Python tensorflow.python.ops.math_ops.reduce_min() Examples

def min(x, axis=None, keepdims=False):
  """Minimum value in a tensor.

  Arguments:
      x: A tensor or variable.
      axis: An integer, the axis to find minimum values.
      keepdims: A boolean, whether to keep the dimensions or not.
          If `keepdims` is `False`, the rank of the tensor is reduced
          by 1. If `keepdims` is `True`,
          the reduced dimension is retained with length 1.

  Returns:
      A tensor with miminum values of `x`.
  """
  axis = _normalize_axis(axis, ndim(x))
  return math_ops.reduce_min(x, reduction_indices=axis, keep_dims=keepdims) 

def _MatrixSetDiagGrad(op, grad):
  input_shape = op.inputs[0].get_shape().merge_with(grad.get_shape())
  diag_shape = op.inputs[1].get_shape()
  batch_shape = input_shape[:-2].merge_with(diag_shape[:-1])
  matrix_shape = input_shape[-2:]
  if batch_shape.is_fully_defined() and matrix_shape.is_fully_defined():
    diag_shape = batch_shape.as_list() + [min(matrix_shape.as_list())]
  else:
    with ops.colocate_with(grad):
      grad_shape = array_ops.shape(grad)
      grad_rank = array_ops.rank(grad)
      batch_shape = array_ops.slice(grad_shape, [0], [grad_rank - 2])
      matrix_shape = array_ops.slice(grad_shape, [grad_rank - 2], [2])
      min_dim = math_ops.reduce_min(matrix_shape)
      diag_shape = array_ops.concat([batch_shape, [min_dim]], 0)
  grad_input = array_ops.matrix_set_diag(
      grad, array_ops.zeros(
          diag_shape, dtype=grad.dtype))
  grad_diag = array_ops.matrix_diag_part(grad)
  return (grad_input, grad_diag) 

def _MatrixSetDiagGrad(op, grad):
  """Gradient for MatrixSetDiag."""
  input_shape = op.inputs[0].get_shape().merge_with(grad.get_shape())
  diag_shape = op.inputs[1].get_shape()
  batch_shape = input_shape[:-2].merge_with(diag_shape[:-1])
  matrix_shape = input_shape[-2:]
  if batch_shape.is_fully_defined() and matrix_shape.is_fully_defined():
    diag_shape = batch_shape.as_list() + [min(matrix_shape.as_list())]
  else:
    with ops.colocate_with(grad):
      grad_shape = array_ops.shape(grad)
      grad_rank = array_ops.rank(grad)
      batch_shape = array_ops.slice(grad_shape, [0], [grad_rank - 2])
      matrix_shape = array_ops.slice(grad_shape, [grad_rank - 2], [2])
      min_dim = math_ops.reduce_min(matrix_shape)
      diag_shape = array_ops.concat([batch_shape, [min_dim]], 0)
  grad_input = array_ops.matrix_set_diag(
      grad, array_ops.zeros(
          diag_shape, dtype=grad.dtype))
  grad_diag = array_ops.matrix_diag_part(grad)
  return (grad_input, grad_diag) 

def _MatrixSetDiagGrad(op, grad):
  input_shape = op.inputs[0].get_shape().merge_with(grad.get_shape())
  diag_shape = op.inputs[1].get_shape()
  batch_shape = input_shape[:-2].merge_with(diag_shape[:-1])
  matrix_shape = input_shape[-2:]
  if batch_shape.is_fully_defined() and matrix_shape.is_fully_defined():
    diag_shape = batch_shape.as_list() + [min(matrix_shape.as_list())]
  else:
    with ops.colocate_with(grad):
      grad_shape = array_ops.shape(grad)
      grad_rank = array_ops.rank(grad)
      batch_shape = array_ops.slice(grad_shape, [0], [grad_rank - 2])
      matrix_shape = array_ops.slice(grad_shape, [grad_rank - 2], [2])
      min_dim = math_ops.reduce_min(matrix_shape)
      diag_shape = array_ops.concat(0, [batch_shape, [min_dim]])
  grad_input = array_ops.matrix_set_diag(
      grad, array_ops.zeros(
          diag_shape, dtype=grad.dtype))
  grad_diag = array_ops.matrix_diag_part(grad)
  return (grad_input, grad_diag) 

def masked_minimum(data, mask, dim=1):
  """Computes the axis wise minimum over chosen elements.

  Args:
    data: 2-D float `Tensor` of size [n, m].
    mask: 2-D Boolean `Tensor` of size [n, m].
    dim: The dimension over which to compute the minimum.

