easy_rec/python/core/easyrec_metrics/distribute_metrics_impl_pai.py [2206:2252]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                                   true_p, false_n)

    update_op = compute_recall(true_positives_update_op,
                               false_negatives_update_op, 'update_op')
    if updates_collections:
      ops.add_to_collections(updates_collections, update_op)

    return rec, update_op


def _at_k_name(name, k=None, class_id=None):
  if k is not None:
    name = '%s_at_%d' % (name, k)
  else:
    name = '%s_at_k' % (name)
  if class_id is not None:
    name = '%s_class%d' % (name, class_id)
  return name


def _select_class_id(ids, selected_id):
  """Filter all but `selected_id` out of `ids`.

  Args:
    ids: `int64` `Tensor` or `SparseTensor` of IDs.
    selected_id: Int id to select.

  Returns:
    `SparseTensor` of same dimensions as `ids`. This contains only the entries
    equal to `selected_id`.
  """
  ids = sparse_tensor.convert_to_tensor_or_sparse_tensor(ids)
  if isinstance(ids, sparse_tensor.SparseTensor):
    return sparse_ops.sparse_retain(ids, math_ops.equal(ids.values,
                                                        selected_id))

  # TODO(ptucker): Make this more efficient, maybe add a sparse version of
  # tf.equal and tf.reduce_any?

  # Shape of filled IDs is the same as `ids` with the last dim collapsed to 1.
  ids_shape = array_ops.shape(ids, out_type=dtypes.int64)
  ids_last_dim = array_ops.size(ids_shape) - 1
  filled_selected_id_shape = math_ops.reduced_shape(
      ids_shape, array_ops.reshape(ids_last_dim, [1]))

  # Intersect `ids` with the selected ID.
  filled_selected_id = array_ops.fill(filled_selected_id_shape,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



easy_rec/python/core/easyrec_metrics/distribute_metrics_impl_tf.py [2218:2264]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                                     true_p, false_n)

    update_op = compute_recall(true_positives_update_op,
                               false_negatives_update_op, 'update_op')
    if updates_collections:
      ops.add_to_collections(updates_collections, update_op)

    return rec, update_op


def _at_k_name(name, k=None, class_id=None):
  if k is not None:
    name = '%s_at_%d' % (name, k)
  else:
    name = '%s_at_k' % (name)
  if class_id is not None:
    name = '%s_class%d' % (name, class_id)
  return name


def _select_class_id(ids, selected_id):
  """Filter all but `selected_id` out of `ids`.

  Args:
    ids: `int64` `Tensor` or `SparseTensor` of IDs.
    selected_id: Int id to select.

  Returns:
    `SparseTensor` of same dimensions as `ids`. This contains only the entries
    equal to `selected_id`.
  """
  ids = sparse_tensor.convert_to_tensor_or_sparse_tensor(ids)
  if isinstance(ids, sparse_tensor.SparseTensor):
    return sparse_ops.sparse_retain(ids, math_ops.equal(ids.values,
                                                        selected_id))

  # TODO(ptucker): Make this more efficient, maybe add a sparse version of
  # tf.equal and tf.reduce_any?

  # Shape of filled IDs is the same as `ids` with the last dim collapsed to 1.
  ids_shape = array_ops.shape(ids, out_type=dtypes.int64)
  ids_last_dim = array_ops.size(ids_shape) - 1
  filled_selected_id_shape = math_ops.reduced_shape(
      ids_shape, array_ops.reshape(ids_last_dim, [1]))

  # Intersect `ids` with the selected ID.
  filled_selected_id = array_ops.fill(filled_selected_id_shape,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -