报这个错，怎么修复

[gangxu822]

Attempting to deserialize object on CUDA device 3 but torch.cuda.device_count() is 1. Please use torch.load with map_location to map your storages to an existing device

[nononononno]

load权重的时候在在后面指定map_location='cuda:0'（类似torch.load(path, map_location='cuda:0'))