
                                                         dim=-1,
                                                         name=None):
  """Computes softmax cross entropy between `logits` and `labels`.

  This function diffs from tf.nn.softmax_cross_entropy_with_logits only in the
  argument order.

  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:**  While the classes are mutually exclusive, their probabilities
  need not be.  All that is required is that each row of `labels` is
  a valid probability distribution.  If they are not, the computation of the
  gradient will be incorrect.

  If using exclusive `labels` (wherein one and only
  one class is true at a time), see `sparse_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` and `labels` must have the same shape `[batch_size, num_classes]`
  and the same dtype (either `float16`, `float32`, or `float64`).

  Args:
    logits: Unscaled log probabilities.
    labels: Each row `labels[i]` must be a valid probability distribution.
    dim: The class dimension. Defaulted to -1 which is the last dimension.
    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.
  """
  return nn.softmax_cross_entropy_with_logits(
      labels=labels, logits=logits, dim=dim, name=name)


# TODO(b/33392402): Formally deprecate this API.
# After LSC (see b/33392402#comment1), this API will be deprecated and callers
# will be suggested to use the (updated version of)
# tf.nn.sparse_softmax_cross_entropy_with_logits.