错误：运行时错误：在当前进程完成引导阶段之前尝试启动新进程

Question

运行以下脚本后出现错误：

--编码：utf-8--

导入东西

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils import data
from torch.utils.data import DataLoader
import torchvision.transforms as transforms

import cv2

import numpy as np

import csv

Step1：从日志文件中读取

samples = []
with open('data/driving_log.csv') as csvfile:
    reader = csv.reader(csvfile)
    next(reader, None)
    for line in reader:
        samples.append(line)
    

Step2：将数据分为训练集和验证集

train_len = int(0.8*len(samples))
valid_len = len(samples) - train_len
train_samples, validation_samples = data.random_split(samples, lengths=[train_len, valid_len])

Step3a：定义数据加载器的增强、转换过程、参数和数据集

def augment(imgName, angle):
  name = 'data/IMG/' + imgName.split('/')[-1]
  current_image = cv2.imread(name)
  current_image = current_image[65:-25, :, :]
  if np.random.rand() < 0.5:
    current_image = cv2.flip(current_image, 1)
    angle = angle * -1.0  
  return current_image, angle

class Dataset(data.Dataset):

    def __init__(self, samples, transform=None):

        self.samples = samples
        self.transform = transform

    def __getitem__(self, index):
      
        batch_samples = self.samples[index]
        
        steering_angle = float(batch_samples[3])
        
        center_img, steering_angle_center = augment(batch_samples[0], steering_angle)
        left_img, steering_angle_left = augment(batch_samples[1], steering_angle + 0.4)
        right_img, steering_angle_right = augment(batch_samples[2], steering_angle - 0.4)

        center_img = self.transform(center_img)
        left_img = self.transform(left_img)
        right_img = self.transform(right_img)

        return (center_img, steering_angle_center), (left_img, steering_angle_left), (right_img, steering_angle_right)
      
    def __len__(self):
        return len(self.samples)

Step3b：使用数据加载器创建生成器以并行化进程

def _my_normalization(x):
    return x/255.0 - 0.5
transformations = transforms.Compose([transforms.Lambda(_my_normalization)])

params = {'batch_size': 32,
          'shuffle': True,
          'num_workers': 4}

training_set = Dataset(train_samples, transformations)
training_generator = data.DataLoader(training_set, **params)

validation_set = Dataset(validation_samples, transformations)
validation_generator = data.DataLoader(validation_set, **params)

第四步：定义网络

class NetworkDense(nn.Module):

    def __init__(self):
        super(NetworkDense, self).__init__()
        self.conv_layers = nn.Sequential(
            nn.Conv2d(3, 24, 5, stride=2),
            nn.ELU(),
            nn.Conv2d(24, 36, 5, stride=2),
            nn.ELU(),
            nn.Conv2d(36, 48, 5, stride=2),
            nn.ELU(),
            nn.Conv2d(48, 64, 3),
            nn.ELU(),
            nn.Conv2d(64, 64, 3),
            nn.Dropout(0.25)
        )
        self.linear_layers = nn.Sequential(
            nn.Linear(in_features=64 * 2 * 33, out_features=100),
            nn.ELU(),
            nn.Linear(in_features=100, out_features=50),
            nn.ELU(),
            nn.Linear(in_features=50, out_features=10),
            nn.Linear(in_features=10, out_features=1)
        )
        
    def forward(self, input):  
        input = input.view(input.size(0), 3, 70, 320)
        output = self.conv_layers(input)
        output = output.view(output.size(0), -1)
        output = self.linear_layers(output)
        return output


class NetworkLight(nn.Module):

    def __init__(self):
        super(NetworkLight, self).__init__()
        self.conv_layers = nn.Sequential(
            nn.Conv2d(3, 24, 3, stride=2),
            nn.ELU(),
            nn.Conv2d(24, 48, 3, stride=2),
            nn.MaxPool2d(4, stride=4),
            nn.Dropout(p=0.25)
        )
        self.linear_layers = nn.Sequential(
            nn.Linear(in_features=48*4*19, out_features=50),
            nn.ELU(),
            nn.Linear(in_features=50, out_features=10),
            nn.Linear(in_features=10, out_features=1)
        )
        

    def forward(self, input):
        input = input.view(input.size(0), 3, 70, 320)
        output = self.conv_layers(input)
        output = output.view(output.size(0), -1)
        output = self.linear_layers(output)
        return output

