How can I train with multi-input like (A1 ,A2……)->B?

[kuhhg]

How can I train with multi-input like (A1 ,A2)->B? I used to try torch.cat to conbine (A1,A2,,A3,A4) but it would change the channel into 4 and get an error.
When I try to change the input_nc =1 and output_nc =4, the error told me assert(opt.input_nc == opt.output_nc).
So, how can I use more then 2 input into the train?

[prabathbr]

you need to disable identity_loss when using different input & output channel numbers as per paper