Windows 10上使用pytorch进行多处理错误

时间:2018-02-27 16:39:32

标签: python windows multiprocessing pytorch

当我尝试执行我的代码时出现以下错误,这清楚地显示了多处理错误:

An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.

在Linux上,以下代码运行正常,但我想知道为什么我无法在Windows 10上运行它。但是,这里是代码:

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.autograd import Variable

kwargs = {'num_workers': 1, 'pin_memory': True}
train_data = torch.utils.data.DataLoader(datasets.MNIST('data', train=True,                 download=True,
                                            transform=transforms.Compose([transforms.ToTensor,
                                                            transforms.Normalize((0.1307,), (0.3081,))])),
                                 batch_size=64, shuffle=True, **kwargs)

test_data = torch.utils.data.DataLoader(datasets.MNIST('data', train=False,
                                                transform=transforms.Compose([transforms.ToTensor,
                                                            transforms.Normalize((0.1307,), (0.3081,))])),
                                 batch_size=64, shuffle=True, **kwargs)



class Netz(nn.Module):
    def __init__(self):
        super(Netz, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv_dropout = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 60)
        self.fc2 = nn.Linear(60, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = F.max_pool2d(x, 2)
        x = F.relu(x)
        x = self.conv2(x)
        x = self.conv_dropout(x)
        x = F.max_pool2d(x, 2)
        x = F.relu(x)
        print(x.size())
        exit()


model = Netz()
model.cuda()

optimizer = optim.SGD(model.parameters(), lr=0.1, momentum=0.8)


def train(epoch):
    model.train()
    for batch_id, (data, target) in enumerate(train_data):
        data = data.cuda()
        target = target.cuda()
        data = Variable(data)
        target = Variable(target)
        optimizer.zero_grad()
        out = model(data)
        criterion = F.nll_loss
        loss = criterion(out, target)
        loss.backward()
        optimizer.step()
        print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(epoch, batch_id * len(data), len(train_data.dataset),
                                                                   100. * batch_id / len(train_data), loss.data[0]))

for epoch in range(1, 30):
    print(epoch)
    train(epoch)

我尝试用以下方法修复它:

if __name__ == '__main__':
    for epoch in range(1, 30):
        train(epoch)

但也没有成功。 任何人都知道如何解决这个多处理错误? 任何帮助,将不胜感激。 (是的,我知道pytorch没有正式发布用于Windows,但我不认为这会导致错误。)

谢谢!

2 个答案:

答案 0 :(得分:3)

我自己发现了。

如果名称 =='主要',我必须将整个代码放入:

此外,我最后忘记了变换中的刹车.ToTensor部分。

答案 1 :(得分:-1)

也许 num_workers = 0 可以解决。