p_in Class — pytorch Architecture
Architecture documentation for the p_in class in DistributionsHelper.h from the pytorch codebase.
Entity Profile
Source Code
aten/src/ATen/core/DistributionsHelper.h lines 212–227
template <typename T>
struct bernoulli_distribution {
C10_HOST_DEVICE inline bernoulli_distribution(T p_in) : p(p_in) {
TORCH_CHECK_IF_NOT_ON_CUDA(p_in >= 0 && p_in <= 1);
}
template <typename RNG>
C10_HOST_DEVICE inline T operator()(RNG* generator) const {
uniform_real_distribution<T> uniform(0.0, 1.0);
return transformation::bernoulli<T>(uniform(generator), p);
}
private:
T p;
};
Source
Analyze Your Own Codebase
Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.
Try Supermodel Free