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

def _log_prob(self, event):
    event = self._maybe_assert_valid_sample(event)
    # TODO(jaana): The current sigmoid_cross_entropy_with_logits has
    # inconsistent  behavior for logits = inf/-inf.
    event = math_ops.cast(event, self.logits.dtype)
    logits = self.logits
    # sigmoid_cross_entropy_with_logits doesn't broadcast shape,
    # so we do this here.

    def _broadcast(logits, event):
      return (array_ops.ones_like(event) * logits,
              array_ops.ones_like(logits) * event)

    # First check static shape.
    if (event.get_shape().is_fully_defined() and
        logits.get_shape().is_fully_defined()):
      if event.get_shape() != logits.get_shape():
        logits, event = _broadcast(logits, event)
    else:
      logits, event = control_flow_ops.cond(
          distribution_util.same_dynamic_shape(logits, event),
          lambda: (logits, event),
          lambda: _broadcast(logits, event))
    return -nn.sigmoid_cross_entropy_with_logits(labels=event, logits=logits) 

def binary_crossentropy(target, output, from_logits=False):
  """Binary crossentropy between an output tensor and a target tensor.

  Arguments:
      target: A tensor with the same shape as `output`.
      output: A tensor.
      from_logits: Whether `output` is expected to be a logits tensor.
          By default, we consider that `output`
          encodes a probability distribution.

  Returns:
      A tensor.
  """
  # Note: nn.softmax_cross_entropy_with_logits
  # expects logits, Keras expects probabilities.
  if not from_logits:
    # transform back to logits
    epsilon_ = _to_tensor(epsilon(), output.dtype.base_dtype)
    output = clip_ops.clip_by_value(output, epsilon_, 1 - epsilon_)
    output = math_ops.log(output / (1 - output))
  return nn.sigmoid_cross_entropy_with_logits(labels=target, logits=output) 

def _log_prob(self, event):
    # TODO(jaana): The current sigmoid_cross_entropy_with_logits has
    # inconsistent  behavior for logits = inf/-inf.
    event = ops.convert_to_tensor(event, name="event")
    event = math_ops.cast(event, self.logits.dtype)
    logits = self.logits
    # sigmoid_cross_entropy_with_logits doesn't broadcast shape,
    # so we do this here.
    # TODO(b/30637701): Check dynamic shape, and don't broadcast if the
    # dynamic shapes are the same.
    if (not event.get_shape().is_fully_defined() or
        not logits.get_shape().is_fully_defined() or
        event.get_shape() != logits.get_shape()):
      logits = array_ops.ones_like(event) * logits
      event = array_ops.ones_like(logits) * event
    return -nn.sigmoid_cross_entropy_with_logits(logits, event) 

def _log_prob(self, event):
    # TODO(jaana): The current sigmoid_cross_entropy_with_logits has
    # inconsistent  behavior for logits = inf/-inf.
    event = ops.convert_to_tensor(event, name="event")
    event = math_ops.cast(event, self.logits.dtype)
    logits = self.logits
    # sigmoid_cross_entropy_with_logits doesn't broadcast shape,
    # so we do this here.

    broadcast = lambda logits, event: (
        array_ops.ones_like(event) * logits,
        array_ops.ones_like(logits) * event)

    # First check static shape.
    if (event.get_shape().is_fully_defined() and
        logits.get_shape().is_fully_defined()):
      if event.get_shape() != logits.get_shape():
        logits, event = broadcast(logits, event)
    else:
      logits, event = control_flow_ops.cond(
          distribution_util.same_dynamic_shape(logits, event),
          lambda: (logits, event),
          lambda: broadcast(logits, event))
    return -nn.sigmoid_cross_entropy_with_logits(labels=event, logits=logits) 

def binary_crossentropy(output, target, from_logits=False):
  """Binary crossentropy between an output tensor and a target tensor.

  Arguments:
      output: A tensor.
      target: A tensor with the same shape as `output`.
      from_logits: Whether `output` is expected to be a logits tensor.
          By default, we consider that `output`
          encodes a probability distribution.

