Multi-GPU training for the illumination-aware fusion network

[LiYunJamesPhD]

Hi,

It is a great work, and thanks for releasing a PyTorch version of your work. I have a quick question for the illumination-aware fusion network training for my own dataset. When I run the training, I have an out of coda memory error. I check your code, and it seems like you do not use multiple GPUs for the model training. Is it correct? If so, does this current implementation support multi-GPU training?

Thanks, Li-Yun