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 )
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
embedding_weights may be a
PartitionedVariable as returned by using
tf.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. Embeddings are always aggregated along the last dimension.
| || 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, a |
| || |
| || |
| ||A string specifying how to combine embedding results for each entry. Currently "mean", "sqrtn" and "sum" are supported, with "mean" the default.|
| ||The id to use for an entry with no features.|
| ||A name for this operation (optional).|
| || A string specifying the partitioning strategy. Currently |
| || If not |
| A dense tensor representing the combined embeddings for the sparse ids. For each row in the dense tensor represented by |
In other words, if
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
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
| || if |
© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.