图像识别代码添加cuda后跑不起来

Question

问题遇到的现象和发生背景

想问下为什么我添加了cuda后它还是跑不起来，提示我好像运算的时候同时用了cpu和gpu所以报错

问题相关代码，请勿粘贴截图

# -*- coding: utf-8 -*-
"""
Created on Fri Jul 22 10:26:33 2022
@author: Blucoris Liang
"""

import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision.transforms as transforms
import torchvision.datasets as datasets
import torchvision.models as models

EPOCH=1
BATCH_SIZE=40
LR=0.001

normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
                              std=[0.229, 0.224, 0.225])   

train_dataset = datasets.ImageFolder(
        'C:\\Users\\19544\\.spyder-py3\\leapGestRecog\\00',
        transforms.Compose([
                transforms.RandomResizedCrop(224),
                transforms.RandomHorizontalFlip(),
                transforms.ToTensor(),
                normalize,
                ]))

train_loader = Data.DataLoader(
        train_dataset,
        batch_size=BATCH_SIZE,
        shuffle=True)

test_loader = Data.DataLoader(
        datasets.ImageFolder(
                'C:\\Users\\19544\\.spyder-py3\\leapGestRecog\\03', 
                transforms.Compose([
                        transforms.Resize(256),
                        transforms.CenterCrop(224),
                        transforms.ToTensor(),
                        normalize,
                        ])),
        batch_size=BATCH_SIZE, shuffle=False,)

# 数据集长度
train_data_size = len(train_dataset)
print('训练集的长度为:{}'.format(train_data_size))



model = models.resnet18(pretrained=True)

################################
if torch.cuda.is_available():  #
    model = models.resnet18(pretrained=True).cuda()   #
################################



model.fc = torch.nn.Linear(in_features=512, out_features=10, bias=True)

fc_params = list(map(id, model.fc.parameters())) # map函数是将fc.parameters()的id返回并组成一个列表
base_params = filter(lambda p: id(p) not in fc_params, model.parameters()) # filter函数是将model.parameters()中地址不在fc.parameters的id中的滤出来
optimizer = torch.optim.SGD([ {'params': base_params}, {'params': model.fc.parameters(), 'lr': LR * 100}], lr=LR,)
loss_func=nn.CrossEntropyLoss()

################################
if torch.cuda.is_available():  #
    loss_func = loss_func.cuda()   #
################################


class AverageMeter(object):
    """Computes and stores the average and current value"""
    def __init__(self, name, fmt=':f'):
        self.name = name
        self.fmt = fmt
        self.reset()

    def reset(self):
        self.val = 0
        self.avg = 0
        self.sum = 0
        self.count = 0

    def update(self, val, n=1):
        self.val = val
        self.sum += val * n
        self.count += n
        self.avg = self.sum / self.count

    def __str__(self):
        fmtstr = '{name} {val' + self.fmt + '} ({avg' + self.fmt + '})'
        return fmtstr.format(**self.__dict__)
            
def accuracy(output, target, topk=(1,)):
    with torch.no_grad():
        maxk = max(topk)
        batch_size = target.size(0)

        _, pred = output.topk(maxk, 1, True, True)
        pred = pred.t()
        correct = pred.eq(target.view(1, -1).expand_as(pred))

        res = []
        for k in topk:
            correct_k = correct[:k].view(-1).float().sum(0, keepdim=True)
            res.append(correct_k.mul_(100.0 / batch_size))
        return res           
            
train_losses = AverageMeter('TrainLoss', ':.4e')
train_top1 = AverageMeter('TrainAccuracy', ':6.2f')
test_losses = AverageMeter('TestLoss', ':.4e')
test_top1 = AverageMeter('TestAccuracy', ':6.2f')

for epoch in range(EPOCH):
    
    model.train()
    for i,(images,target) in enumerate(train_loader):
        ################################
        if torch.cuda.is_available():  #
            images = images.cuda()         #
            target = target.cuda()   #
        ################################
        output=model(images)
        loss= loss_func(output,target)
        
        acc1, = accuracy(output, target, topk=(1,))
        train_losses.update(loss.item(), images.size(0))
        train_top1.update(acc1[0], images.size(0))

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
        print('Epoch[{}/{}],TrainLoss:{}, TrainAccuracy:{}'.format(epoch,EPOCH,train_losses.val, train_top1.val))
           
    model.eval()
    with torch.no_grad():
        for i,(images,target) in enumerate(test_loader):
            ################################
            if torch.cuda.is_available():  #
                images = images.cuda()         #
                target = target.cuda()   #
            ################################
            output=model(images)
            loss= loss_func(output,target)
            
            acc1, = accuracy(output, target, topk=(1,))
            test_losses.update(loss.item(), images.size(0))
            test_top1.update(acc1[0], images.size(0))
            
    print('TestLoss:{}, TestAccuracy:{}'.format(test_losses.avg, test_top1.avg))


import visdom

# 新建一个连接客户端
# 指定env = u'test1', 默认端口为8097，host是localhost
vis = visdom.Visdom(env = u'test1')
vis.line(X = train_top1.val , Y = train_losses.val)

运行结果及报错内容

runfile('C:/Users/19544/.spyder-py3/成功对手势识别用resnet进行了第一次训练.py', wdir='C:/Users/19544/.spyder-py3')
训练集的长度为:2000
Traceback (most recent call last):

  File "C:\Users\19544\.spyder-py3\成功对手势识别用resnet进行了第一次训练.py", line 126, in <module>
    output=model(images)

  File "D:\ANACONDA\envs\MyEnv\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)

  File "D:\ANACONDA\envs\MyEnv\lib\site-packages\torchvision\models\resnet.py", line 283, in forward
    return self._forward_impl(x)

  File "D:\ANACONDA\envs\MyEnv\lib\site-packages\torchvision\models\resnet.py", line 278, in _forward_impl
    x = self.fc(x)

  File "D:\ANACONDA\envs\MyEnv\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)

  File "D:\ANACONDA\envs\MyEnv\lib\site-packages\torch\nn\modules\linear.py", line 103, in forward
    return F.linear(input, self.weight, self.bias)

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument mat1 in method wrapper_addmm)

我的解答思路和尝试过的方法

我尝试过在几处补上了cuda项，可是还是没有成功

我想要达到的结果

希望用cuda跑起来。

Answer 1

Expected all tensors to be on the same device。
也就是说，有的data在cpu上，而有的在cuda上。通过观察代码可以发现你的model是cuda对象，但是model.fc却不是。第61行这里应该改成：model.fc = torch.nn.Linear(in_features=512, out_features=10, bias=True).cuda()