dragnn_ops.dragnn_embedding_initializer(sstable, vocab, embedding_init=None, name=None)

`dragnn_ops.dragnn_embedding_initializer(sstable, vocab, embedding_init=None, name=None)`

Defined in tensorflow/dragnn/core/ops/gen_dragnn_ops.py.

Reads embeddings from an sstable of dist_belief.TokenEmbedding protos for

every key specified in a text vocabulary file.

Args:

sstable: A string. path to sstable location with embedding vectors.
vocab: A string. path to list of keys corresponding to the sstable to extract.
embedding_init: An optional float. Defaults to 1.
name: A name for the operation (optional).

Returns:

A Tensor of type float32. a tensor containing embeddings from the specified sstable.