Step5：定义优化器

model = NetworkLight()
optimizer = optim.Adam(model.parameters(), lr=0.0001)

criterion = nn.MSELoss()

第 6 步：检查设备并定义将张量移动到该设备的函数

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print('device is: ', device)

def toDevice(datas, device):
  
  imgs, angles = datas
  return imgs.float().to(device), angles.float().to(device)

第 7 步：根据定义的最大历元训练和验证网络

max_epochs = 22

for epoch in range(max_epochs):
    
    model.to(device)
    
    # Training
    train_loss = 0
    model.train()
    for local_batch, (centers, lefts, rights) in enumerate(training_generator):
        # Transfer to GPU
        centers, lefts, rights = toDevice(centers, device), toDevice(lefts, device), toDevice(rights, device)
        
        # Model computations
        optimizer.zero_grad()
        datas = [centers, lefts, rights]        
        for data in datas:
            imgs, angles = data
#             print("training image: ", imgs.shape)
            outputs = model(imgs)
            loss = criterion(outputs, angles.unsqueeze(1))
            loss.backward()
            optimizer.step()

            train_loss += loss.data[0].item()
            
        if local_batch % 100 == 0:
            print('Loss: %.3f '
                 % (train_loss/(local_batch+1)))

    
    # Validation
    model.eval()
    valid_loss = 0
    with torch.set_grad_enabled(False):
        for local_batch, (centers, lefts, rights) in enumerate(validation_generator):
            # Transfer to GPU
            centers, lefts, rights = toDevice(centers, device), toDevice(lefts, device), toDevice(rights, device)
        
            # Model computations
            optimizer.zero_grad()
            datas = [centers, lefts, rights]        
            for data in datas:
                imgs, angles = data
#                 print("Validation image: ", imgs.shape)
                outputs = model(imgs)
                loss = criterion(outputs, angles.unsqueeze(1))
                
                valid_loss += loss.data[0].item()

            if local_batch % 100 == 0:
                print('Valid Loss: %.3f '
                     % (valid_loss/(local_batch+1)))

Step8：定义状态并将模型保存到状态

state = {
        'model': model.module if device == 'cuda' else model,
        }

torch.save(state, 'model.h5')