  Returns:
      A tensor.
  """
  # Note: nn.softmax_cross_entropy_with_logits
  # expects logits, Keras expects probabilities.
  if not from_logits:
    # transform back to logits
    epsilon = _to_tensor(_EPSILON, output.dtype.base_dtype)
    output = clip_ops.clip_by_value(output, epsilon, 1 - epsilon)
    output = math_ops.log(output / (1 - output))
  return nn.sigmoid_cross_entropy_with_logits(labels=target, logits=output) 

def _log_prob(self, event):
    # TODO(jaana): The current sigmoid_cross_entropy_with_logits has
    # inconsistent  behavior for logits = inf/-inf.
    event = ops.convert_to_tensor(event, name="event")
    event = math_ops.cast(event, self.logits.dtype)
    logits = self.logits
    # sigmoid_cross_entropy_with_logits doesn't broadcast shape,
    # so we do this here.

    broadcast = lambda logits, event: (
        array_ops.ones_like(event) * logits,
        array_ops.ones_like(logits) * event)

    # First check static shape.
    if (event.get_shape().is_fully_defined() and
        logits.get_shape().is_fully_defined()):
      if event.get_shape() != logits.get_shape():
        logits, event = broadcast(logits, event)
    else:
      logits, event = control_flow_ops.cond(
          distribution_util.same_dynamic_shape(logits, event),
          lambda: (logits, event),
          lambda: broadcast(logits, event))
    return -nn.sigmoid_cross_entropy_with_logits(labels=event, logits=logits) 

def _sigmoid_cross_entropy_loss(labels, logits, weights=None):
  with ops.name_scope(None, "sigmoid_cross_entropy_loss",
                      (logits, labels)) as name:
    # sigmoid_cross_entropy_with_logits requires [batch_size, n_classes] labels.
    loss = nn.sigmoid_cross_entropy_with_logits(
        labels=math_ops.to_float(labels), logits=logits, name=name)
    return _compute_weighted_loss(loss, weights) 

def create_loss(self, features, mode, logits, labels):
    """See `Head`."""
    del mode, features  # Unused for this head.
    labels = _check_labels(_maybe_expand_dim(labels), self.logits_dimension)
    if self._label_vocabulary is not None:
      labels = lookup_ops.index_table_from_tensor(
          vocabulary_list=tuple(self._label_vocabulary),
          name='class_id_lookup').lookup(labels)
    labels = math_ops.to_float(labels)
    labels = _assert_range(labels, 2)
    return LossAndLabels(
        unweighted_loss=nn.sigmoid_cross_entropy_with_logits(
            labels=labels, logits=logits),
        processed_labels=labels) 

def _log_loss_with_two_classes(logits, target):
  # sigmoid_cross_entropy_with_logits requires [batch_size, 1] target.
  if len(target.get_shape()) == 1:
    target = array_ops.expand_dims(target, dim=[1])
  loss_vec = nn.sigmoid_cross_entropy_with_logits(logits,
                                                  math_ops.to_float(target))
  return loss_vec 

def _sigmoid_cross_entropy_loss(logits, labels):
  # sigmoid_cross_entropy_with_logits requires [batch_size, n_classes] labels.
  return nn.sigmoid_cross_entropy_with_logits(logits, math_ops.to_float(labels)) 

def _log_loss_with_two_classes(logits, labels):
  # sigmoid_cross_entropy_with_logits requires [batch_size, 1] labels.
  if len(labels.get_shape()) == 1:
    labels = array_ops.expand_dims(labels, dim=[1])
  loss_vec = nn.sigmoid_cross_entropy_with_logits(logits,
                                                  math_ops.to_float(labels))
  return loss_vec 

def _log_prob(self, event):
    if self.validate_args:
      event = distribution_util.embed_check_integer_casting_closed(
          event, target_dtype=dtypes.bool)

    # TODO(jaana): The current sigmoid_cross_entropy_with_logits has
    # inconsistent behavior for logits = inf/-inf.
    event = math_ops.cast(event, self.logits.dtype)
    logits = self.logits
    # sigmoid_cross_entropy_with_logits doesn't broadcast shape,
    # so we do this here.

    def _broadcast(logits, event):
      return (array_ops.ones_like(event) * logits,
              array_ops.ones_like(logits) * event)

