Applies a linear transformation to the incoming data: y = xA^T + b.
y = xA^T + b
nnf_linear(input, weight, bias = NULL)
input
(N, *, in\_features) where * means any number of additional dimensions
(N, *, in\_features)
*
weight
(out\_features, in\_features) the weights tensor.
(out\_features, in\_features)
bias
optional tensor (out\_features)
(out\_features)