  Returns:
    masked_minimums: N-D `Tensor`.
      The minimized dimension is of size 1 after the operation.
  """
  axis_maximums = math_ops.reduce_max(data, dim, keep_dims=True)
  masked_minimums = math_ops.reduce_min(
      math_ops.multiply(
          data - axis_maximums, mask), dim, keep_dims=True) + axis_maximums
  return masked_minimums 

def masked_maximum(data, mask, dim=1):
  """Computes the axis wise maximum over chosen elements.

  Args:
    data: 2-D float `Tensor` of size [n, m].
    mask: 2-D Boolean `Tensor` of size [n, m].
    dim: The dimension over which to compute the maximum.

  Returns:
    masked_maximums: N-D `Tensor`.
      The maximized dimension is of size 1 after the operation.
  """
  axis_minimums = math_ops.reduce_min(data, dim, keep_dims=True)
  masked_maximums = math_ops.reduce_max(
      math_ops.multiply(
          data - axis_minimums, mask), dim, keep_dims=True) + axis_minimums
  return masked_maximums 

def masked_minimum(data, mask, dim=1):
  """Computes the axis wise minimum over chosen elements.

  Args:
    data: 2-D float `Tensor` of size [n, m].
    mask: 2-D Boolean `Tensor` of size [n, m].
    dim: The dimension over which to compute the minimum.

  Returns:
    masked_minimums: N-D `Tensor`.
      The minimized dimension is of size 1 after the operation.
  """
  axis_maximums = math_ops.reduce_max(data, dim, keepdims=True)
  masked_minimums = math_ops.reduce_min(
      math_ops.multiply(data - axis_maximums, mask), dim,
      keepdims=True) + axis_maximums
  return masked_minimums 

def masked_maximum(data, mask, dim=1):
  """Computes the axis wise maximum over chosen elements.

  Args:
    data: 2-D float `Tensor` of size [n, m].
    mask: 2-D Boolean `Tensor` of size [n, m].
    dim: The dimension over which to compute the maximum.

  Returns:
    masked_maximums: N-D `Tensor`.
      The maximized dimension is of size 1 after the operation.
  """
  axis_minimums = math_ops.reduce_min(data, dim, keepdims=True)
  masked_maximums = math_ops.reduce_max(
      math_ops.multiply(data - axis_minimums, mask), dim,
      keepdims=True) + axis_minimums
  return masked_maximums 

def _MatrixSetDiagGrad(op, grad):
  """Gradient for MatrixSetDiag."""
  input_shape = op.inputs[0].get_shape().merge_with(grad.get_shape())
  diag_shape = op.inputs[1].get_shape()
  batch_shape = input_shape[:-2].merge_with(diag_shape[:-1])
  matrix_shape = input_shape[-2:]
  if batch_shape.is_fully_defined() and matrix_shape.is_fully_defined():
    diag_shape = batch_shape.as_list() + [min(matrix_shape.as_list())]
  else:
    with ops.colocate_with(grad):
      grad_shape = array_ops.shape(grad)
      grad_rank = array_ops.rank(grad)
      batch_shape = array_ops.slice(grad_shape, [0], [grad_rank - 2])
      matrix_shape = array_ops.slice(grad_shape, [grad_rank - 2], [2])
      min_dim = math_ops.reduce_min(matrix_shape)
      diag_shape = array_ops.concat([batch_shape, [min_dim]], 0)
  grad_input = array_ops.matrix_set_diag(
      grad, array_ops.zeros(
          diag_shape, dtype=grad.dtype))
  grad_diag = array_ops.matrix_diag_part(grad)
  return (grad_input, grad_diag) 

def _MatrixSetDiagGrad(op, grad):
  input_shape = op.inputs[0].get_shape().merge_with(grad.get_shape())
  diag_shape = op.inputs[1].get_shape()
  batch_shape = input_shape[:-2].merge_with(diag_shape[:-1])
  matrix_shape = input_shape[-2:]
  if batch_shape.is_fully_defined() and matrix_shape.is_fully_defined():
    diag_shape = batch_shape.as_list() + [min(matrix_shape.as_list())]
  else:
    with ops.colocate_with(grad):
      grad_shape = array_ops.shape(grad)
      grad_rank = array_ops.rank(grad)
      batch_shape = array_ops.slice(grad_shape, [0], [grad_rank - 2])
      matrix_shape = array_ops.slice(grad_shape, [grad_rank - 2], [2])
      min_dim = math_ops.reduce_min(matrix_shape)
      diag_shape = array_ops.concat([batch_shape, [min_dim]], 0)
  grad_input = array_ops.matrix_set_diag(
      grad, array_ops.zeros(
          diag_shape, dtype=grad.dtype))
  grad_diag = array_ops.matrix_diag_part(grad)
  return (grad_input, grad_diag) 

