pytorch使用cuda出错RuntimeError: Expected object of backend CUDA but got backend CPU for argument

第一种情况：
数据集忘记转成cuda模式提示RuntimeError: Expected object of backend CUDA but got backend CPU for argument

device = torch.cuda('cuda:0')
net = MLP()
net = net.to(device)
data = data.to(device) #而不是直接data.to(device)
target = target.cuda()
logits = net(data).cuda()

第二种情况：提示CUDA: invalid device ordinal
可能是你的显卡序列号不对，显卡是从0开始算的，或者你的显卡不支持cuda，例如1050Ti就不支持cuda（很难受。。。）
这里是cuda的支持情况列表官网
https://developer.nvidia.com/cuda-gpus#compute
以下代码可以查看你的GPU

import pycuda
from pycuda import compiler
import pycuda.driver as drv

drv.init()
print("%d device(s) found." % drv.Device.count())
           
for ordinal in range(drv.Device.count()):
    dev = drv.Device(ordinal)
    print (ordinal, dev.name())

安装pycuda可能碰到的问题“failed building wheel for pycuda”，解决办法：
https://www.cnblogs.com/harvey888/p/5467276.html

本人使用cuda测试MNIST数据集的完整代码如下：

import  torch
import  torch.nn as nn
import  torch.nn.functional as F
import  torch.optim as optim
from    torchvision import datasets, transforms
batch_size=200
learning_rate=0.01
epochs=10

train_loader = torch.utils.data.DataLoader(
    datasets.MNIST('../data', train=True, download=True,
                   transform=transforms.Compose([
                       transforms.ToTensor(),
                       transforms.Normalize((0.1307,), (0.3081,))
                   ])),
    batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(
    datasets.MNIST('../data', train=False, transform=transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize((0.1307,), (0.3081,))
    ])),
    batch_size=batch_size, shuffle=True)



class MLP(nn.Module):

    def __init__(self):
        super(MLP, self).__init__()
        
        self.model = nn.Sequential(
            nn.Linear(784, 200),
            nn.ReLU(inplace=True),
            nn.Linear(200, 200),
            nn.ReLU(inplace=True),
            nn.Linear(200, 10),
            nn.ReLU(inplace=True),
        )

    def forward(self, x):
        x = self.model(x)

        return x
device = torch.device('cuda:0')

net = MLP()
net = net.to(device)
optimizer = optim.SGD(net.parameters(), lr=learning_rate)
criteon = nn.CrossEntropyLoss().to(device)

for epoch in range(epochs):

    for batch_idx, (data, target) in enumerate(train_loader):
        data = data.view(-1, 28*28)
        data, target = data.to(device), target.cuda()
        logits = net(data)
        loss = criteon(logits, target)

        optimizer.zero_grad()
        loss.backward()
        # print(w1.grad.norm(), w2.grad.norm())
        optimizer.step()

        if batch_idx % 100 == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                       100. * batch_idx / len(train_loader), loss.item()))


    test_loss = 0
    correct = 0
    for data, target in test_loader:
        data = data.view(-1, 28 * 28)
        data = data.to(device)
        target = target.cuda()
        logits = net(data)
        test_loss += criteon(logits, target).item()
        
        pred = logits.data.max(1)[1]
        correct += pred.eq(target.data).sum()

    test_loss /= len(test_loader.dataset)
    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))
    #结束