I was curious if it is possible to create a U-net type architecture that takes in a 3d image and outputs a 2d image? Or, alternatively, would some other architecture be better suited for this problem? Has anyone tried stacking 2d conv layers in keras (or any other lib) on top of 3d conv layers? I am about to try this myself, but was just wondering if it makes sense, and if any deep learning experts cared to weigh in.


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.