def testNotEqual(self):
    # Scalar inputs.
    tf_val = math_ops.not_equal(constant_op.constant(1),
                                constant_op.constant(1))
    self.assertEqual(tensor_util.constant_value(tf_val), False)

    tf_val = math_ops.not_equal(constant_op.constant(1),
                                constant_op.constant(0))
    self.assertEqual(tensor_util.constant_value(tf_val), True)

    # Shaped inputs with broadcast semantics.
    tf_val = math_ops.not_equal(constant_op.constant([[0, 1]]),
                                constant_op.constant([[0], [1]]))
    c_val = tensor_util.constant_value(tf_val)
    self.assertAllEqual(c_val, [[False, True], [True, False]])

 def call(self, inputs):
   boolean_mask = K.any(
       math_ops.not_equal(inputs, self.mask_value), axis=-1, keepdims=True)
   outputs = inputs * math_ops.cast(boolean_mask, inputs.dtype)
   # Compute the mask and outputs simultaneously.
   outputs._keras_mask = array_ops.squeeze(boolean_mask, axis=-1)  # pylint: disable=protected-access
   return outputs

def collapse_repeated(labels, seq_length, name=None):
  """Merge repeated labels into single labels.

  Args:
    labels: Tensor of shape [batch, max value in seq_length]
    seq_length: Tensor of shape [batch], sequence length of each batch element.
    name: A name for this `Op`. Defaults to "collapse_repeated_labels".

  Returns:
    A tuple `(collapsed_labels, new_seq_length)` where

    collapsed_labels: Tensor of shape [batch, max_seq_length] with repeated
    labels collapsed and padded to max_seq_length, eg:
    `[[A, A, B, B, A], [A, B, C, D, E]] => [[A, B, A, 0, 0], [A, B, C, D, E]]`

    new_seq_length: int tensor of shape [batch] with new sequence lengths.
  """

  with ops.name_scope(name, "collapse_repeated_labels", [labels, seq_length]):
    labels = ops.convert_to_tensor(labels, name="labels")
    seq_length = ops.convert_to_tensor(seq_length, name="seq_length")

    # Mask labels that don't equal previous label.
    label_mask = array_ops.concat([
        array_ops.ones_like(labels[:, :1], dtypes.bool),
        math_ops.not_equal(labels[:, 1:], labels[:, :-1])
    ],
                                  axis=1)

    # Filter labels that aren't in the original sequence.
    maxlen = _get_dim(labels, 1)
    seq_mask = array_ops.sequence_mask(seq_length, maxlen=maxlen)
    label_mask = math_ops.logical_and(label_mask, seq_mask)

    # Count masks for new sequence lengths.
    new_seq_len = math_ops.reduce_sum(
        math_ops.cast(label_mask, dtypes.int32), axis=1)

    # Mask indexes based on sequence length mask.
    new_maxlen = math_ops.reduce_max(new_seq_len)
    idx_mask = array_ops.sequence_mask(new_seq_len, maxlen=new_maxlen)

    # Flatten everything and mask out labels to keep and sparse indices.
    flat_labels = array_ops.reshape(labels, [-1])
    flat_label_mask = array_ops.reshape(label_mask, [-1])
    flat_idx_mask = array_ops.reshape(idx_mask, [-1])
    idx = math_ops.range(_get_dim(flat_idx_mask, 0))

    # Scatter to flat shape.
    flat = array_ops.scatter_nd(
        indices=array_ops.expand_dims(
            array_ops.boolean_mask(idx, flat_idx_mask), axis=1),
        updates=array_ops.boolean_mask(flat_labels, flat_label_mask),
        shape=array_ops.shape(flat_idx_mask))

    # Reshape back to square batch.
    batch_size = _get_dim(labels, 0)
    new_shape = [batch_size, new_maxlen]
    return (array_ops.reshape(flat, new_shape),
            math_ops.cast(new_seq_len, seq_length.dtype))

def _filter_input(input_tensor, vocab_freq_table, vocab_min_count,
                  vocab_subsampling, corpus_size, seed):
  """Filters input tensor based on vocab freq, threshold, and subsampling."""
  if vocab_freq_table is None:
    return input_tensor

  if not isinstance(vocab_freq_table, lookup.InitializableLookupTableBase):
    raise ValueError(
        "vocab_freq_table must be a subclass of "
        "InitializableLookupTableBase (such as HashTable) instead of type "
        "{}.".format(type(vocab_freq_table)))

  with ops.name_scope(
      "filter_vocab", values=[vocab_freq_table, input_tensor, vocab_min_count]):
    freq = vocab_freq_table.lookup(input_tensor)
    # Filters out elements in input_tensor that are not found in
    # vocab_freq_table (table returns a default value of -1 specified above when
    # an element is not found).
    mask = math_ops.not_equal(freq, vocab_freq_table.default_value)

