Winning Solution in NTIRE19 Challenges on Video Restoration and Enhancement (CVPR19 Workshops) - Video Restoration with Enhanced Deformable Convolutional Networks. EDVR has been merged into BasicSR and this repo is a mirror of BasicSR.
Hello,thanks for your greatful work and all open source files.
Sorry for bothering you that I have tried to retrain this model for learning, but I have encountered some problems during training. When I run the .sh for training, it always show the Runtime error of [RuntimeError: module must have its parameters and buffers on device cuda:0 (device_ids[0]) but found one of them on device: cuda:1].
it trained but had something wrong, so I change to train on one GPU. Could you tell me how to correct train on distributed GPU?
Hello,thanks for your greatful work and all open source files. Sorry for bothering you that I have tried to retrain this model for learning, but I have encountered some problems during training. When I run the .sh for training, it always show the Runtime error of [RuntimeError: module must have its parameters and buffers on device cuda:0 (device_ids[0]) but found one of them on device: cuda:1]. it trained but had something wrong, so I change to train on one GPU. Could you tell me how to correct train on distributed GPU?