def hashed_embedding_column(column_name,
size,
dimension,
combiner=None,
initializer=None):
"""Creates an embedding column of a sparse feature using parameter hashing.
The i-th embedding component of a value v is found by retrieving an
embedding weight whose index is a fingerprint of the pair (v,i).
Args:
column_name: A string defining sparse column name.
size: An integer specifying the number of parameters in the embedding layer.
dimension: An integer specifying dimension of the embedding.
combiner: A string specifying how to reduce if there are multiple entries
in a single row. Currently "mean", "sqrtn" and "sum" are supported. Each
of this can be thought as example level normalizations on the column:
* "sum": do not normalize features in the column
* "mean": do l1 normalization on features in the column
* "sqrtn": do l2 normalization on features in the column
For more information: `tf.embedding_lookup_sparse`.
initializer: A variable initializer function to be used in embedding
variable initialization. If not specified, defaults to
`tf.truncated_normal_initializer` with mean 0 and standard deviation 0.1.
Returns:
A _HashedEmbeddingColumn.
Raises:
ValueError: if dimension or size is not a positive integer; or if combiner
is not supported.
"""
if combiner is None:
logging.warn("The default value of combiner will change from \"mean\" "
"to \"sqrtn\" after 2016/11/01.")
combiner = "mean"
if (dimension < 1) or (size < 1):
raise ValueError("Dimension and size must be greater than 0. "
"dimension: {}, size: {}, column_name: {}".format(
dimension, size, column_name))
if combiner not in ("mean", "sqrtn", "sum"):
raise ValueError("Combiner must be one of 'mean', 'sqrtn' or 'sum'. "
"combiner: {}, column_name: {}".format(combiner,
column_name))
return _HashedEmbeddingColumn(column_name, size, dimension, combiner,
initializer)
评论列表
文章目录