    # Filters out elements whose vocab frequencies are less than the threshold.
    if vocab_min_count is not None:
      cast_threshold = math_ops.cast(vocab_min_count, freq.dtype)
      mask = math_ops.logical_and(mask,
                                  math_ops.greater_equal(freq, cast_threshold))

    input_tensor = array_ops.boolean_mask(input_tensor, mask)
    freq = array_ops.boolean_mask(freq, mask)

  if not vocab_subsampling:
    return input_tensor

  if vocab_subsampling < 0 or vocab_subsampling > 1:
    raise ValueError(
        "Invalid vocab_subsampling={} - it should be within range [0, 1].".
        format(vocab_subsampling))

  # Subsamples the input tokens based on vocabulary frequency and
  # vocab_subsampling threshold (ie randomly discard commonly appearing
  # tokens).
  with ops.name_scope(
      "subsample_vocab", values=[input_tensor, freq, vocab_subsampling]):
    corpus_size = math_ops.cast(corpus_size, dtypes.float64)
    freq = math_ops.cast(freq, dtypes.float64)
    vocab_subsampling = math_ops.cast(vocab_subsampling, dtypes.float64)

    # From tensorflow_models/tutorials/embedding/word2vec_kernels.cc, which is
    # suppose to correlate with Eq. 5 in http://arxiv.org/abs/1310.4546.
    keep_prob = ((math_ops.sqrt(freq /
                                (vocab_subsampling * corpus_size)) + 1.0) *
                 (vocab_subsampling * corpus_size / freq))
    random_prob = random_ops.random_uniform(
        array_ops.shape(freq),
        minval=0,
        maxval=1,
        dtype=dtypes.float64,
        seed=seed)

    mask = math_ops.less_equal(random_prob, keep_prob)
    return array_ops.boolean_mask(input_tensor, mask)

def dense_to_sparse_tensor(dense_tensor, ignore_value=None):
  """Converts dense `Tensor` to `SparseTensor`, dropping `ignore_value` cells.

  Args:
    dense_tensor: A `Tensor`.
    ignore_value: Entries in `dense_tensor` equal to this value will be
      absent from the return `SparseTensor`. If `None`, default value of
      `dense_tensor` dtype will be used (e.g. '' for `str`, 0 for `int`).

  Returns:
    A `SparseTensor` with the same shape as `dense_tensor`.

  Raises:
    ValueError: when `dense_tensor`'s rank is `None`.
  """
  with ops.name_scope("DenseToSparseTensor"):
    dense_tensor = ops.convert_to_tensor(dense_tensor)
    ignore_value = _ignore_value_tensor(dense_tensor.dtype, ignore_value)
    indices = array_ops.where(
        math_ops.not_equal(dense_tensor, ignore_value), name="indices")
    return sparse_tensor.SparseTensor(
        indices=indices,
        values=array_ops.gather_nd(dense_tensor, indices, name="values"),
        dense_shape=array_ops.shape(
            dense_tensor, out_type=dtypes.int64, name="dense_shape"))

  def weighted(y_true, y_pred, weights, mask=None):
    """Wrapper function.

    Arguments:
        y_true: `y_true` argument of `fn`.
        y_pred: `y_pred` argument of `fn`.
        weights: Weights tensor.
        mask: Mask tensor.

