PyTorch 教程 freeze_support() 问题

Question

我尝试按照 PyTorch 中的教程进行操作： https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html#sphx-glr-beginner-blitz-cifar10-tutorial-py 。

完整代码在这里：

import torch
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import numpy as np
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim


# Loading and normalizing CIFAR10
transform = transforms.Compose(
    [transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,
                                          shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4,
                                         shuffle=False, num_workers=2)

classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')


# Shows training images, DOESN'T WORK

def imshow(img):
    img = img / 2 + 0.5     # unnormalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()


# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()

# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))


# define a convolutional neural network
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x


net = Net()

# Define a loss function and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

# Train the network
for epoch in range(2):  # loop over the dataset multiple times

    running_loss = 0.0
    
    # DOESN'T WORK
    for i, data in enumerate(trainloader, 0):
        # get the inputs; data is a list of [inputs, labels]
        inputs, labels = data

        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.item()
        if i % 2000 == 1999:    # print every 2000 mini-batches
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

print('Finished Training')


# save trained model
PATH = './cifar_net.pth'
torch.save(net.state_dict(), PATH)

# test the network on the test data
dataiter = iter(testloader)
images, labels = dataiter.next()

# print images
dataiter = iter(testloader)
images, labels = dataiter.next()
imshow(torchvision.utils.make_grid(images))
print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))


# load back saved model
net = Net()
net.load_state_dict(torch.load(PATH))

# see what the nueral network thinks these examples above are:
ouputs = net(images)

# index of the highest energy
_, predicted = torch.max(outputs, 1)

print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
                              for j in range(4)))

# accuracy on the whole dataset
correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: %d %%' % (
    100 * correct / total))

# classes that perfomed well vs classes that didn't perform well
class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
with torch.no_grad():
    for data in testloader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs, 1)
        c = (predicted == labels).squeeze()
        for i in range(4):
            label = labels[i]
            class_correct[label] += c[i].item()
            class_total[label] += 1


for i in range(10):
    print('Accuracy of %5s : %2d %%' % (
        classes[i], 100 * class_correct[i] / class_total[i]))


if __name__ == '__main__':
    torch.multiprocessing.freeze_support()

但是我遇到了这个问题：

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

        This probably means that you are not using fork to start your
        child processes and you have forgotten to use the proper idiom
        in the main module:

            if __name__ == '__main__':
                freeze_support()
                ...

        The "freeze_support()" line can be omitted if the program
        is not going to be frozen to produce an executable.

我只是想在常规 python 文件中运行它。 当我添加

if __name__ == '__main__':
                freeze_support()

到我的文件末尾，我仍然收到错误。

Answer 1

只需将训练和测试DataLoader的num_workers参数设置为等于0 。 在代码中只需这样做：

trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,
                                          shuffle=True, num_workers=0)

testloader = torch.utils.data.DataLoader(testset, batch_size=4,
                                         shuffle=False, num_workers=0)

Answer 2

对于遇到此问题的其他任何人，我相信您需要定义一个主要功能并在那里运行培训。 然后加：

if __name__ == '__main__':
    main()

在python文件的末尾。

这为我在不同的 PyTorch 培训计划中解决了 freeze_support() 问题。

Answer 3

以下为我工作：

1. 使用 spawn start 方法

import torch.multiprocessing as mp

mp.use_start_method('spawn', force=True)

force 是必不可少的，因为它返回了另一个上下文已经设置的错误

2. 甚至在导入之前的第一行使用 main 函数（ if __name__ == '__main__': ）（stackoverflow 上的许多答案表明 start() 和 join() 方法应该在 main 中并且它运行良好。但我想我我正在使用多个脚本和模块，因此它无法识别正确的 main，因此我不得不将其包含在第一个文件的第一行中）。

Answer 4

在 MacOS 上，M1 mac mini，火炬版本 1.13.1，在脚本顶部添加这个对我有用，没有定义main ：

# after `import torch`:    

import torch.multiprocessing as mp

mp.set_start_method('fork', force=True)