    # First check static shape.
    if (event.get_shape().is_fully_defined() and
        logits.get_shape().is_fully_defined()):
      if event.get_shape() != logits.get_shape():
        logits, event = _broadcast(logits, event)
    else:
      logits, event = control_flow_ops.cond(
          distribution_util.same_dynamic_shape(logits, event),
          lambda: (logits, event),
          lambda: _broadcast(logits, event))
    return -nn.sigmoid_cross_entropy_with_logits(labels=event, logits=logits) 

def _sigmoid_cross_entropy_loss(logits, labels):
  with ops.name_scope(None, "sigmoid_cross_entropy_loss",
                      (logits, labels)) as name:
    # sigmoid_cross_entropy_with_logits requires [batch_size, n_classes] labels.
    return nn.sigmoid_cross_entropy_with_logits(
        labels=math_ops.to_float(labels), logits=logits, name=name) 

def _log_loss_with_two_classes(logits, labels):
  with ops.name_scope(None, "log_loss_with_two_classes",
                      (logits, labels)) as name:
    # sigmoid_cross_entropy_with_logits requires [batch_size, 1] labels.
    if len(labels.get_shape()) == 1:
      labels = array_ops.expand_dims(labels, dim=(1,))
    return nn.sigmoid_cross_entropy_with_logits(
        labels=math_ops.to_float(labels), logits=logits, name=name) 

def _log_loss_with_two_classes(logits, labels):
  with ops.name_scope(None, "log_loss_with_two_classes",
                      (logits, labels)) as name:
    # sigmoid_cross_entropy_with_logits requires [batch_size, 1] labels.
    if len(labels.get_shape()) == 1:
      labels = array_ops.expand_dims(labels, dim=(1,))
    return nn.sigmoid_cross_entropy_with_logits(
        labels=math_ops.to_float(labels), logits=logits, name=name) 

def _log_loss_with_two_classes(logits, target):
  # sigmoid_cross_entropy_with_logits requires [batch_size, 1] target.
  if len(target.get_shape()) == 1:
    target = array_ops.expand_dims(target, dim=[1])
  loss_vec = nn.sigmoid_cross_entropy_with_logits(
      labels=math_ops.to_float(target), logits=logits)
  return loss_vec 

def _sigmoid_cross_entropy_loss(logits, labels):
  with ops.name_scope(None, "sigmoid_cross_entropy_loss",
                      (logits, labels)) as name:
    # sigmoid_cross_entropy_with_logits requires [batch_size, n_classes] labels.
    return nn.sigmoid_cross_entropy_with_logits(
        labels=math_ops.to_float(labels), logits=logits, name=name) 

def sigmoid_cross_entropy(
    multi_class_labels, logits, weights=1.0, label_smoothing=0, scope=None,
    loss_collection=ops.GraphKeys.LOSSES,
    reduction=Reduction.SUM_BY_NONZERO_WEIGHTS):
  """Creates a cross-entropy loss using tf.nn.sigmoid_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.

  If `label_smoothing` is nonzero, smooth the labels towards 1/2:

      new_multiclass_labels = multiclass_labels * (1 - label_smoothing)
                              + 0.5 * label_smoothing

  Args:
    multi_class_labels: `[batch_size, num_classes]` target integer labels in
      `(0, 1)`.
    logits: Float `[batch_size, num_classes]` logits outputs of the network.
    weights: Optional `Tensor` whose rank is either 0, or the same rank as
      `labels`, and must be broadcastable to `labels` (i.e., all dimensions must
      be either `1`, or the same as the corresponding `losses` dimension).
    label_smoothing: If greater than `0` then smooth the 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 `logits`; otherwise, it is scalar.

  Raises:
    ValueError: If the shape of `logits` doesn't match that of
      `multi_class_labels` or if the shape of `weights` is invalid, or if
      `weights` is None.  Also if `multi_class_labels` or `logits` is None.
  """
  if multi_class_labels is None:
    raise ValueError("multi_class_labels must not be None.")
  if logits is None:
    raise ValueError("logits must not be None.")
  with ops.name_scope(scope, "sigmoid_cross_entropy_loss",
                      (logits, multi_class_labels, weights)) as scope:
    logits = ops.convert_to_tensor(logits)
    multi_class_labels = math_ops.cast(multi_class_labels, logits.dtype)
    logits.get_shape().assert_is_compatible_with(multi_class_labels.get_shape())

