Python array_ops.unique方法代码示例

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import unique [as 别名]
def _deduplicate_indexed_slices(values, indices):
  """Sums `values` associated with any non-unique `indices`.

  Args:
    values: A `Tensor` with rank >= 1.
    indices: A one-dimensional integer `Tensor`, indexing into the first
      dimension of `values` (as in an IndexedSlices object).
  Returns:
    A tuple of (`summed_values`, `unique_indices`) where `unique_indices` is a
    de-duplicated version of `indices` and `summed_values` contains the sum of
    `values` slices associated with each unique index.
  """
  unique_indices, new_index_positions = array_ops.unique(indices)
  summed_values = math_ops.unsorted_segment_sum(
      values, new_index_positions,
      array_ops.shape(unique_indices)[0])
  return (summed_values, unique_indices) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import unique [as 别名]
def _resource_apply_sparse_duplicate_indices(self, grad, handle, indices):
    """Add ops to apply sparse gradients to `handle`, with repeated indices.

    Optimizers which override this method must deal with repeated indices. See
    the docstring of `_apply_sparse_duplicate_indices` for details. By default
    the correct behavior, to sum non-unique indices and their associated
    gradients, is enforced by first pre-processing `grad` and `indices` and
    passing them on to `_resource_apply_sparse`. Optimizers which deal correctly
    with duplicate indices may instead override this method to avoid the
    overhead of summing.

    Args:
      grad: a `Tensor` representing the gradient for the affected indices.
      handle: a `Tensor` of dtype `resource` which points to the variable
       to be updated.
      indices: a `Tensor` of integral type representing the indices for
       which the gradient is nonzero. Indices may be repeated.

    Returns:
      An `Operation` which updates the value of the variable.
    """
    summed_grad, unique_indices = _deduplicate_indexed_slices(
        values=grad, indices=indices)
    return self._resource_apply_sparse(summed_grad, handle, unique_indices) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import unique [as 别名]
def _resource_apply_sparse(self, grad, handle, indices):
    """Add ops to apply sparse gradients to the variable `handle`.

    Similar to `_apply_sparse`, the `indices` argument to this method has been
    de-duplicated. Optimizers which deal correctly with non-unique indices may
    instead override `_resource_apply_sparse_duplicate_indices` to avoid this
    overhead.

    Args:
      grad: a `Tensor` representing the gradient for the affected indices.
      handle: a `Tensor` of dtype `resource` which points to the variable
       to be updated.
      indices: a `Tensor` of integral type representing the indices for
       which the gradient is nonzero. Indices are unique.

    Returns:
      An `Operation` which updates the value of the variable.
    """
    raise NotImplementedError() 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import unique [as 别名]
def _apply_sparse_duplicate_indices(self, grad, var):
    """Add ops to apply sparse gradients to `var`, with repeated sparse indices.

    Optimizers which override this method must deal with IndexedSlices objects
    such as the following:

      IndexedSlicesValue(values=[1, 1], indices=[0, 0], dense_shape=[1])

    The correct interpretation is:

      IndexedSlicesValue(values=[2], indices=[0], dense_shape=[1])

    Many optimizers deal incorrectly with repeated indices when updating based
    on sparse gradients (e.g. summing squares rather than squaring the sum, or
    applying momentum terms multiple times). Adding first is always the correct
    behavior, so this is enforced here by reconstructing the IndexedSlices to
    have only unique indices, then calling _apply_sparse.

    Optimizers which deal correctly with repeated indices may instead override
    this method to avoid the overhead of summing indices.

    Args:
      grad: `IndexedSlices`.
      var: A `Variable` object.

    Returns:
      An `Operation`.
    """
    summed_values, unique_indices = _deduplicate_indexed_slices(
        values=grad.values, indices=grad.indices)
    gradient_no_duplicate_indices = ops.IndexedSlices(
        indices=unique_indices,
        values=summed_values,
        dense_shape=grad.dense_shape)
    return self._apply_sparse(gradient_no_duplicate_indices, var) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import unique [as 别名]
def _apply_sparse_duplicate_indices(self, grad, var):
    """Add ops to apply sparse gradients to `var`, with repeated sparse indices.

    Optimizers which override this method must deal with IndexedSlices objects
    such as the following:

      IndexedSlicesValue(values=[1, 1], indices=[0, 0], dense_shape=[1])

    The correct interpretation is:

      IndexedSlicesValue(values=[2], indices=[0], dense_shape=[1])

    Many optimizers deal incorrectly with repeated indices when updating based
    on sparse gradients (e.g. summing squares rather than squaring the sum, or
    applying momentum terms multiple times). Adding first is always the correct
    behavior, so this is enforced here by reconstructing the IndexedSlices to
    have only unique indices, then calling _apply_sparse.

    Optimizers which deal correctly with repeated indices may instead override
    this method to avoid the overhead of summing indices.

    Args:
      grad: `IndexedSlices`.
      var: A `Variable` object.

    Returns:
      An `Operation`.
    """
    unique_indices, new_index_positions = array_ops.unique(grad.indices)
    summed_values = math_ops.unsorted_segment_sum(
        grad.values, new_index_positions, array_ops.shape(unique_indices)[0])
    gradient_no_duplicate_indices = ops.IndexedSlices(
        indices=unique_indices,
        values=summed_values,
        dense_shape=grad.dense_shape)
    return self._apply_sparse(gradient_no_duplicate_indices, var) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import unique [as 别名]
def embedding_lookup_unique(params, ids, name=None):
  """Version of embedding_lookup that avoids duplicate lookups.

  This can save communication in the case of repeated ids.
  Same interface as embedding_lookup. Except it supports multi-dimensional `ids`
  which allows to not reshape input/output to fit gather.

  Args:
    params: A list of tensors with the same shape and type, or a
      `PartitionedVariable`. Shape `[index, d1, d2, ...]`.
    ids: A one-dimensional `Tensor` with type `int32` or `int64` containing
      the ids to be looked up in `params`. Shape `[ids1, ids2, ...]`.
    name: A name for this operation (optional).

  Returns:
    A `Tensor` with the same type as the tensors in `params` and dimension of
    `[ids1, ids2, d1, d2, ...]`.

  Raises:
    ValueError: If `params` is empty.
  """
  with ops.name_scope(name, "EmbeddingLookupUnique", [params, ids]):
    ids = ops.convert_to_tensor(ids)
    shape = array_ops.shape(ids)
    ids_flat = array_ops.reshape(
        ids, math_ops.reduce_prod(shape, keep_dims=True))
    unique_ids, idx = array_ops.unique(ids_flat)
    unique_embeddings = embedding_ops.embedding_lookup(params, unique_ids)
    embeds_flat = array_ops.gather(unique_embeddings, idx)
    embed_shape = array_ops.concat(
        [shape, array_ops.shape(unique_embeddings)[1:]], 0)
    embeds = array_ops.reshape(embeds_flat, embed_shape)
    embeds.set_shape(ids.get_shape().concatenate(
        unique_embeddings.get_shape()[1:]))
    return embeds 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import unique [as 别名]
def compute_gt_cluster_score(pairwise_distances, labels):
  """Compute ground truth facility location score.

  Loop over each unique classes and compute average travel distances.

  Args:
    pairwise_distances: 2-D Tensor of pairwise distances.
    labels: 1-D Tensor of ground truth cluster assignment.