def _assert_non_singular(self):
    """Private default implementation of _assert_non_singular."""
    logging.warn(
        "Using (possibly slow) default implementation of assert_non_singular."
        "  Requires conversion to a dense matrix and O(N^3) operations.")
    if self._can_use_cholesky():
      return self.assert_positive_definite()
    else:
      singular_values = linalg_ops.svd(
          self._get_cached_dense_matrix(), compute_uv=False)
      # TODO(langmore) Add .eig and .cond as methods.
      cond = (math_ops.reduce_max(singular_values, axis=-1) /
              math_ops.reduce_min(singular_values, axis=-1))
      return check_ops.assert_less(
          cond,
          self._max_condition_number_to_be_non_singular(),
          message="Singular matrix up to precision epsilon.")
    raise NotImplementedError("assert_non_singular is not implemented.") 

def _ones_diag(self):
    """Returns the diagonal of this operator as all ones."""
    if self.shape.is_fully_defined():
      d_shape = self.batch_shape.concatenate(
          [min(self.domain_dimension.value, self.range_dimension.value)])
    else:
      d_shape = array_ops.concat(
          [self.batch_shape_tensor(),
           [math_ops.reduce_min(self.shape_tensor()[-2:])]], axis=0)

    return array_ops.ones(shape=d_shape, dtype=self.dtype) 

def test(self):
    result_lt = ops.reduce_min(self.original_lt, {'channel'})
    golden_lt = core.LabeledTensor(
        math_ops.reduce_min(self.original_lt.tensor, 1),
        [self.a0, self.a2, self.a3])
    self.assertLabeledTensorsEqual(result_lt, golden_lt) 

def test_name(self):
    result_lt = ops.reduce_min(self.original_lt, {'channel'})
    self.assertIn('lt_reduce_min', result_lt.name) 

def get_best(self, n):
    """Return the indices and values of the n highest scores in the TopN."""

    def refresh_shortlist():
      """Update the shortlist with the highest scores in id_to_score."""
      new_scores, new_ids = nn_ops.top_k(self.id_to_score, self.shortlist_size)
      smallest_new_score = math_ops.reduce_min(new_scores)
      new_length = math_ops.reduce_sum(
          math_ops.to_int32(math_ops.greater(new_scores, dtypes.float32.min)))
      u1 = self.sl_ids.assign(
          math_ops.to_int64(array_ops.concat([[new_length], new_ids], 0)))
      u2 = self.sl_scores.assign(
          array_ops.concat([[smallest_new_score], new_scores], 0))
      self.last_ops = [u1, u2]
      return control_flow_ops.group(u1, u2)

    # We only need to refresh the shortlist if n is greater than the
    # current shortlist size (which is stored in sl_ids[0]).
    with ops.control_dependencies(self.last_ops):
      cond_op = control_flow_ops.cond(n > self.sl_ids[0], refresh_shortlist,
                                      control_flow_ops.no_op)
      with ops.control_dependencies([cond_op]):
        topk_values, topk_indices = nn_ops.top_k(
            self.sl_scores,
            math_ops.minimum(n, math_ops.to_int32(self.sl_ids[0])))
        # topk_indices are the indices into the shortlist, we want to return
        # the indices into id_to_score
        gathered_indices = array_ops.gather(self.sl_ids, topk_indices)
        return gathered_indices, topk_values 

def min(x, axis=None, keepdims=False):
  """Minimum value in a tensor.

  Arguments:
      x: A tensor or variable.
      axis: An integer, the axis to find minimum values.
      keepdims: A boolean, whether to keep the dimensions or not.
          If `keepdims` is `False`, the rank of the tensor is reduced
          by 1. If `keepdims` is `True`,
          the reduced dimension is retained with length 1.

  Returns:
      A tensor with miminum values of `x`.
  """
  return math_ops.reduce_min(x, axis=axis, keep_dims=keepdims) 

def _test_reduce_min(data, keep_dims=None):
    """ One iteration of reduce_min """
    return _test_reduce(math_ops.reduce_min, data, keep_dims)

#######################################################################
# Reduce_max
# ---------- 

def _prepare_and_validate_params(labels, predictions, weights=None, topn=None):
    """Prepares and validates the parameters.

