Function embedding_lookup_sparse_v2

tensorflow/python/ops/embedding_ops.py:838–899

Computes embeddings for the given ids and weights. This op assumes that there is at least one id for each row in the dense tensor represented by sp_ids (i.e. there are no rows with empty features), and that all the indices of sp_ids are in canonical row-major order. It also assumes that all

(params,
                               sp_ids,
                               sp_weights,
                               combiner=None,
                               max_norm=None,
                               name=None)

@tf_export("nn.embedding_lookup_sparse", v1=[])
def embedding_lookup_sparse_v2(params,
                               sp_ids,
                               sp_weights,
                               combiner=None,
                               max_norm=None,
                               name=None):
  """Computes embeddings for the given ids and weights.
  This op assumes that there is at least one id for each row in the dense tensor
  represented by sp_ids (i.e. there are no rows with empty features), and that
  all the indices of sp_ids are in canonical row-major order.
  It also assumes that all id values lie in the range [0, p0), where p0
  is the sum of the size of params along dimension 0.
  Args:
    params: A single tensor representing the complete embedding tensor, or a
      list of P tensors all of same shape except for the first dimension,
      representing sharded embedding tensors.  Alternatively, a
      `PartitionedVariable`, created by partitioning along dimension 0. Each
      element must be appropriately sized for ``"div"`` `partition_strategy`.
    sp_ids: N x M `SparseTensor` of int64 ids where N is typically batch size
      and M is arbitrary.
    sp_weights: either a `SparseTensor` of float / double weights, or `None` to
      indicate all weights should be taken to be 1. If specified, `sp_weights`
      must have exactly the same shape and indices as `sp_ids`.
    combiner: A string specifying the reduction op. Currently "mean", "sqrtn",
      "tile" and "sum" are supported. "sum" computes the weighted sum of the
      embedding results for each row. "mean" is the weighted sum divided by the
      total weight. "sqrtn" is the weighted sum divided by the square root of the
      sum of the squares of the weights.
    max_norm: If not `None`, each embedding is clipped if its l2-norm is larger
      than this value, before combining.
    name: Optional name for the op.
  Returns:
    A dense tensor representing the combined embeddings for the
    sparse ids. For each row in the dense tensor represented by `sp_ids`, the op
    looks up the embeddings for all ids in that row, multiplies them by the
    corresponding weight, and combines these embeddings as specified.
    In other words, if
      `shape(combined params) = [p0, p1, ..., pm]`
    and
      `shape(sp_ids) = shape(sp_weights) = [d0, d1, ..., dn]`
    then
      `shape(output) = [d0, d1, ..., dn-1, p1, ..., pm]`.
    For instance, if params is a 10x20 matrix, and sp_ids / sp_weights are
      ```python
      [0, 0]: id 1, weight 2.0
      [0, 1]: id 3, weight 0.5
      [1, 0]: id 0, weight 1.0
      [2, 3]: id 1, weight 3.0
      ```
    with `combiner`="mean", then the output will be a 3x20 matrix where
      ```python
      output[0, :] = (params[1, :] * 2.0 + params[3, :] * 0.5) / (2.0 + 0.5)
      output[1, :] = (params[0, :] * 1.0) / 1.0
      output[2, :] = (params[1, :] * 3.0) / 3.0
      ```
  Raises:
    TypeError: If `sp_ids` is not a `SparseTensor`, or if `sp_weights` is
      neither `None` nor `SparseTensor`.