1
$\begingroup$

For https://www.intel.ai/winograd-2/ , why use stride = 2 ?

Why need to transform input image pixels ?

Why this C++ implementation of winograd convolution does not require any input tensors transformation ?

enter image description here

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.