tf.sparse.cross  |  TensorFlow v2.16.1 (original) (raw)

tf.sparse.cross

Stay organized with collections Save and categorize content based on your preferences.

Generates sparse cross from a list of sparse and dense tensors.

View aliases

Compat aliases for migration

SeeMigration guide for more details.

tf.compat.v1.sparse.cross

tf.sparse.cross(
    inputs, name=None, separator=None
)

For example, if the inputs are

* inputs[0]: SparseTensor with shape = [2, 2]
  [0, 0]: "a"
  [1, 0]: "b"
  [1, 1]: "c"
* inputs[1]: SparseTensor with shape = [2, 1]
  [0, 0]: "d"
  [1, 0]: "e"
* inputs[2]: Tensor [["f"], ["g"]]

then the output will be:

shape = [2, 2]
[0, 0]: "a_X_d_X_f"
[1, 0]: "b_X_e_X_g"
[1, 1]: "c_X_e_X_g"

Customized separator "Y":

inp_0 = tf.constant([['a'], ['b']]) inp_1 = tf.constant([['c'], ['d']]) output = tf.sparse.cross([inp_0, inp_1], separator='_Y_') output.values <tf.Tensor: shape=(2,), dtype=string, numpy=array([b'a_Y_c', b'b_Y_d'], dtype=object)>