  Returns:
    gt_cluster_score: dtypes.float32 score.
  """
  unique_class_ids = array_ops.unique(labels)[0]
  num_classes = array_ops.size(unique_class_ids)
  iteration = array_ops.constant(0)
  gt_cluster_score = array_ops.constant(0.0, dtype=dtypes.float32)

  def func_cond(iteration, gt_cluster_score):
    del gt_cluster_score  # Unused argument.
    return iteration < num_classes

  def func_body(iteration, gt_cluster_score):
    """Per each cluster, compute the average travel distance."""
    mask = math_ops.equal(labels, unique_class_ids[iteration])
    this_cluster_ids = array_ops.where(mask)
    pairwise_distances_subset = array_ops.transpose(
        array_ops.gather(
            array_ops.transpose(
                array_ops.gather(pairwise_distances, this_cluster_ids)),
            this_cluster_ids))
    this_cluster_score = -1.0 * math_ops.reduce_min(
        math_ops.reduce_sum(
            pairwise_distances_subset, axis=0))
    return iteration + 1, gt_cluster_score + this_cluster_score

  _, gt_cluster_score = control_flow_ops.while_loop(
      func_cond, func_body, [iteration, gt_cluster_score])
  return gt_cluster_score 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import unique [as 别名]
def embedding_lookup_unique(params, ids, name=None):
  """Version of embedding_lookup that avoids duplicate lookups.

  This can save communication in the case of repeated ids.
  Same interface as embedding_lookup. Except it supports multi-dimensional `ids`
  which allows to not reshape input/output to fit gather.

  Args:
    params: A list of tensors with the same shape and type, or a
      `PartitionedVariable`. Shape `[index, d1, d2, ...]`.
    ids: A one-dimensional `Tensor` with type `int32` or `int64` containing
      the ids to be looked up in `params`. Shape `[ids1, ids2, ...]`.
    name: A name for this operation (optional).

  Returns:
    A `Tensor` with the same type as the tensors in `params` and dimension of
    `[ids1, ids2, d1, d2, ...]`.

  Raises:
    ValueError: If `params` is empty.
  """
  with ops.name_scope(name, "EmbeddingLookupUnique", [params, ids]):
    ids = ops.convert_to_tensor(ids)
    shape = array_ops.shape(ids)
    ids_flat = array_ops.reshape(
        ids, math_ops.reduce_prod(shape, keep_dims=True))
    unique_ids, idx = array_ops.unique(ids_flat)
    unique_embeddings = embedding_ops.embedding_lookup(params, unique_ids)
    embeds_flat = array_ops.gather(unique_embeddings, idx)
    embed_shape = array_ops.concat(
        0, [shape, array_ops.shape(unique_embeddings)[1:]])
    embeds = array_ops.reshape(embeds_flat, embed_shape)
    embeds.set_shape(ids.get_shape().concatenate(
        unique_embeddings.get_shape()[1:]))
    return embeds 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import unique [as 别名]
def scattered_embedding_lookup(params,
                               values,
                               dimension,
                               name=None,
                               hash_key=None):
  """Looks up embeddings using parameter hashing for each value in `values`.

  The i-th embedding component of a value v in `values` is found by retrieving
  the weight whose index is a fingerprint of the pair (v,i).
  The concept is explored as "feature hashing" for model compression in this
  paper: http://arxiv.org/pdf/1504.04788.pdf

  Feature hashing has the pleasant effect of allowing us to compute an embedding
  without needing a pre-determined vocabulary, relieving some amount of process
  complexity. It also allows for us to maintain embeddings for possibly
  trillions of features with a fixed amount of memory.

  Note that this is superior to out-of-vocabulary shared "hash buckets" in that
  the embedding is extremely likely to be unique for each token as opposed to
  being shared across probably-colliding tokens. The price is that we must
  compute a hash once for each scalar in the token's embedding as opposed to
  once per token.

  If `params` is a list, it represents a partition of the embedding parameters.
  Each tensor in the list should have the same length, except for the first ones
  which may have an additional element. For instance 10 parameters can be
  partitioned in 4 tensors with length `[3, 3, 2, 2]`.