    Returns:
        Scalar tensor.
    """
    # score_array has ndim >= 2
    score_array = fn(y_true, y_pred)
    if mask is not None:
      # Cast the mask to floatX to avoid float64 upcasting in theano
      mask = math_ops.cast(mask, K.floatx())
      # mask should have the same shape as score_array
      score_array *= mask
      #  the loss per batch should be proportional
      #  to the number of unmasked samples.
      score_array /= K.mean(mask)

    # apply sample weighting
    if weights is not None:
      # reduce score_array to same ndim as weight array
      ndim = K.ndim(score_array)
      weight_ndim = K.ndim(weights)
      score_array = K.mean(score_array, axis=list(range(weight_ndim, ndim)))
      score_array *= weights
      score_array /= K.mean(
          math_ops.cast(math_ops.not_equal(weights, 0), K.floatx()))
    return K.mean(score_array)

 def _dense_to_sparse_tensor(dense_tensor):
   """Returns a SparseTensor for the input dense_tensor."""
   ignore_value = 0.0
   sparse_indices = array_ops.where(math_ops.not_equal(
       dense_tensor, math_ops.cast(ignore_value, dense_tensor.dtype)))
   sparse_values = array_ops.gather_nd(dense_tensor, sparse_indices)
   # SparseTensor needs the shape to be converted to int64.
   int64_shape = math_ops.to_int64(array_ops.shape(dense_tensor))
   return ops.SparseTensor(sparse_indices, sparse_values, shape=int64_shape)

 def testStringComparison(self):
   x = np.array([["abc", "bh"], ["c", ""]])
   y = np.array([["abc", "bh"], ["def", "hi"]])
   with self.test_session(use_gpu=False) as sess:
     cmp_eq = math_ops.equal(x, y)
     cmp_not_eq = math_ops.not_equal(x, y)
     values = sess.run([cmp_eq, cmp_not_eq])
     self.assertAllEqual([[True, True], [False, False]], values[0])
     self.assertAllEqual([[False, False], [True, True]], values[1])

 def testStringComparison(self):
   x = np.array([["abc", "bh"], ["c", ""]])
   y = np.array([["abc", "bh"], ["def", "hi"]])
   with test_util.force_cpu():
     cmp_eq = math_ops.equal(x, y)
     cmp_not_eq = math_ops.not_equal(x, y)
     values = self.evaluate([cmp_eq, cmp_not_eq])
     self.assertAllEqual([[True, True], [False, False]], values[0])
     self.assertAllEqual([[False, False], [True, True]], values[1])

  def testFilterRange(self):
    dataset = dataset_ops.Dataset.range(100).filter(
        lambda x: math_ops.not_equal(math_ops.mod(x, 3), 2))
    iterator = dataset.make_one_shot_iterator()
    get_next = iterator.get_next()

    with self.test_session() as sess:
      self.assertEqual(0, sess.run(get_next))
      self.assertEqual(1, sess.run(get_next))
      self.assertEqual(3, sess.run(get_next))

  def _create_cond(self, x):

    def branch_fn():
      # Use a random value so the adds can't be constant folded.
      return x + sum(random_ops.random_normal([])
                     for _ in range(self.NUM_INTERMEDIATES))

    # Use a dynamic predicate to make sure the cond isn't constant folded.
    return control_flow_ops.cond(math_ops.not_equal(x, -1),
                                 branch_fn, lambda: 0.0)

 def _gif():
   # Create assert op to check that bytes are GIF decodable
   is_gif = math_ops.equal(substr, b'\x47\x49\x46\x38', name='is_gif')
   decode_msg = 'Unable to decode bytes as JPEG, PNG, or GIF'
   assert_decode = control_flow_ops.Assert(is_gif, [decode_msg])
   # Create assert to make sure that channels is not set to 1
   # Already checked above that channels is in (None, 0, 1, 3)
   gif_channels = 0 if channels is None else channels
   good_channels = math_ops.not_equal(gif_channels, 1, name='check_channels')
   channels_msg = 'Channels must be in (None, 0, 3) when decoding GIF images'
   assert_channels = control_flow_ops.Assert(good_channels, [channels_msg])
   with ops.control_dependencies([assert_decode, assert_channels]):
     return gen_image_ops.decode_gif(contents)

def _num_present(losses, weights, per_batch=False):
  """Computes the number of elements in the loss function induced by `weights`.

  A given weights tensor induces different numbers of usable elements in the
  `losses` tensor. The `weights` tensor is broadcast across `losses` for all
  possible dimensions. For example, if `losses` is a tensor of dimension
  `[4, 5, 6, 3]` and `weights` is a tensor of shape `[4, 5]`, then `weights` is,
  in effect, tiled to match the shape of `losses`. Following this effective
  tile, the total number of present elements is the number of non-zero weights.

  Args:
    losses: `Tensor` of shape `[batch_size, d1, ... dN]`.
    weights: `Tensor` of shape `[]`, `[batch_size]` or
      `[batch_size, d1, ... dK]`, where K < N.
    per_batch: Whether to return the number of elements per batch or as a sum
      total.

