tf.contrib.layers.embedding_lookup_unique

Version of embedding_lookup that avoids duplicate lookups.

tf.contrib.layers.embedding_lookup_unique(
    params,
    ids,
    partition_strategy='mod',
    name=None
)

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, ...].
partition_strategy: A string specifying the partitioning strategy, relevant if len(params) > 1. Currently "div" and "mod" are supported. Default is "mod".
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.