Please use torch.load with map_location=torch.device(‘cpu‘），If you are running on a CPU-only machine

在CPU中运行GPU程序，出现以下问题

If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.

问题

RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.

出现以下错误

定位到19行

model_hyper.load_state_dict((torch.load('./koniq_pretrained.pkl')))

解决方案：

在模型加载时，指定 map_location='cpu' 即可，代码如下：

model_hyper.load_state_dict((torch.load('./koniq_pretrained.pkl',map_location='cpu')))