解决pytorch多GPU训练保存的模型,在单GPU环境下加载出错问题

from collections import OrderedDict
def myOwnLoad(model, check):
  modelState = model.state_dict()
  tempState = OrderedDict()
  for i in range(len(check.keys())-2):
    print modelState.keys()[i], check.keys()[i]
    tempState[modelState.keys()[i]] = check[check.keys()[i]]
  temp = [[0.02]*1024 for i in range(200)] # mean=0, std=0.02
  tempState['myFc.weight'] = torch.normal(mean=0, std=torch.FloatTensor(temp)).cuda()
  tempState['myFc.bias']  = torch.normal(mean=0, std=torch.FloatTensor([0]*200)).cuda()

  model.load_state_dict(tempState)
  return model

gpu_ids = [0, 1, 2, 3]
device = t.device("cuda:0" if t.cuda.is_available() else "cpu") # 只能单GPU运行
net = LeNet()
if len(gpu_ids) > 1:
  net = nn.DataParallel(net, device_ids=gpu_ids)
net = net.to(device)

DataParallel(
 (module): LeNet(
  (conv1): Conv2d(3, 6, kernel_size=(5, 5), stride=(1, 1))
  (conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
  (fc1): Linear(in_features=400, out_features=120, bias=True)
  (fc2): Linear(in_features=120, out_features=84, bias=True)
  (fc3): Linear(in_features=84, out_features=10, bias=True)
 )
)

LeNet(
 (conv1): Conv2d(3, 6, kernel_size=(5, 5), stride=(1, 1))
 (conv2): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
 (fc1): Linear(in_features=400, out_features=120, bias=True)
 (fc2): Linear(in_features=120, out_features=84, bias=True)
 (fc3): Linear(in_features=84, out_features=10, bias=True)
)

if len(gpu_ids) > 1:
  t.save(net.module.state_dict(), "model.pth")
else:
  t.save(net.state_dict(), "model.pth")