torch.Tensor.bernoulli — PyTorch 2.7 documentation (original) (raw)
Tensor.bernoulli(*, generator=None) → Tensor¶
Returns a result tensor where each result[i]\texttt{result[i]} is independently sampled from Bernoulli(self[i])\text{Bernoulli}(\texttt{self[i]}). self must have floating point dtype, and the result will have the same dtype.