tf.random.categorical

Draws samples from a categorical distribution.

Compat aliases for migration

tf.compat.v1.random.categorical

tf.random.categorical(
    logits, num_samples, dtype=None, seed=None, name=None
)

Used in the tutorials
Generate music with an RNN Playing CartPole with the Actor-Critic method Text generation with an RNN Wiki40B Language Models Federated Learning for Text Generation

# samples has shape [1, 5], where each value is either 0 or 1 with equal
# probability.
samples = tf.random.categorical(tf.math.log([[0.5, 0.5]]), 5)

Args
`logits`	2-D Tensor with shape `[batch_size, num_classes]`. Each slice `[i, :]` represents the unnormalized log-probabilities for all classes.
`num_samples`	0-D. Number of independent samples to draw for each row slice.
`dtype`	The integer type of the output: `int32` or `int64`. Defaults to `int64`.
`seed`	A Python integer. Used to create a random seed for the distribution. See `tf.random.set_seed` for behavior.
`name`	Optional name for the operation.

Returns
The drawn samples of shape `[batch_size, num_samples]`.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2024-04-26 UTC.

Args