Shaun
Shaun
Hi, I implement the code, but for the fcn.py on line 145. It says: "The size of tensor a (44) must match the size of tensor b (45) at non-singleton...
Hi, I'm trying to figure out why use the one hot of the index to deconvolve with style patch. Would that loose the original content information? Why not use the...
Hi, I am interested in your work. I know it's being years, but wondering where is your style transfer taking place? I don't see any gram matrix taking places. Thanks