    if label_smoothing > 0:
      multi_class_labels = (multi_class_labels * (1 - label_smoothing) +
                            0.5 * label_smoothing)

    losses = nn.sigmoid_cross_entropy_with_logits(labels=multi_class_labels,
                                                  logits=logits,
                                                  name="xentropy")
    return compute_weighted_loss(
        losses, weights, scope, loss_collection, reduction=reduction) 

def sigmoid_cross_entropy(
    multi_class_labels, logits, weights=1.0, label_smoothing=0, scope=None,
    loss_collection=ops.GraphKeys.LOSSES):
  """Creates a cross-entropy loss using tf.nn.sigmoid_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.

  If `label_smoothing` is nonzero, smooth the labels towards 1/2:

      new_multiclass_labels = multiclass_labels * (1 - label_smoothing)
                              + 0.5 * label_smoothing

  Args:
    multi_class_labels: `[batch_size, num_classes]` target integer labels in
      `(0, 1)`.
    logits: `[batch_size, num_classes]` logits outputs of the network.
    weights: Optional `Tensor` whose rank is either 0, or the same rank as
      `labels`, and must be broadcastable to `labels` (i.e., all dimensions must
      be either `1`, or the same as the corresponding `losses` dimension).
    label_smoothing: If greater than `0` then smooth the 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 loss value.

  Raises:
    ValueError: If the shape of `logits` doesn't match that of
      `multi_class_labels` or if the shape of `weights` is invalid, or if
      `weights` is None.
  """
  with ops.name_scope(scope, "sigmoid_cross_entropy_loss",
                      (logits, multi_class_labels, weights)) as scope:
    logits = ops.convert_to_tensor(logits)
    multi_class_labels = math_ops.cast(multi_class_labels, logits.dtype)
    logits.get_shape().assert_is_compatible_with(multi_class_labels.get_shape())

    if label_smoothing > 0:
      multi_class_labels = (multi_class_labels * (1 - label_smoothing) +
                            0.5 * label_smoothing)

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

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_sigmoid_cross_entropy_with_logits(logits,
                                                         targets,
                                                         name=None):
  """Computes sigmoid cross entropy given `logits`.

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

  Measures the probability error in discrete classification tasks in which each
  class is independent and not mutually exclusive.  For instance, one could
  perform multilabel classification where a picture can contain both an elephant
  and a dog at the same time.

  For brevity, let `x = logits`, `z = targets`.  The logistic loss is

        z * -log(sigmoid(x)) + (1 - z) * -log(1 - sigmoid(x))
      = z * -log(1 / (1 + exp(-x))) + (1 - z) * -log(exp(-x) / (1 + exp(-x)))
      = z * log(1 + exp(-x)) + (1 - z) * (-log(exp(-x)) + log(1 + exp(-x)))
      = z * log(1 + exp(-x)) + (1 - z) * (x + log(1 + exp(-x))
      = (1 - z) * x + log(1 + exp(-x))
      = x - x * z + log(1 + exp(-x))

  For x < 0, to avoid overflow in exp(-x), we reformulate the above

        x - x * z + log(1 + exp(-x))
      = log(exp(x)) - x * z + log(1 + exp(-x))
      = - x * z + log(1 + exp(x))

  Hence, to ensure stability and avoid overflow, the implementation uses this
  equivalent formulation

      max(x, 0) - x * z + log(1 + exp(-abs(x)))

  `logits` and `targets` must have the same type and shape.

  Args:
    logits: A `Tensor` of type `float32` or `float64`.
    targets: A `Tensor` of the same type and shape as `logits`.
    name: A name for the operation (optional).

  Returns:
    A `Tensor` of the same shape as `logits` with the componentwise
    logistic losses.

  Raises:
    ValueError: If `logits` and `targets` do not have the same shape.
  """
  return nn.sigmoid_cross_entropy_with_logits(
      labels=targets, logits=logits, name=name) 

def sigmoid_cross_entropy(
    logits, multi_class_labels, weights=1.0, label_smoothing=0, scope=None):
  """Creates a cross-entropy loss using tf.nn.sigmoid_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.

