Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are

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. 这个错误通常出现在使用CPU加载CUDA训练的模型时。这是因为模型是在CUDA设备上训练的，而在CPU上加载时需要使用map_location参数将模型映射到CPU上。解决方法是在加载模型时加上map_location='cpu'参数。例如：weights = torch.load('model.pt', map_location='cpu')。如果你的机器支持CUDA，也可以将模型加载到CUDA设备上，例如：device = torch.device('cuda')，weights = torch.load('model.pt', map_location=device)。相关问题：