why I trained like 1.1 Train a face generator using the Celeb-A dataset can't be used in Vector Arithmetic about dcgan.torch

[soumith]

it can be used. what's the issue that you see?

[CCapellen]

Hello, I also trained the GAN using the Celeb-A dataset on the GPU. However arithmetic.lua does not work on the checkpoints generated doing this. (with the checkpoints, which I downloaded from the repository it worked.)
When I run net=checkpoints/experiment1_1_net_G.t7 gpu=0 qlua arithmetic.lua I get the following error:
table: 0x41a862a8
qlua: /home/catherine/torch/install/share/lua/5.1/torch/File.lua:343: unknown Torch class <torch.CudaTensor>
stack traceback:
[C]: at 0x7f7f513a0f50
[C]: in function 'error'
/home/catherine/torch/install/share/lua/5.1/torch/File.lua:343: in function 'readObject'
/home/catherine/torch/install/share/lua/5.1/torch/File.lua:369: in function 'readObject'
/home/catherine/torch/install/share/lua/5.1/nn/Module.lua:192: in function 'read'
/home/catherine/torch/install/share/lua/5.1/torch/File.lua:351: in function 'readObject'
/home/catherine/torch/install/share/lua/5.1/torch/File.lua:409: in function 'load'
arithmetic.lua:27: in main chunk
When I try to run it in gpu mode I get the same error. I tried to include require cunn and require cudnn at the beginning of arithmetic.lua, but then I get different errors. Thank you.