遇到一个错误：

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='cpu' to map your storages to the CPU.
出错语句：

torch.load(model_file)
改为：

model = torch.load(model_path, map_location='cpu')
 

多个ＧＰＵ训练的，

参考：

＜https://blog.csdn.net/iamjingong/article/details/85308600＞