  If `label_smoothing` is nonzero, smooth the labels towards 1/2:

      new_multiclass_labels = multiclass_labels * (1 - label_smoothing)
                              + 0.5 * label_smoothing

  Args:
    logits: [batch_size, num_classes] logits outputs of the network .
    multi_class_labels: [batch_size, num_classes] labels in (0, 1).
    weights: Coefficients for the loss. The tensor must be a scalar, a tensor of
      shape [batch_size] or shape [batch_size, num_classes].
    label_smoothing: If greater than 0 then smooth the labels.
    scope: The scope for the operations performed in computing the loss.

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

  Raises:
    ValueError: If the shape of `logits` doesn't match that of
      `multi_class_labels` or if the shape of `weights` is invalid, or if
      `weights` is None.
  """
  with ops.name_scope(scope, "sigmoid_cross_entropy_loss",
                      [logits, multi_class_labels, weights]) as scope:
    logits.get_shape().assert_is_compatible_with(multi_class_labels.get_shape())

    multi_class_labels = math_ops.cast(multi_class_labels, logits.dtype)

    if label_smoothing > 0:
      multi_class_labels = (multi_class_labels * (1 - label_smoothing) +
                            0.5 * label_smoothing)

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

def _binary_logistic_head_with_sigmoid_cross_entropy_loss(
    weight_column=None, thresholds=None, label_vocabulary=None, name=None):
  """Creates a `Head` for single label binary classification.

  This head uses `sigmoid_cross_entropy_with_logits` loss.

  This head expects to be fed float labels of shape `(batch_size, 1)`.

  Args:
    weight_column: A string or a `_NumericColumn` created by
      `tf.feature_column.numeric_column` defining feature column representing
      weights. It is used to down weight or boost examples during training. It
      will be multiplied by the loss of the example.
    thresholds: Iterable of floats in the range `(0, 1)`. For binary
      classification metrics such as precision and recall, an eval metric is
      generated for each threshold value. This threshold is applied to the
      logistic values to determine the binary classification (i.e., above the
      threshold is `true`, below is `false`.
    label_vocabulary: A list of strings represents possible label values. If it
      is not given, that means labels are already encoded within [0, 1]. If
      given, labels must be string type and have any value in
      `label_vocabulary`. Also there will be errors if vocabulary is not
      provided and labels are string.
    name: name of the head. If provided, summary and metrics keys will be
      suffixed by `"/" + name`.

  Returns:
    An instance of `Head` for binary classification.

  Raises:
    ValueError: if `thresholds` contains a value outside of `(0, 1)`.
  """
  thresholds = tuple(thresholds) if thresholds else tuple()
  if label_vocabulary is not None and not isinstance(label_vocabulary,
                                                     (list, tuple)):
    raise ValueError('label_vocabulary should be a list. Given type: {}'.format(
        type(label_vocabulary)))

  for threshold in thresholds:
    if (threshold <= 0.0) or (threshold >= 1.0):
      raise ValueError('thresholds not in (0, 1): %s.' % (thresholds,))
  return _BinaryLogisticHeadWithSigmoidCrossEntropyLoss(
      weight_column=weight_column,
      thresholds=thresholds,
      label_vocabulary=label_vocabulary,
      name=name) 

def sigmoid_cross_entropy(
    logits, multi_class_labels, weights=_WEIGHT_SENTINEL, label_smoothing=0,
    scope=None, weight=_WEIGHT_SENTINEL):
  """Creates a cross-entropy loss using tf.nn.sigmoid_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.

  If `label_smoothing` is nonzero, smooth the labels towards 1/2:

      new_multiclass_labels = multiclass_labels * (1 - label_smoothing)
                              + 0.5 * label_smoothing

