tf.random.experimental.stateless_split

Splits an RNG seed into num new seeds by adding a leading axis.

Used in the notebooks

Used in the tutorials

Example:

seed = [1, 2]
new_seeds = tf.random.experimental.stateless_split(seed, num=3)
print(new_seeds)
tf.Tensor(
[[1105988140 1738052849]
 [-335576002  370444179]
 [  10670227 -246211131]], shape=(3, 2), dtype=int32)
tf.random.stateless_normal(shape=[3], seed=new_seeds[0, :])
<tf.Tensor: shape=(3,), dtype=float32, numpy=array([-0.59835213, -0.9578608 ,
0.9002807 ], dtype=float32)>

seed </