Sayantan Das
Sayantan Das
the documentation on readme is not very good.
@ProgrammingTD i think the code presumes all images are face-cropped already so 256*256 will just resize to fit model input size
@flyingtief47 @lzw-lzw check your gcc version, cuda version and python version. The problem seems that ninja is not able to build the cpp extension of a pytorch function, largely due...
@beerose any updates on this?
cc: @liangchen527
@zpshs what do u mean by that? please explain so that i can understand if it is a useful thing.
@jzhang38
@CharlieFRuan is it solved?