  Args:
    params: A `Tensor`, `list` of `Tensors`, or `PartitionedVariable`.
      Each tensor must be of rank 1 with fully-defined shape.
    values: `Tensor` of values to be embedded with shape `[d0, ..., dn]`.
    dimension: Embedding dimension.
    name: An optional name for this op.
    hash_key: Specify the hash_key that will be used by the `FingerprintCat64`
      function to combine the crosses fingerprints on SparseFeatureCrossOp
      (optional).

  Returns:
    A `Tensor` with shape `[d0, ..., dn, dimension]`.

  Raises:
    ValueError: if dimension is not positive or the partition size is invalid.
  """
  if dimension is None:
    raise ValueError("You must specify dimension.")
  return _sampled_scattered_embedding_lookup(
      params, values, dimension=dimension, sampled_candidates=None,
      hash_key=hash_key, name=name) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import unique [as 别名]
def compute_augmented_facility_locations(pairwise_distances, labels, all_ids,
                                         margin_multiplier, margin_type):
  """Computes the centroid locations.

  Args:
    pairwise_distances: 2-D Tensor of pairwise distances.
    labels: 1-D Tensor of ground truth cluster assignment.
    all_ids: 1-D Tensor of all data indices.
    margin_multiplier: multiplication constant.
    margin_type: Type of structured margin to use. Default is nmi.

  Returns:
    chosen_ids: 1-D Tensor of chosen centroid indices.
  """

  def func_cond_augmented(iteration, chosen_ids):
    del chosen_ids  # Unused argument in func_cond_augmented.
    return iteration < num_classes

  def func_body_augmented(iteration, chosen_ids):
    # find a new facility location to add
    #  based on the clustering score and the NMI score
    candidate_ids = array_ops.setdiff1d(all_ids, chosen_ids)[0]
    new_chosen_idx = _find_loss_augmented_facility_idx(pairwise_distances,
                                                       labels, chosen_ids,
                                                       candidate_ids,
                                                       margin_multiplier,
                                                       margin_type)
    chosen_ids = array_ops.concat([chosen_ids, [new_chosen_idx]], 0)
    return iteration + 1, chosen_ids

  num_classes = array_ops.size(array_ops.unique(labels)[0])
  chosen_ids = array_ops.constant(0, dtype=dtypes.int32, shape=[0])

  # num_classes get determined at run time based on the sampled batch.
  iteration = array_ops.constant(0)

  _, chosen_ids = control_flow_ops.while_loop(
      func_cond_augmented,
      func_body_augmented, [iteration, chosen_ids],
      shape_invariants=[iteration.get_shape(), tensor_shape.TensorShape(
          [None])])
  return chosen_ids 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import unique [as 别名]
def update_all_medoids(pairwise_distances, predictions, labels, chosen_ids,
                       margin_multiplier, margin_type):
  """Updates all cluster medoids a cluster at a time.

  Args:
    pairwise_distances: 2-D Tensor of pairwise distances.
    predictions: 1-D Tensor of predicted cluster assignment.
    labels: 1-D Tensor of ground truth cluster assignment.
    chosen_ids: 1-D Tensor of cluster centroid indices.
    margin_multiplier: multiplication constant.
    margin_type: Type of structured margin to use. Default is nmi.

  Returns:
    chosen_ids: Updated 1-D Tensor of cluster centroid indices.
  """

  def func_cond_augmented_pam(iteration, chosen_ids):
    del chosen_ids  # Unused argument.
    return iteration < num_classes

  def func_body_augmented_pam(iteration, chosen_ids):
    """Call the update_medoid_per_cluster subroutine."""
    mask = math_ops.equal(
        math_ops.cast(predictions, dtypes.int64),
        math_ops.cast(iteration, dtypes.int64))
    this_cluster_ids = array_ops.where(mask)

    pairwise_distances_subset = array_ops.transpose(
        array_ops.gather(
            array_ops.transpose(
                array_ops.gather(pairwise_distances, this_cluster_ids)),
            this_cluster_ids))

    chosen_ids = update_medoid_per_cluster(pairwise_distances,
                                           pairwise_distances_subset, labels,
                                           chosen_ids, this_cluster_ids,
                                           iteration, margin_multiplier,
                                           margin_type)
    return iteration + 1, chosen_ids

  unique_class_ids = array_ops.unique(labels)[0]
  num_classes = array_ops.size(unique_class_ids)
  iteration = array_ops.constant(0)

