tf.random.stateless_poisson

View source on GitHub

Outputs deterministic pseudorandom values from a Poisson distribution.

tf.random.stateless_poisson(
    shape, seed, lam, dtype=tf.dtypes.int32, name=None
)

The generated values follow a Poisson distribution with specified rate parameter.

This is a stateless version of tf.random.poisson: if run twice with the same seeds, it will produce the same pseudorandom numbers. The output is consistent across multiple runs on the same hardware (and between CPU and GPU), but may change between versions of TensorFlow or on non-CPU/GPU hardware.

A slight difference exists in the interpretation of the shape parameter between stateless_poisson and poisson: in poisson, the shape is always prepended to the shape of rate; whereas in stateless_poisson the shape of rate must match the trailing dimensions of shape.

Example:

samples = tf.random.stateless_poisson([10, 2], seed=[12, 34], lam=[5, 15])
# samples has shape [10, 2], where each slice [:, 0] and [:, 1] represents
# the samples drawn from each distribution

samples = tf.random.stateless_poisson([7, 5, 2], seed=[12, 34], lam=[5, 15])
# samples has shape [7, 5, 2], where each slice [:, :, 0] and [:, :, 1]
# represents the 7x5 samples drawn from each of the two distributions

rate = tf.constant([[1.], [3.], [5.]])
samples = tf.random.stateless_poisson([30, 3, 1], seed=[12, 34], lam=rate)
# samples has shape [30, 3, 1], with 30 samples each of 3x1 distributions.