Functionally is torch.multinomial the same as torch.distributions.categorical.Categorical?
Question:
For example, if I provide a probability array of [0.5, 0.5], both functions will sample the index [0,1] with equal probability?
Answers:
Yes:
[torch.distributions.categorical.Categorical()] is equivalent to the distribution that torch.multinomial() samples from.
For example, if I provide a probability array of [0.5, 0.5], both functions will sample the index [0,1] with equal probability?
Yes:
[
torch.distributions.categorical.Categorical()] is equivalent to the distribution thattorch.multinomial()samples from.