Reserve a data! O Google I / O retorna de 18 a 20 de maio Registre-se agora


Outputs deterministic pseudorandom values from a gamma distribution.

The generated values follow a gamma distribution with specified concentration (alpha) and inverse scale (beta) parameters.

This is a stateless version of tf.random.gamma: if run twice with the same seeds and shapes, 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_gamma and gamma: in gamma, the shape is always prepended to the shape of the broadcast of alpha with beta; whereas in stateless_gamma the shape parameter must always encompass the shapes of each of alpha and beta (which must broadcast together to match the trailing dimensions of shape).

The samples are differentiable w.r.t. alpha and beta. The derivatives are computed using the approach described in (Figurnov et al., 2018).


samples = tf.random.stateless_gamma([10, 2], seed=[12, 34], alpha=[0.5, 1.5])
# samples has shape [10, 2], where each slice [:, 0] and [:, 1] represents
# the samples drawn from each distribution

samples = tf.random.stateless_gamma([7, 5, 2], seed=[12, 34], alpha=[.5, 1.5])
# samples has shape [7, 5, 2], where each slice [:, :, 0] and [:, :, 1]
# represents the 7x5 samples drawn from each of the two distributions

alpha = tf.constant([[1.], [3.], [5.]])
beta = tf.constant([[3., 4.]])
samples = tf.random.stateless_gamma(
    [30, 3, 2], seed=[12, 34], alpha=alpha, beta=beta)
# samples has shape [30, 3, 2], with 30 samples each of 3x2 distributions.

with tf.GradientTape() as tape:[alpha, beta])
  loss = tf.reduce_mean(tf.square(tf.random.stateless_gamma(
      [30, 3, 2], seed=[12, 34], alpha=alpha, beta=beta)))
dloss_dalpha, dloss_dbeta = tape.gradient(loss, [alpha, beta])
# unbiased stochastic derivatives of the loss function
alpha.shape == dloss_dalpha.shape  # True
beta.shape == dloss_dbeta.shape  # True

shape A 1-D integer Tensor or Python array. The shape of the output tensor.
seed A shape [2] Tensor, the seed to the random number generator. Must have dtype int32 or int64. (When using XLA, only int32 is allowed.)
alpha Tensor. The concentration parameter of the gamma distribution. Must be broadcastable with beta, and broadcastable with the rightmost dimensions of shape.
beta Tensor. The inverse scale parameter of the gamma distribution. Must be broadcastable with alpha and broadcastable with the rightmost dimensions of shape.
dtype Floating point dtype of alpha, beta, and the output.
name A name for the operation (optional).

samples A Tensor of the specified shape filled with random gamma values. For each i, each `samples[..., i] is an independent draw from the gamma distribution with concentration alpha[i] and scale beta[i].