The starting image size is 49x49 and therefore the encoder and decoder parts are not symmetric. Is it going to affect the ability of the network to learn? PS - By asymmetric I mean the filter sizes (kernel sizes), strides are not same for the encoder and decoder part of the network.


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.