input Class — pytorch Architecture
Architecture documentation for the input class in RNN.cpp from the pytorch codebase.
Entity Profile
Source Code
aten/src/ATen/native/RNN.cpp lines 722–733
template<typename nonlinearity, typename cell_params>
struct SimpleCell : Cell<Tensor, cell_params> {
using hidden_type = Tensor;
Tensor operator()(
const Tensor& input,
const Tensor& hidden,
const cell_params& params,
bool pre_compute_input = false) const override {
return nonlinearity{}(params.linear_hh(hidden).add_(
pre_compute_input ? input : params.linear_ih(input)));
}
};
Source
Analyze Your Own Codebase
Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.
Try Supermodel Free