tf.compat.v1.nn.safe_embedding_lookup_sparse

Stay organized with collections Save and categorize content based on your preferences.

Lookup embedding results, accounting for invalid IDs and empty features.

tf.compat.v1.nn.safe_embedding_lookup_sparse(
    embedding_weights,
    sparse_ids,
    sparse_weights=None,
    combiner='mean',
    default_id=None,
    name=None,
    partition_strategy='div',
    max_norm=None,
    allow_fast_lookup=False
)

The partitioned embedding in embedding_weights must all be the same shape except for the first dimension. The first dimension is allowed to vary as the vocabulary size is not necessarily a multiple of P. embedding_weightsmay be a PartitionedVariable as returned by usingtf.compat.v1.get_variable() with a partitioner.

Invalid IDs (< 0) are pruned from input IDs and weights, as well as any IDs with non-positive weight. For an entry with no features, the embedding vector for default_id is returned, or the 0-vector if default_id is not supplied.

The ids and weights may be multi-dimensional SparseTensors orRaggedTensors with rank of 2. For SpareTensors with left-aligned non-zero entries which can be described as RaggedTensors, use of RaggedTensors can yield higher performance. Embeddings are always aggregated along the last dimension.

Args
embedding_weights	A single tensor representing the complete embedding tensor, or a list tensors all of same shape except for the first dimension, representing sharded embedding tensors. Alternatively, aPartitionedVariable, created by partitioning along dimension 0. Each element must be appropriately sized for the given partition_strategy.
sparse_ids	SparseTensor of shape [d_0, d_1, ..., d_n] containing the ids, where d_0 is typically batch size, or a RaggedTensor with rank 2.
sparse_weights	SparseTensor or RaggedTensor of same type and shape assparse_ids, containing float weights corresponding to sparse_ids, orNone if all weights are assumed to be 1.0.
combiner	A string specifying how to combine embedding results for each entry. Currently "mean", "sqrtn" and "sum" are supported, with "mean" the default.
default_id	The id to use for an entry with no features.
name	A name for this operation (optional).
partition_strategy	A string specifying the partitioning strategy. Currently"div" and "mod" are supported. Default is "div".
max_norm	If not None, all embeddings are l2-normalized to max_norm before combining.
allow_fast_lookup	An optional boolean specifying whether to allow simplified embedding lookups when params is a single tensor andmax_norm is None. Setting this flag to True during training can cause the use of dense gradients with increased memory footprint.

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 embedding_weights) = [p0, p1, ..., pm] and shape(sparse_ids) = shape(sparse_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 [0, 0]: id 1, weight 2.0 [0, 1]: id 3, weight 0.5 [1, 0]: id -1, weight 1.0 [2, 3]: id 1, weight 3.0 default_id is 0. with combiner="mean", then the output will be a 3x20 matrix where 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

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 embedding_weights) = [p0, p1, ..., pm] and shape(sparse_ids) = shape(sparse_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 [0, 0]: id 1, weight 2.0 [0, 1]: id 3, weight 0.5 [1, 0]: id -1, weight 1.0 [2, 3]: id 1, weight 3.0 default_id is 0. with combiner="mean", then the output will be a 3x20 matrix where 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
ValueError	if embedding_weights is empty.

tf.compat.v1.nn.safe_embedding_lookup_sparse | TensorFlow v2.16.1 (original) (raw)