  _, chosen_ids = control_flow_ops.while_loop(
      func_cond_augmented_pam, func_body_augmented_pam, [iteration, chosen_ids])
  return chosen_ids 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import unique [as 别名]
def update_all_medoids(pairwise_distances, predictions, labels, chosen_ids,
                       margin_multiplier, margin_type):
  """Updates all cluster medoids a cluster at a time.

  Args:
    pairwise_distances: 2-D Tensor of pairwise distances.
    predictions: 1-D Tensor of predicted cluster assignment.
    labels: 1-D Tensor of ground truth cluster assignment.
    chosen_ids: 1-D Tensor of cluster centroid indices.
    margin_multiplier: multiplication constant.
    margin_type: Type of structured margin to use. Default is nmi.

  Returns:
    chosen_ids: Updated 1-D Tensor of cluster centroid indices.
  """

  def func_cond_augmented_pam(iteration, chosen_ids):
    del chosen_ids  # Unused argument.
    return iteration < num_classes

  def func_body_augmented_pam(iteration, chosen_ids):
    """Call the update_medoid_per_cluster subroutine."""
    mask = math_ops.equal(
        math_ops.to_int64(predictions), math_ops.to_int64(iteration))
    this_cluster_ids = array_ops.where(mask)

    pairwise_distances_subset = array_ops.transpose(
        array_ops.gather(
            array_ops.transpose(
                array_ops.gather(pairwise_distances, this_cluster_ids)),
            this_cluster_ids))

    chosen_ids = update_medoid_per_cluster(pairwise_distances,
                                           pairwise_distances_subset, labels,
                                           chosen_ids, this_cluster_ids,
                                           iteration, margin_multiplier,
                                           margin_type)
    return iteration + 1, chosen_ids

  unique_class_ids = array_ops.unique(labels)[0]
  num_classes = array_ops.size(unique_class_ids)
  iteration = array_ops.constant(0)

  _, chosen_ids = control_flow_ops.while_loop(
      func_cond_augmented_pam, func_body_augmented_pam, [iteration, chosen_ids])
  return chosen_ids 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import unique [as 别名]
def _aggregate_sparse_grad(self, grad, var, train_ops):
    """Aggregate sparse gradients.

    Args:
      grad: The sparse gradient to aggregate.
      var: The variable to apply this gradient to.
      train_ops: The train_ops for the worker to run.

    Returns:
      aggregated_grad: Aggregated grad.
    """
    # Sparse gradients have to be inserted as one pair of (value,
    # indice) as an element instead of the whole "indexedslice" because
    # their shapes are not deterministic.
    sparse_grad_queue = (data_flow_ops.FIFOQueue(
        -1,
        (grad.values.dtype, grad.indices.dtype),
        shapes=(var.get_shape().as_list()[1:], ()),
        shared_name="sparse_grad_q_%s" % var.name))
    self._sparse_grad_queues_and_devs.append((sparse_grad_queue, var.device))

