_linear_combination Class — pytorch Architecture
Architecture documentation for the _linear_combination class in LinearAlgebra.cpp from the pytorch codebase.
Entity Profile
Source Code
aten/src/ATen/native/LinearAlgebra.cpp lines 2331–2342
template <typename scalar_t>
inline Tensor _linear_combination(
const Tensor& t,
std::initializer_list<scalar_t> blob) {
// _blob_to_Tensor converts blob to a 2D tensor for _compute_linear_combination.
// If this tensor is of shape (1, *), the result of _compute_linear_combination
// is going to be of shape (1, *t.shape) so we squeeze(0) so that
// for any t with t.dim() >= 1: t.dim() == _compute_linear_combination(t, ...).dim().
return at::native::_compute_linear_combination(
t, _blob_to_Tensor<scalar_t>(blob, t))
.squeeze(0);
}
Source
Analyze Your Own Codebase
Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.
Try Supermodel Free