tf.nn.embedding_lookup( params, ids, partition_strategy='mod', name=None, validate_indices=True, max_norm=None )
See the guide: Neural Network > Embeddings
ids in a list of embedding tensors.
This function is used to perform parallel lookups on the list of
params. It is a generalization of
interpreted as a partitioning of a large embedding tensor.
params may be
PartitionedVariable as returned by using
tf.get_variable() with a
len(params) > 1, each element
ids is partitioned between
the elements of
params according to the
In all strategies, if the id space does not evenly divide the number of
partitions, each of the first
(max_id + 1) % len(params) partitions will
be assigned one more id.
"mod", we assign each id to partition
p = id % len(params). For instance,
13 ids are split across 5 partitions as:
[[0, 5, 10], [1, 6, 11], [2, 7, 12], [3, 8], [4, 9]]
"div", we assign ids to partitions in a
contiguous manner. In this case, 13 ids are split across 5 partitions as:
[[0, 1, 2], [3, 4, 5], [6, 7, 8], [9, 10], [11, 12]]
The results of the lookup are concatenated into a dense
tensor. The returned tensor has shape
shape(ids) + shape(params)[1:].
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 the given
int64containing the ids to be looked up in
partition_strategy: A string specifying the partitioning strategy, relevant if
len(params) > 1. Currently
"mod"are supported. Default is
name: A name for the operation (optional).
validate_indices: DEPRECATED. If this operation is assigned to CPU, values in
indicesare always validated to be within range. If assigned to GPU, out-of-bound indices result in safe but unspecified behavior, which may include raising an error.
max_norm: If provided, embedding values are l2-normalized to the value of max_norm.
Tensor with the same type as the tensors in