    # Sparse token is inserted after the "enqueue_many" finishes. This
    # is needed to make sure enough sparse gradients have been enqueued
    # before applying them to the variables.
    sparse_token_queue = (data_flow_ops.FIFOQueue(
        self._replicas_to_aggregate * 2,
        types_pb2.DT_INT32,
        shapes=(),
        shared_name="sparse_token_q_%s" % var.name))
    self._one_element_queue_list.append((sparse_token_queue, var.device))

    enqueue_spares_op = sparse_grad_queue.enqueue_many([grad.values,
                                                        grad.indices])
    with ops.control_dependencies([enqueue_spares_op]):
      train_ops.append(sparse_token_queue.enqueue((1,)))

    with ops.control_dependencies([sparse_token_queue.dequeue_many(
        self._replicas_to_aggregate)]):
      values, indices = sparse_grad_queue.dequeue_many(sparse_grad_queue.size())
      concat_grad = ops.IndexedSlices(values, indices, grad.dense_shape)

      # Sum the gradients of the same variables in the sparse layers so
      # that each variable is only updated once. Note that with 2
      # gradients g1 and g2 from 2 replicas for the same variable,
      # apply(g1+g2) is different from apply(g1) and then apply(g2) when
      # the optimizer is complex like Momentum or Adagrad.
      values = concat_grad.values
      indices = concat_grad.indices
      new_indices, indx = array_ops.unique(indices)
      num_indices = array_ops.shape(new_indices)[0]
      sum_values = math_ops.unsorted_segment_sum(values, indx, num_indices)
      return ops.IndexedSlices(sum_values, new_indices, concat_grad.dense_shape) 

# 需要导入模块: from tensorflow.python.ops import array_ops [as 别名]
# 或者: from tensorflow.python.ops.array_ops import unique [as 别名]
def testAllowsWatchingUnconnectedOutputTensor(self):
    """Watch an output slot not emitting any edges.

    (Not even control edges from the node.)
    """

    with session.Session() as sess:
      x_init = constant_op.constant([2, 2, 3, 5, 5])
      x = variables.Variable(x_init, name="unconnected/x")

      # The UniqueOp (tf.unique) has two output slots. Use only slot 0 in the
      # graph. Let the debugger watch the unused slot 1.
      unique_x, _ = array_ops.unique(x, name="unconnected/unique_x")
      y = math_ops.add(unique_x, [0, 1, 2], name="unconnected/y")

      x.initializer.run()

      # Verify that only slot 0 of unique_x has recipients, while slot 1 of the
      # same node does not have recipients.
      unique_x_slot_0_recipients = []
      unique_x_slot_1_recipients = []
      for op in sess.graph.get_operations():
        for inp in op.inputs:
          if inp.name == "unconnected/unique_x:0":
            unique_x_slot_0_recipients.append(op.name)
          elif inp.name == "unconnected/unique_x:1":
            unique_x_slot_1_recipients.append(op.name)

      self.assertEqual(["unconnected/y"], unique_x_slot_0_recipients)
      self.assertEqual([], unique_x_slot_1_recipients)

      y_result, dump = self._debug_run_and_get_dump(sess, y)
      self.assertAllClose([2, 4, 7], y_result)

      # Assert that the connected slot (slot 0) is dumped properly.
      unique_x_slot_0_dumps = dump.watch_key_to_data(
          "unconnected/unique_x:0:DebugIdentity")
      self.assertEqual(1, len(unique_x_slot_0_dumps))
      self.assertEqual("unconnected/unique_x",
                       unique_x_slot_0_dumps[0].node_name)
      self.assertEqual(0, unique_x_slot_0_dumps[0].output_slot)
      self.assertAllClose([2, 3, 5], unique_x_slot_0_dumps[0].get_tensor())

      # Assert that the unconnected slot (slot 1) is dumped properly.
      unique_x_slot_1_dumps = dump.watch_key_to_data(
          "unconnected/unique_x:1:DebugIdentity")
      self.assertEqual(1, len(unique_x_slot_1_dumps))
      self.assertEqual("unconnected/unique_x",
                       unique_x_slot_1_dumps[0].node_name)
      self.assertEqual(1, unique_x_slot_1_dumps[0].output_slot)
      self.assertAllClose([0, 0, 1, 2, 2],
                          unique_x_slot_1_dumps[0].get_tensor())