multinomial(probs, num_samples, f=None)¶
Draws samples from a multinomial distribution. Specifcally, returns a tensor where each row contains num_samples indices sampled from the multinomial probability distribution located in the corresponding row of tensor input.
probs (array) – The unnormalized probabilities for all classes [batch_shape, num_classes]
num_samples (int) – Number of independent samples to draw for each row slice
f (ml_framework, optional) – Machine learning framework. Inferred from inputs if None.
Drawn samples from the multinomial distribution.