tf.sparse.expand_dims

View source on GitHub

Inserts a dimension of 1 into a tensor's shape.

tf.sparse.expand_dims(
    sp_input, axis=None, name=None
)

Given a tensor sp_input, this operation inserts a dimension of 1 at the dimension index axis of sp_input's shape. The dimension index axis starts at zero; if you specify a negative number for axis it is counted backwards from the end.

Args:

Returns:

A SparseTensor with the same data as sp_input, but its shape has an additional dimension of size 1 added.