    Args:
      labels: A `Tensor` of the same shape as `predictions`. A value >= 1 means a
        relevant example.
      predictions: A `Tensor` with shape [batch_size, list_size]. Each value is
        the ranking score of the corresponding example.
      weights: A `Tensor` of the same shape of predictions or [batch_size, 1]. The
        former case is per-example and the latter case is per-list.
      topn: A cutoff for how many examples to consider for this metric.

    Returns:
      (labels, predictions, weights, topn) ready to be used for metric
      calculation.
    """
    labels = ops.convert_to_tensor(labels)
    predictions = ops.convert_to_tensor(predictions)
    weights = 1.0 if weights is None else ops.convert_to_tensor(weights)
    example_weights = array_ops.ones_like(labels) * weights
    predictions.get_shape().assert_is_compatible_with(example_weights.get_shape())
    predictions.get_shape().assert_is_compatible_with(labels.get_shape())
    predictions.get_shape().assert_has_rank(2)
    if topn is None:
        topn = array_ops.shape(predictions)[1]

    # All labels should be >= 0. Invalid entries are reset.
    is_label_valid = utils.is_label_valid(labels)
    labels = array_ops.where(
        is_label_valid,
        labels,
        array_ops.zeros_like(labels))
    predictions = array_ops.where(
        is_label_valid, predictions,
        -1e-6 * array_ops.ones_like(predictions) + math_ops.reduce_min(
            predictions, axis=1, keepdims=True))
    return labels, predictions, example_weights, topn 

def test(self):
    result_lt = ops.reduce_min(self.original_lt, {'channel'})
    golden_lt = core.LabeledTensor(
        math_ops.reduce_min(self.original_lt.tensor, 1),
        [self.a0, self.a2, self.a3])
    self.assertLabeledTensorsEqual(result_lt, golden_lt) 

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 

def compute_facility_energy(pairwise_distances, centroid_ids):
  """Compute the average travel distance to the assigned centroid.

  Args:
    pairwise_distances: 2-D Tensor of pairwise distances.
    centroid_ids: 1-D Tensor of indices.

  Returns:
    facility_energy: dtypes.float32 scalar.
  """
  return -1.0 * math_ops.reduce_sum(
      math_ops.reduce_min(
          array_ops.gather(pairwise_distances, centroid_ids), axis=0)) 

def get_best(self, n):
    """Return the indices and values of the n highest scores in the TopN."""

    def refresh_shortlist():
      """Update the shortlist with the highest scores in id_to_score."""
      new_scores, new_ids = nn_ops.top_k(self.id_to_score, self.shortlist_size)
      smallest_new_score = math_ops.reduce_min(new_scores)
      new_length = math_ops.reduce_sum(
          math_ops.to_int32(math_ops.greater(new_scores, dtypes.float32.min)))
      u1 = self.sl_ids.assign(
          math_ops.to_int64(array_ops.concat([[new_length], new_ids], 0)))
      u2 = self.sl_scores.assign(
          array_ops.concat([[smallest_new_score], new_scores], 0))
      self.last_ops = [u1, u2]
      return control_flow_ops.group(u1, u2)

    # We only need to refresh the shortlist if n is greater than the
    # current shortlist size (which is stored in sl_ids[0]).
    with ops.control_dependencies(self.last_ops):
      cond_op = control_flow_ops.cond(n > self.sl_ids[0], refresh_shortlist,
                                      control_flow_ops.no_op)
      with ops.control_dependencies([cond_op]):
        topk_values, topk_indices = nn_ops.top_k(
            self.sl_scores,
            math_ops.minimum(n, math_ops.to_int32(self.sl_ids[0])))
        # topk_indices are the indices into the shortlist, we want to return
        # the indices into id_to_score
        gathered_indices = array_ops.gather(self.sl_ids, topk_indices)
        return gathered_indices, topk_values 

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 

def compute_facility_energy(pairwise_distances, centroid_ids):
  """Compute the average travel distance to the assigned centroid.

  Args:
    pairwise_distances: 2-D Tensor of pairwise distances.
    centroid_ids: 1-D Tensor of indices.

  Returns:
    facility_energy: dtypes.float32 scalar.
  """
  return -1.0 * math_ops.reduce_sum(
      math_ops.reduce_min(
          array_ops.gather(pairwise_distances, centroid_ids), axis=0)) 

def test_name(self):
    result_lt = ops.reduce_min(self.original_lt, {'channel'})
    self.assertIn('lt_reduce_min', result_lt.name)