Instead of taking seed as an attr which initializes a mutable state within
the op, these random ops take seed as an input, and the random numbers are
a deterministic function of shape and seed.
Functions
stateless_multinomial(...): Draws deterministic pseudorandom samples from a multinomial distribution. (deprecated)
[null,null,["Last updated 2020-10-01 UTC."],[],[],null,["# Module: tf.contrib.stateless\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/contrib/stateless/__init__.py) |\n\nStateless random ops which take seed as a tensor input.\n\nDEPRECATED: Use [`tf.random.stateless_uniform`](../../tf/random/stateless_uniform) rather than\n[`tf.contrib.stateless.stateless_random_uniform`](../../tf/random/stateless_uniform), and similarly for the other\nroutines.\n\nInstead of taking `seed` as an attr which initializes a mutable state within\nthe op, these random ops take `seed` as an input, and the random numbers are\na deterministic function of `shape` and `seed`.\n| **Warning:** These ops are in contrib, and are not stable. They should be consistent across multiple runs on the same hardware, but only for the same version of the code.\n\nFunctions\n---------\n\n[`stateless_multinomial(...)`](../../tf/random/stateless_multinomial): Draws deterministic pseudorandom samples from a multinomial distribution. (deprecated)\n\n[`stateless_random_normal(...)`](../../tf/random/stateless_normal): Outputs deterministic pseudorandom values from a normal distribution.\n\n[`stateless_random_uniform(...)`](../../tf/random/stateless_uniform): Outputs deterministic pseudorandom values from a uniform distribution.\n\n[`stateless_truncated_normal(...)`](../../tf/random/stateless_truncated_normal): Outputs deterministic pseudorandom values, truncated normally distributed."]]