  Args:
    logits: [batch_size, num_classes] logits outputs of the network .
    multi_class_labels: [batch_size, num_classes] target labels in (0, 1).
    weights: Coefficients for the loss. The tensor must be a scalar, a tensor of
      shape [batch_size] or shape [batch_size, num_classes].
    label_smoothing: If greater than 0 then smooth the labels.
    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 shape of `logits` doesn't match that of
      `multi_class_labels` or if the shape of `weight` is invalid, or if
      `weight` is None.
  """
  weights = _weights(weights, weight)
  with ops.name_scope(scope, "sigmoid_cross_entropy_loss",
                      [logits, multi_class_labels, weights]):
    logits.get_shape().assert_is_compatible_with(multi_class_labels.get_shape())

    multi_class_labels = math_ops.cast(multi_class_labels, logits.dtype)

    if label_smoothing > 0:
      multi_class_labels = (multi_class_labels * (1 - label_smoothing) +
                            0.5 * label_smoothing)

    losses = nn.sigmoid_cross_entropy_with_logits(logits, multi_class_labels,
                                                  name="xentropy")
    return compute_weighted_loss(losses, weights) 

def sigmoid_cross_entropy(logits,
                          multi_class_labels,
                          weights=1.0,
                          label_smoothing=0,
                          scope=None):
  """Creates a cross-entropy loss using tf.nn.sigmoid_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.

  If `label_smoothing` is nonzero, smooth the labels towards 1/2:

      new_multiclass_labels = multiclass_labels * (1 - label_smoothing)
                              + 0.5 * label_smoothing

  Args:
    logits: [batch_size, num_classes] logits outputs of the network .
    multi_class_labels: [batch_size, num_classes] labels in (0, 1).
    weights: Coefficients for the loss. The tensor must be a scalar, a tensor of
      shape [batch_size] or shape [batch_size, num_classes].
    label_smoothing: If greater than 0 then smooth the labels.
    scope: The scope for the operations performed in computing the loss.

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

  Raises:
    ValueError: If the shape of `logits` doesn't match that of
      `multi_class_labels` or if the shape of `weights` is invalid, or if
      `weights` is None.
  """
  with ops.name_scope(scope, "sigmoid_cross_entropy_loss",
                      [logits, multi_class_labels, weights]) as scope:
    logits.get_shape().assert_is_compatible_with(multi_class_labels.get_shape())

    multi_class_labels = math_ops.cast(multi_class_labels, logits.dtype)

    if label_smoothing > 0:
      multi_class_labels = (
          multi_class_labels * (1 - label_smoothing) + 0.5 * label_smoothing)

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

def sigmoid_cross_entropy(
    logits, multi_class_labels, weights=1.0, label_smoothing=0, scope=None):
  """Creates a cross-entropy loss using tf.nn.sigmoid_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.

  If `label_smoothing` is nonzero, smooth the labels towards 1/2:

      new_multiclass_labels = multiclass_labels * (1 - label_smoothing)
                              + 0.5 * label_smoothing

  Args:
    logits: [batch_size, num_classes] logits outputs of the network .
    multi_class_labels: [batch_size, num_classes] labels in (0, 1).
    weights: Coefficients for the loss. The tensor must be a scalar, a tensor of
      shape [batch_size] or shape [batch_size, num_classes].
    label_smoothing: If greater than 0 then smooth the labels.
    scope: The scope for the operations performed in computing the loss.

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

  Raises:
    ValueError: If the shape of `logits` doesn't match that of
      `multi_class_labels` or if the shape of `weights` is invalid, or if
      `weights` is None.
  """
  with ops.name_scope(scope, "sigmoid_cross_entropy_loss",
                      [logits, multi_class_labels, weights]) as scope:
    logits.get_shape().assert_is_compatible_with(multi_class_labels.get_shape())

    multi_class_labels = math_ops.cast(multi_class_labels, logits.dtype)

    if label_smoothing > 0:
      multi_class_labels = (multi_class_labels * (1 - label_smoothing) +
                            0.5 * label_smoothing)

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

def deprecated_flipped_sigmoid_cross_entropy_with_logits(logits,
                                                         targets,
                                                         name=None):
  """Computes sigmoid cross entropy given `logits`.

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

  Measures the probability error in discrete classification tasks in which each
  class is independent and not mutually exclusive.  For instance, one could
  perform multilabel classification where a picture can contain both an elephant
  and a dog at the same time.