这是错误消息：

“D:\VICO\Back up\venv\Scripts\python.exe” “D:/VICO/Back up/venv/Scripts/self_driven_car.py” 设备是： cpu 设备是： cpu 回溯（最近一次调用）：文件“”，第 1 行，文件“C:\Users\isonata\AppData\Local\Programs\Python\Python37\lib\multiprocessing\spawn.py”，第 105 行，spawn_main exitcode = _main(fd) 文件“C :\Users\isonata\AppData\Local\Programs\Python\Python37\lib\multiprocessing\spawn.py”，第 114 行，在 _main 准备（preparation_data）文件“C:\Users\isonata\AppData\Local\Programs\Python \Python37\lib\multiprocessing\spawn.py”，第 225 行，在准备 _fixup_main_from_path(data['init_main_from_path']) 文件“C:\Users\isonata\AppData\Local\Programs\Python\Python37\lib\multiprocessing\spawn .py”，第 277 行，在 _fixup_main_from_path run_name=" mp_main ") 文件“C:\Users\isonata\AppData\Local\Programs\Python\Python37\lib\runpy.py”，第 263 行，在 run_path Traceback 中（最新最后调用）：文件“D:/VICO/Back up/venv/Scripts/self_driven_car.py”，第 165 行，在 pkg_name=pkg_name, script_name=fname 中） 文件“C:\Users\isonata\AppData\Local\Programs\ Python\Python37\lib\runpy.py”，第 96 行，local_batch 的 _run_module_code 中，枚举（training_generator）中的（中心、左、右）：文件“D:\VICO\Back up\venv\lib\site-packages\ torch\utils\data\dataloader.py”，第 291 行，在iter mod_name、mod_spec、pkg_name、script_name 中） 文件“C:\Users\isonata\AppData\Local\Programs\Python\Python37\lib\runpy.py”，第 85 行，在 _run_code exec(code, run_globals) 文件“D:\VICO\Back up\venv\Scripts\self_driven_car.py”中，第 165 行，返回 _MultiProcessingDataLoaderIter(self) 文件“D:\VICO\Back up\venv” \lib\site-packages\torch\utils\data\dataloader.py”，第 737 行，在local_batch 的init中 ，枚举（training_generator）中的（中心、左、右）：文件“D:\VICO\Back up\venv \lib\site-packages\torch\utils\data\dataloader.py”，第 291 行，在iter 中 返回 _MultiProcessingDataLoaderIter(self) 文件“D:\VICO\Back up\venv\lib\site-packages\torch\utils\ data\dataloader.py”，第 737 行，在init w.start() 文件“C:\Users\isonata\AppData\Local\Programs\Python\Python37\lib\multiprocessing\process.py”，第 112 行，在 start 中self._popen = self._Popen(self) 文件“C:\Users\isonata\AppData\Local\Programs\Python\Python37\lib\multiprocessing\context.py”，第 223 行，在 _Popen w.start() 文件中“ C:\Users\isonata\AppData\Local\Programs\Python\Python37\lib\multiprocessing\process.py”，第 112 行，在开始返回 _default_context.get_context().Process._Popen(process_obj) 文件“C:\Users \isonata\AppData\Local\Programs\Python\Python37\lib\multiprocessing\context.py”，第 322 行，在 _Popen self._popen = self._Popen(self) 文件“C:\Users\isonata\AppData\Local\Programs\Python\Python37\lib\multiprocessing\context.py”，第 223 行，在 _Popen 返回 Popen(process_obj) 文件“C:\Users\isonata\AppData\Local\Programs\Python \Python37\lib\multiprocessing\popen_spawn_win32.py”，第 89 行，在init return _default_context.get_context().Process._Popen(process_obj) 文件“C:\Users\isonata\AppData\Local\Programs\Python\Python37\lib\multiprocessing\context.py”，第 322 行，在 _Popenduction.dump (process_obj, to_child) 文件“C:\Users\isonata\AppData\Local\Programs\Python\Python37\lib\multiprocessing\reduction.py”，第 60 行，在转储中返回 Popen(process_obj) 文件“C:\Users\ isonata\AppData\Local\Programs\Python\Python37\lib\multiprocessing\popen_spawn_win32.py"，第 46 行，在init ForkingPickler(file, protocol).dump(obj) BrokenPipeError: [Errno 32] 损坏的管道 prep_data = spawn.get_preparation_data (process_obj._name) 文件“C:\Users\isonata\AppData\Local\Programs\Python\Python37\lib\multiprocessing\spawn.py”，第 143 行，在 get_preparation_data _check_not_importing_main() 文件“C:\Users\isonata\ AppData\Local\Programs\Python\Python37\lib\multiprocessing\spawn.py"，第 136 行，在 _check_not_importing_main 中不会被冻结以生成可执行文件。''') RuntimeError: 已尝试启动新的当前进程完成其引导阶段之前的进程。

    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.

进程已完成，退出代码为 1

我不确定解决问题的下一步

Answer 1

解决了，简单来说：

if __name__ == "__main__":
        main()

避免每次循环都重新加载模块。

Answer 2

我遇到了类似的问题，并通过将 DataLoader 中的“num_workers”参数设置回零来修复它：

DataLoader(num_workers=0)