zp678
zp678
When I trained in mnist, I added deformable conv layer, the experimental accuracy did not increase, and become very low, what is the reason for this phenomenon, how about your...
I met the same problem, have you solved it out? @feitiandemiaomi @samlong-yang @unsky
Just want to use Luna data set, does this file need to be regenerated, how to generate?@lfz
我的也是这个问题，在执行test的时候出现错误，提示时out of memory, 但我训练的时候是可以通过的啊。我也尝试将test时的batch_size减小，但还是不行。不知道您解决了没有？希望可以指教一下，万分感谢@Carl-Lei
Run main.py for testing, but got out of memory。Set batch_size to 1，the result also failed。Error log: @lfz
我也遇到这个问题了，是删除最后一层出现的问题，想问问你怎么解决的，望回答，万分感谢@zj463261929
global name 'DeconvBNLayer' is not defined?，Have you solved this problem?@jufeng123@Qh-chen
I tried your method but it didn't work。Do you have other methods？@lijuan123