tf.sparse.retain

TensorFlow 2 version View source on GitHub

Retains specified non-empty values within a SparseTensor.

Main aliases

`tf.sparse_retain`

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.sparse.retain, tf.compat.v1.sparse_retain, `tf.compat.v2.sparse.retain`

 
tf.sparse.retain(
    sp_input, to_retain
)

For example, if sp_input has shape [4, 5] and 4 non-empty string values:

[0, 1]: a
[0, 3]: b
[2, 0]: c
[3, 1]: d

and to_retain = [True, False, False, True], then the output will be a SparseTensor of shape [4, 5] with 2 non-empty values:

[0, 1]: a
[3, 1]: d

sp_input The input SparseTensor with N non-empty elements.
to_retain A bool vector of length N with M true values.

A SparseTensor with the same shape as the input and M non-empty elements corresponding to the true positions in to_retain.

TypeError If sp_input is not a SparseTensor.