  Returns:
    The number of present (non-zero) elements in the losses tensor. If
      `per_batch` is `True`, the value is returned as a tensor of size
      `[batch_size]`. Otherwise, a single scalar tensor is returned.
  """
  # If weights is a scalar, its easy to compute:
  if weights.get_shape().ndims == 0:
    if losses.get_shape().ndims == 0:
      batch_size = 1
    else:
      batch_size = array_ops.reshape(array_ops.slice(array_ops.shape(losses),
                                                     [0], [1]), [])
    num_per_batch = math_ops.div(math_ops.to_float(array_ops.size(losses)),
                                 math_ops.to_float(batch_size))
    num_per_batch = array_ops.where(math_ops.equal(weights, 0),
                                    0.0, num_per_batch)
    num_per_batch = math_ops.multiply(array_ops.ones(
        array_ops.reshape(batch_size, [1])), num_per_batch)
    return num_per_batch if per_batch else math_ops.reduce_sum(num_per_batch)

  # First, count the number of nonzero weights.
  if weights.get_shape().ndims >= 1:
    reduction_indices = list(range(1, weights.get_shape().ndims))
    num_nonzero_per_batch = math_ops.reduce_sum(
        math_ops.to_float(math_ops.not_equal(weights, 0)),
        reduction_indices=reduction_indices)

  # Next, determine the number of elements that weight would broadcast to:
  broadcast_dims = array_ops.slice(array_ops.shape(losses),
                                   [weights.get_shape().ndims], [-1])
  num_to_broadcast = math_ops.to_float(math_ops.reduce_prod(broadcast_dims))

  num_per_batch = math_ops.multiply(num_nonzero_per_batch, num_to_broadcast)
  return num_per_batch if per_batch else math_ops.reduce_sum(num_per_batch)

def _XDivyGrad(op, grad):
  """Returns gradient of xdivy(x, y) with respect to x and y."""
  x = op.inputs[0]
  y = op.inputs[1]
  sx = array_ops.shape(x)
  sy = array_ops.shape(y)
  rx, ry = gen_array_ops.broadcast_gradient_args(sx, sy)
  with ops.control_dependencies([grad]):
    not_zero_x = math_ops.cast(
        math_ops.not_equal(x, math_ops.cast(0., dtype=x.dtype)), dtype=x.dtype)
    partial_x = gen_math_ops.xdivy(not_zero_x, y)
    partial_y = gen_math_ops.xdivy(math_ops.negative(x), y**2)
    return (array_ops.reshape(math_ops.reduce_sum(partial_x * grad, rx), sx),
            array_ops.reshape(math_ops.reduce_sum(partial_y * grad, ry), sy))

 def _tensor_to_sparse_feature_column(dense_tensor):
     """Returns SparseFeatureColumn for the input dense_tensor."""
     ignore_value = 0.0
     sparse_indices = array_ops.where(
         math_ops.not_equal(dense_tensor, math_ops.cast(ignore_value, dense_tensor.dtype))
     )
     sparse_values = array_ops.gather_nd(dense_tensor, sparse_indices)
     # TODO(sibyl-Aix6ihai, sibyl-vie3Poto): Makes this efficient, as now SDCA supports
     # very sparse features with weights and not weights.
     return sdca_ops.SparseFeatureColumn(
         array_ops.reshape(array_ops.split(1, 2, sparse_indices)[0], [-1]),
         array_ops.reshape(array_ops.split(1, 2, sparse_indices)[1], [-1]),
         array_ops.reshape(math_ops.to_float(sparse_values), [-1]),
     )

def _num_present(losses, weight, per_batch=False):
  """Computes the number of elements in the loss function induced by `weight`.

  A given weight tensor induces different numbers of usable elements in the
  `losses` tensor. The `weight` tensor is broadcast across `losses` for all
  possible dimensions. For example, if `losses` is a tensor of dimension
  [4, 5, 6, 3] and weight is a tensor of size [4, 5], then weight is, in effect,
  tiled to match the size of `losses`. Following this effective tile, the total
  number of present elements is the number of non-zero weights.

  Args:
    losses: A tensor of size [batch_size, d1, ... dN].
    weight: A tensor of size [1] or [batch_size, d1, ... dK] where K < N.
    per_batch: Whether to return the number of elements per batch or as a sum
      total.