  For brevity, let `x = logits`, `z = targets`.  The logistic loss is

        z * -log(sigmoid(x)) + (1 - z) * -log(1 - sigmoid(x))
      = z * -log(1 / (1 + exp(-x))) + (1 - z) * -log(exp(-x) / (1 + exp(-x)))
      = z * log(1 + exp(-x)) + (1 - z) * (-log(exp(-x)) + log(1 + exp(-x)))
      = z * log(1 + exp(-x)) + (1 - z) * (x + log(1 + exp(-x))
      = (1 - z) * x + log(1 + exp(-x))
      = x - x * z + log(1 + exp(-x))

  For x < 0, to avoid overflow in exp(-x), we reformulate the above

        x - x * z + log(1 + exp(-x))
      = log(exp(x)) - x * z + log(1 + exp(-x))
      = - x * z + log(1 + exp(x))

  Hence, to ensure stability and avoid overflow, the implementation uses this
  equivalent formulation

      max(x, 0) - x * z + log(1 + exp(-abs(x)))

  `logits` and `targets` must have the same type and shape.

  Args:
    logits: A `Tensor` of type `float32` or `float64`.
    targets: A `Tensor` of the same type and shape as `logits`.
    name: A name for the operation (optional).

  Returns:
    A `Tensor` of the same shape as `logits` with the componentwise
    logistic losses.

  Raises:
    ValueError: If `logits` and `targets` do not have the same shape.
  """
  return nn.sigmoid_cross_entropy_with_logits(
      labels=targets, logits=logits, name=name) 

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 sigmoid_cross_entropy(
    multi_class_labels, logits, weights=1.0, label_smoothing=0, scope=None,
    loss_collection=ops.GraphKeys.LOSSES):
  """Creates a cross-entropy loss using tf.nn.sigmoid_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.

  If `label_smoothing` is nonzero, smooth the labels towards 1/2:

      new_multiclass_labels = multiclass_labels * (1 - label_smoothing)
                              + 0.5 * label_smoothing

  Args:
    multi_class_labels: `[batch_size, num_classes]` target integer labels in
      `(0, 1)`.
    logits: `[batch_size, num_classes]` logits outputs of the network.
    weights: Optional `Tensor` whose rank is either 0, or the same rank as
      `labels`, and must be broadcastable to `labels` (i.e., all dimensions must
      be either `1`, or the same as the corresponding `losses` dimension).
    label_smoothing: If greater than `0` then smooth the 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 loss value.

  Raises:
    ValueError: If the shape of `logits` doesn't match that of
      `multi_class_labels` or if the shape of `weights` is invalid, or if
      `weights` is None.
  """
  with ops.name_scope(scope, "sigmoid_cross_entropy_loss",
                      (logits, multi_class_labels, weights)) as scope:
    logits = ops.convert_to_tensor(logits)
    multi_class_labels = math_ops.cast(multi_class_labels, logits.dtype)
    logits.get_shape().assert_is_compatible_with(multi_class_labels.get_shape())

    if label_smoothing > 0:
      multi_class_labels = (multi_class_labels * (1 - label_smoothing) +
                            0.5 * label_smoothing)

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

def sigmoid_cross_entropy(
    logits, multi_class_labels, weights=1.0, label_smoothing=0, scope=None):
  """Creates a cross-entropy loss using tf.nn.sigmoid_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.

  If `label_smoothing` is nonzero, smooth the labels towards 1/2:

      new_multiclass_labels = multiclass_labels * (1 - label_smoothing)
                              + 0.5 * label_smoothing

  Args:
    logits: [batch_size, num_classes] logits outputs of the network .
    multi_class_labels: [batch_size, num_classes] labels in (0, 1).
    weights: Coefficients for the loss. The tensor must be a scalar, a tensor of
      shape [batch_size] or shape [batch_size, num_classes].
    label_smoothing: If greater than 0 then smooth the labels.
    scope: The scope for the operations performed in computing the loss.

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

  Raises:
    ValueError: If the shape of `logits` doesn't match that of
      `multi_class_labels` or if the shape of `weights` is invalid, or if
      `weights` is None.
  """
  with ops.name_scope(scope, "sigmoid_cross_entropy_loss",
                      [logits, multi_class_labels, weights]) as scope:
    logits.get_shape().assert_is_compatible_with(multi_class_labels.get_shape())

    multi_class_labels = math_ops.cast(multi_class_labels, logits.dtype)

    if label_smoothing > 0:
      multi_class_labels = (multi_class_labels * (1 - label_smoothing) +
                            0.5 * label_smoothing)

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