|View source on GitHub|
Outputs deterministic pseudorandom values from a gamma distribution.
Compat aliases for migration
See Migration guide for more details.
tf.random.stateless_gamma( shape, seed, alpha, beta=None, dtype=tf.dtypes.float32, name=None )
The generated values follow a gamma distribution with specified concentration
alpha) and inverse scale (
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
but may change between versions of TensorFlow or on non-CPU/GPU hardware.
A slight difference exists in the interpretation of the
shape is always
prepended to the shape of the broadcast of
beta; whereas in
shape parameter must always encompass the shapes of
beta (which must broadcast together to match the
trailing dimensions of
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: tape.watch([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
||A 1-D integer Tensor or Python array. The shape of the output tensor.|
A shape  Tensor, the seed to the random number generator. Must have
Tensor. The concentration parameter of the gamma distribution. Must
be broadcastable with
Tensor. The inverse scale parameter of the gamma distribution. Must be
Floating point dtype of
||A name for the operation (optional).|
||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].|