RuntimeError:设备字符串开头应为cpu、cuda、mkldnn、opengl、opencl、ideep、hip、msnpu设备类型之一:0

Question

我正在尝试运行此代码https://github.com/AshwinRJ/Federated-Learning-PyTorch

我得到了错误RuntimeError:在设备字符串的开头应该是cpu，cuda，mkldnn，opengl，opencl，ideep，hip，msnpu设备类型之一: 0。如何解决这个问题。任何关于ecan的指南如何解决这些错误..请帮帮忙

import os
import copy
import time
import pickle
import numpy as np
from tqdm import tqdm
import torch
from tensorboardX import SummaryWriter

from options import args_parser
from update import LocalUpdate, test_inference
from models import MLP, CNNMnist, CNNFashion_Mnist, CNNCifar
from utils import get_dataset, average_weights, exp_details


if __name__ == '__main__':
    start_time = time.time()

    # define paths
    path_project = os.path.abspath('..')
    logger = SummaryWriter('../logs')

    args = args_parser()
    exp_details(args)

    if args.gpu:
        torch.cuda.set_device(args.gpu)
    device = 'cuda' if args.gpu else 'cpu'

    # load dataset and user groups
    train_dataset, test_dataset, user_groups = get_dataset(args)

    # BUILD MODEL
    if args.model == 'cnn':
        # Convolutional neural netork
        if args.dataset == 'mnist':
            global_model = CNNMnist(args=args)
        elif args.dataset == 'fmnist':
            global_model = CNNFashion_Mnist(args=args)
        elif args.dataset == 'cifar':
            global_model = CNNCifar(args=args)

    elif args.model == 'mlp':
        # Multi-layer preceptron
        img_size = train_dataset[0][0].shape
        len_in = 1
        for x in img_size:
            len_in *= x
            global_model = MLP(dim_in=len_in, dim_hidden=64,
                               dim_out=args.num_classes)
    else:
        exit('Error: unrecognized model')

    # Set the model to train and send it to device.
    global_model.to(device)
    global_model.train()
    print(global_model)

    # copy weights
    global_weights = global_model.state_dict()

    # Training
    train_loss, train_accuracy = [], []
    val_acc_list, net_list = [], []
    cv_loss, cv_acc = [], []
    print_every = 2
    val_loss_pre, counter = 0, 0

    for epoch in tqdm(range(args.epochs)):
        local_weights, local_losses = [], []
        print(f'\n | Global Training Round : {epoch+1} |\n')

        global_model.train()
        m = max(int(args.frac * args.num_users), 1)
        idxs_users = np.random.choice(range(args.num_users), m, replace=False)

        for idx in idxs_users:
            local_model = LocalUpdate(args=args, dataset=train_dataset,
                                      idxs=user_groups[idx], logger=logger)
            w, loss = local_model.update_weights(
                model=copy.deepcopy(global_model), global_round=epoch)
            local_weights.append(copy.deepcopy(w))
            local_losses.append(copy.deepcopy(loss))

        # update global weights
        global_weights = average_weights(local_weights)

        # update global weights
        global_model.load_state_dict(global_weights)

        loss_avg = sum(local_losses) / len(local_losses)
        train_loss.append(loss_avg)

        # Calculate avg training accuracy over all users at every epoch
        list_acc, list_loss = [], []
        global_model.eval()
        for c in range(args.num_users):
            local_model = LocalUpdate(args=args, dataset=train_dataset,
                                      idxs=user_groups[idx], logger=logger)
            acc, loss = local_model.inference(model=global_model)
            list_acc.append(acc)
            list_loss.append(loss)
        train_accuracy.append(sum(list_acc)/len(list_acc))

        # print global training loss after every 'i' rounds
        if (epoch+1) % print_every == 0:
            print(f' \nAvg Training Stats after {epoch+1} global rounds:')
            print(f'Training Loss : {np.mean(np.array(train_loss))}')
            print('Train Accuracy: {:.2f}% \n'.format(100*train_accuracy[-1]))

    # Test inference after completion of training
    test_acc, test_loss = test_inference(args, global_model, test_dataset)

    print(f' \n Results after {args.epochs} global rounds of training:')
    print("|---- Avg Train Accuracy: {:.2f}%".format(100*train_accuracy[-1]))
    print("|---- Test Accuracy: {:.2f}%".format(100*test_acc))

    # Saving the objects train_loss and train_accuracy:
    file_name = '../save/objects/{}_{}_{}_C[{}]_iid[{}]_E[{}]_B[{}].pkl'.\
        format(args.dataset, args.model, args.epochs, args.frac, args.iid,
               args.local_ep, args.local_bs)

    with open(file_name, 'wb') as f:
        pickle.dump([train_loss, train_accuracy], f)

    print('\n Total Run Time: {0:0.4f}'.format(time.time()-start_time))

    # PLOTTING (optional)
    # import matplotlib
    # import matplotlib.pyplot as plt
    # matplotlib.use('Agg')

    # Plot Loss curve
    # plt.figure()
    # plt.title('Training Loss vs Communication rounds')
    # plt.plot(range(len(train_loss)), train_loss, color='r')
    # plt.ylabel('Training loss')
    # plt.xlabel('Communication Rounds')
    # plt.savefig('../save/fed_{}_{}_{}_C[{}]_iid[{}]_E[{}]_B[{}]_loss.png'.
    #             format(args.dataset, args.model, args.epochs, args.frac,
    #                    args.iid, args.local_ep, args.local_bs))
    #
    # # Plot Average Accuracy vs Communication rounds
    # plt.figure()
    # plt.title('Average Accuracy vs Communication rounds')
    # plt.plot(range(len(train_accuracy)), train_accuracy, color='k')
    # plt.ylabel('Average Accuracy')
    # plt.xlabel('Communication Rounds')
    # plt.savefig('../save/fed_{}_{}_{}_C[{}]_iid[{}]_E[{}]_B[{}]_acc.png'.
    #             format(args.dataset, args.model, args.epochs, args.frac,
    #                    args.iid, args.local_ep, args.local_bs))

OUtput日志

Experimental details:
    Model     : cnn
    Optimizer : sgd
    Learning  : 0.01
    Global Rounds   : 10

    Federated parameters:
    IID
    Fraction of users  : 0.1
    Local Batch size   : 10
    Local Epochs       : 10

Traceback (most recent call last):
  File "src/federated_main.py", line 32, in <module>
    torch.cuda.set_device(args.gpu)
  File "C:\Users\S\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\cuda\__init__.py", line 298, in set_device
    device = _get_device_index(device)
  File "C:\Users\S\AppData\Local\Programs\Python\Python37\lib\site-packages\torch\cuda\_utils.py", line 20, in _get_device_index
    device = torch.device(device)
RuntimeError: Expected one of cpu, cuda, mkldnn, opengl, opencl, ideep, hip, msnpu device type at start of device string: 0
PS C:\Users\S\Downloads\Federated-Learning-PyTorch-master\Federated-Learning-PyTorch-master> 

Answer 1

如果您只使用单个gpu，请尝试更换

if args.gpu:
    torch.cuda.set_device(args.gpu)
device = 'cuda' if args.gpu else 'cpu'

使用

if torch.cuda.is_available():
    device = "cuda:0"
else:
    device = "cpu"

device = torch.device(device)

Answer 2

torch.cuda.set_device(args.gpu)

在上面的命令中，args.gpu可能是一个字符串，您需要将其转换为int，如下所示：

int(args.gpu)