junqiangchen
junqiangchen
you can modify it,but i set the if stridez >= 1 and stridewidth >= 1 and strideheight >= 1: that is for making sure input image size(x,y,z) is bigger than...
hi，the truncation value remove interference area，make the net better training.
> This error refers to code line 37: "from SiddonGpuPy import pySiddonGpu " from the ProjectorsModule.py file. I don't know how to resolve this issue. you can rebuild the SiddonGpuPy.cp36-win_amd64.pyd...
> hello, > > I want to download this model, but the url showed on the web is invalid. Can you share the current url again? > > Best Regards,...
you can use any one,but i suggest use focal_loss_sigmodv1 fucntion,you can use mixed loss,the param a is depent on your task,may be have try to decide the value,in general a...
> Hello, I'm looking forward to your reply~ thank you for your suggestion，i have converted tf code to pytorch，and using pytorch dataset load the dataset，you can find the pytorch project...
the number class is 7,but your is 8,there is different.
> 你可以修改这行代码 > prepare3dtraindata(pathlgg_list, bratslgg_path, trainImage, trainMask, (64, 128, 128), 3, 15, 2) > 把他修改为 > prepare3dtraindata(pathlgg_list, bratslgg_path, trainImage, trainMask, (64, 128, 128), 12, 60, 8) > 就可以解决这个问题 这是正解
> > > > > 你可以修改这行代码 > > > > > prepare3dtraindata(pathlgg_list, bratslgg_path, trainImage, trainMask, (64, 128, 128), 3, 15, 2) > > > > > 把他修改为 > > >...