  Returns:
    The number of present (non-zero) elements in the losses tensor. If
      `per_batch` is True, the value is returned as a tensor of size
      [batch_size]. Otherwise, a single scalar tensor is returned.
  """
  # To ensure that dims of [2, 1] gets mapped to [2,]
  weight = array_ops.squeeze(weight)

  # If the weight is a scalar, its easy to compute:
  if weight.get_shape().ndims == 0:
    batch_size = array_ops.reshape(array_ops.slice(array_ops.shape(losses),
                                                   [0], [1]), [])
    num_per_batch = math_ops.div(math_ops.to_float(array_ops.size(losses)),
                                 math_ops.to_float(batch_size))
    num_per_batch = math_ops.select(math_ops.equal(weight, 0),
                                    0.0, num_per_batch)
    num_per_batch = math_ops.mul(array_ops.ones(
        array_ops.reshape(batch_size, [1])), num_per_batch)
    return num_per_batch if per_batch else math_ops.reduce_sum(num_per_batch)

  # First, count the number of nonzero weights:
  if weight.get_shape().ndims >= 1:
    reduction_indices = list(range(1, weight.get_shape().ndims))
    num_nonzero_per_batch = math_ops.reduce_sum(
        math_ops.to_float(math_ops.not_equal(weight, 0)),
        reduction_indices=reduction_indices)

  # Next, determine the number of elements that weight would broadcast to:
  broadcast_dims = array_ops.slice(array_ops.shape(losses),
                                   [weight.get_shape().ndims], [-1])
  num_to_broadcast = math_ops.to_float(math_ops.reduce_prod(broadcast_dims))

  num_per_batch = math_ops.mul(num_nonzero_per_batch, num_to_broadcast)
  return num_per_batch if per_batch else math_ops.reduce_sum(num_per_batch)

def assert_none_equal(
    x, y, data=None, summarize=None, message=None, name=None):
  """Assert the condition `x != y` holds for all elements.

  Example of adding a dependency to an operation:

  ```python
  with tf.control_dependencies([tf.assert_none_equal(x, y)]):
    output = tf.reduce_sum(x)
  ```

  This condition holds if for every pair of (possibly broadcast) elements
  `x[i]`, `y[i]`, we have `x[i] != y[i]`.
  If both `x` and `y` are empty, this is trivially satisfied.

  Args:
    x:  Numeric `Tensor`.
    y:  Numeric `Tensor`, same dtype as and broadcastable to `x`.
    data:  The tensors to print out if the condition is False.  Defaults to
      error message and first few entries of `x`, `y`.
    summarize: Print this many entries of each tensor.
    message: A string to prefix to the default message.
    name: A name for this operation (optional).
      Defaults to "assert_none_equal".

  Returns:
    Op that raises `InvalidArgumentError` if `x != y` is ever False.
  """
  message = message or ''
  with ops.name_scope(name, 'assert_none_equal', [x, y, data]):
    x = ops.convert_to_tensor(x, name='x')
    y = ops.convert_to_tensor(y, name='y')
    if context.executing_eagerly():
      x_name = _shape_and_dtype_str(x)
      y_name = _shape_and_dtype_str(y)
    else:
      x_name = x.name
      y_name = y.name

    if data is None:
      data = [
          message,
          'Condition x != y did not hold for every single element:',
          'x (%s) = ' % x_name, x,
          'y (%s) = ' % y_name, y
      ]
    condition = math_ops.reduce_all(math_ops.not_equal(x, y))
    return control_flow_ops.Assert(condition, data, summarize=summarize)

  def lookup(self, keys, name=None):
    """Looks up `keys` in the table, outputs the corresponding values.

    It assigns out-of-vocabulary keys to buckets based in their hashes.

    Args:
      keys: Keys to look up. May be either a `SparseTensor` or dense `Tensor`.
      name: Optional name for the op.

    Returns:
      A `SparseTensor` if keys are sparse, otherwise a dense `Tensor`.

