Error using vl_nnconv

[nh13871101238]

Hello:
I meet some problem when I using "trainOpts.gpus = [1] ;",the error like these:

" Error using vl_nnconv
DATA and FILTERS do not have compatible formats.

Error in dagnn.Conv/forward (line 11)
  outputs{1} = vl_nnconv(...

....."
if I using trainOpts.gpus = [],it worked, very strange
Looking for your help ,thanks!!!

[HLinn]

YOU should make the data have the same formats, when you use gpu , the data formats is gpuArray, you should change the inputs data to be gpuArray formats