After a series of convolutions, I am up-sampling a compressed representation, I was curious what is the methodology I should follow to choose an optimum kernel size for up-sampling.

  1. How will the filter (or kernel) size affect the transpose convolution operation (e.g. when using ConvTranspose2d)? Will a larger kernel help upsample with better detail or a small-sized kernel? And how would padding fit in this scenario?

  2. At what rate should the depth decrease while upsampling i.e from (Dx24x24) to (D/2 or D/4, 48, 48)


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.