    Raises:
      TypeError: when `keys` doesn't match the table key data type.
    """
    if keys.dtype.base_dtype != self._key_dtype:
      raise TypeError("Signature mismatch. Keys must be dtype %s, got %s." %
                      (self._key_dtype, keys.dtype))
    values = keys
    if isinstance(keys, sparse_tensor.SparseTensor):
      values = keys.values
    if self._table and (self._table.key_dtype.base_dtype == dtypes.int64):
      values = math_ops.to_int64(values)

    if self._num_oov_buckets == 0:
      ids = self._table.lookup(values, name=name)
    else:
      # TODO(yleon): Consider moving this functionality to its own kernel.
      with ops.name_scope(name, "%s_Lookup" % self.name) as scope:
        str_to_hash_bucket = self._get_string_to_hash_bucket_fn(
            self._hasher_spec)
        buckets = str_to_hash_bucket(
            _as_string(values),
            num_buckets=self._num_oov_buckets,
            name="hash_bucket")
        if self._table:
          ids = self._table.lookup(values)
          buckets = math_ops.add(buckets, self._table.size())
          is_id_non_default = math_ops.not_equal(ids, self._table.default_value)
          ids = array_ops.where(is_id_non_default, ids, buckets, name=scope)
        else:
          ids = buckets
    if isinstance(keys, sparse_tensor.SparseTensor):
      return sparse_tensor.SparseTensor(keys.indices, ids, keys.dense_shape)
    return ids

def _PowGrad(op, grad):
    """Returns grad * (y*x^(y-1), z*log(x))."""
    x = op.inputs[0]
    y = op.inputs[1]
    z = op.outputs[0]
    sx = array_ops.shape(x)
    sy = array_ops.shape(y)
    rx, ry = gen_array_ops._broadcast_gradient_args(sx, sy)
    gx = array_ops.reshape(math_ops.reduce_sum(grad * y * math_ops.pow(x, y - 1), rx), sx)
    # Avoid false singularity at x = 0
    if x.dtype.is_complex:
        # real(x) < 0 is fine for the complex case
        log_x = math_ops.select(math_ops.not_equal(x, 0), math_ops.log(x), array_ops.zeros_like(x))
    else:
        # There's no sensible real value to return if x < 0, so return 0
        log_x = math_ops.select(x > 0, math_ops.log(x), array_ops.zeros_like(x))
    gy = array_ops.reshape(math_ops.reduce_sum(grad * z * log_x, ry), sy)
    return gx, gy

def dense_to_sparse_tensor(dense_tensor, ignore_value=None):
  """Converts a dense Tensor to a SparseTensor, dropping ignore_value cells.

  Args:
    dense_tensor: A `Tensor`.
    ignore_value: Entries in `dense_tensor` equal to this value will be
      absent from the return `SparseTensor`. If `None`, default value of
      dense_tensor's dtype will be used (e.g. '' for `str`, 0 for `int`).

  Returns:
    A `SparseTensor` with the same shape as `dense_tensor`.

  Raises:
    ValueError: when `dense_tensor`'s rank is `None`.
  """
  with ops.name_scope("DenseToSparseTensor"):
    dense_t = ops.convert_to_tensor(dense_tensor)
    if dense_t.get_shape().ndims is None:
      # TODO(b/32318825): Implement dense_to_sparse_tensor for undefined rank.
      raise ValueError("dense_tensor.get_shape() should be defined, got None.")
    if ignore_value is None:
      if dense_t.dtype == dtypes.string:
        # Exception due to TF strings are converted to numpy objects by default.
        ignore_value = ""
      else:
        ignore_value = dense_t.dtype.as_numpy_dtype()
    dense_shape = math_ops.cast(array_ops.shape(dense_t), dtypes.int64)
    indices = array_ops.where(
        math_ops.not_equal(dense_t, math_ops.cast(ignore_value, dense_t.dtype)))
    index_dims = len(dense_t.get_shape())
    # Flattens the tensor and indices for use with gather.
    flat_tensor = array_ops.reshape(dense_t, [-1])
    flat_indices = indices[:, index_dims - 1]
    # Computes the correct flattened indices for 2d (or higher) tensors.
    if index_dims > 1:
      higher_dims = indices[:, :index_dims - 1]
      shape_multipliers = array_ops.stack(
          _multiplier_helper(array_ops.unstack(dense_shape)[1:]))
      offsets = math_ops.reduce_sum(
          math_ops.multiply(higher_dims, shape_multipliers),
          reduction_indices=[1])
      flat_indices = math_ops.add(flat_indices, offsets)
    values = array_ops.gather(flat_tensor, flat_indices)
    return sparse_tensor.SparseTensor(indices, values, dense_shape)