Open DaehanKim-Korea opened 3 years ago
Yes, we can use multiple gpus during training (--gpu 0,1,3,...). For evaluation, we only use one gpu.
how to evaluate an image with a large size, such as 1920x1080 or 1280x720?
One commonly used way is to split the full images into image patches and then compose the generate patches to full images again. https://github.com/YapengTian/TDAN-VSR-CVPR-2020/blob/master/solver.py pls look at the chop_forward function.
Are multiple GPUs available?