当两个相同的脚本同时在GPUpytorch DDP上运行时，会发生一些奇怪的ImportError / PermissionError

如何解决当两个相同的脚本同时在GPUpytorch DDP上运行时，会发生一些奇怪的ImportError / PermissionError

我有一个程序，该程序使用与pytorch一起使用分布式数据并行来执行muti-gpu并行性。 该脚本可以通过CUDA_VISIBLE_DEVICES=0,1 python ddp_test.py正确运行，但是问题是，当我尝试通过CUDA_VISIBLE_DEVICES=2,3 python ddp_test.py在同一节点上同时运行同一脚本时，我运行的第二个脚本将发生ImportError / PermissionError。>

这是一个最小的示例，ddp_test.py是一个小型培训程序，ddp_import.py和ddp_import_import.py是用来模拟我的真实培训程序的。

# ddp_test.py
import os
from datetime import datetime
import argparse
import torch.multiprocessing as mp
import torchvision
import torchvision.transforms as transforms
import torch
import torch.nn as nn
import torch.distributed as dist

from ddp_import import *

def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('-n','--nodes',default=1,type=int,metavar='N',help='number of data loading workers (default: 4)')
    parser.add_argument('-g','--gpus',default=2,help='number of gpus per node')
    parser.add_argument('-nr','--nr',default=0,help='ranking within the nodes')
    parser.add_argument('--epochs',default=50,help='number of total epochs to run')
    args = parser.parse_args()
    args.world_size = args.gpus * args.nodes
    os.environ['MASTER_ADDR'] = '127.0.0.1'
    os.environ['MASTER_PORT'] = '1234'
    mp.spawn(train,nprocs=args.gpus,args=(args,))


class ConvNet(nn.Module):
    def __init__(self,num_classes=10):
        super(ConvNet,self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(1,16,kernel_size=5,stride=1,padding=2),nn.BatchNorm2d(16),nn.ReLU(),nn.MaxPool2d(kernel_size=2,stride=2))
        self.layer2 = nn.Sequential(
            nn.Conv2d(16,32,nn.BatchNorm2d(32),stride=2))
        self.fc = nn.Linear(7*7*32,num_classes)

    def forward(self,x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.reshape(out.size(0),-1)
        out = self.fc(out)
        return out


def train(gpu,args):
    rank = args.nr * args.gpus + gpu
    dist.init_process_group(backend='nccl',init_method='env://',world_size=args.world_size,rank=rank)
    torch.manual_seed(0)
    model = ConvNet()
    print("rank:{} gpu:{}".format(rank,gpu))
    torch.cuda.set_device(gpu)  
    model.cuda(gpu)
    batch_size = 20
    # define loss function (criterion) and optimizer
    criterion = nn.CrossEntropyLoss().cuda(gpu)
    optimizer = torch.optim.SGD(model.parameters(),1e-4)
    # Wrap the model
    model = nn.parallel.DistributedDataParallel(model,device_ids=[gpu])
    # Data loading code
    train_dataset = torchvision.datasets.MNIST(root='./data',train=True,transform=transforms.ToTensor(),download=True)
    train_sampler = torch.utils.data.distributed.DistributedSampler(train_dataset,num_replicas=args.world_size,rank=rank)
    train_loader = torch.utils.data.DataLoader(dataset=train_dataset,batch_size=batch_size,shuffle=False,num_workers=0,pin_memory=True,sampler=train_sampler)

    start = datetime.now()
    total_step = len(train_loader)
    for epoch in range(args.epochs):
        for i,(images,labels) in enumerate(train_loader):
            images = images.cuda(non_blocking=True)
            labels = labels.cuda(non_blocking=True)
            # Forward pass
            outputs = model(images)
            loss = criterion(outputs,labels)

            # Backward and optimize
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
            if (i + 1) % 100 == 0 and gpu == 0:
                print('Epoch [{}/{}],Step [{}/{}],Loss: {:.4f}'.format(epoch + 1,args.epochs,i + 1,total_step,loss.item()))
    if gpu == 0:
        print("Training complete in: " + str(datetime.now() - start))


if __name__ == '__main__':
    main()

# ddp_import.py
from ddp_import_import import *

# ddp_import_import.py
import nltk
from pycocotools.coco import COCO

当我通过CUDA_VISIBLE_DEVICES=0,1 python ddp_test.py运行脚本时，脚本可以正常工作。但是，如果同时运行两个此脚本，一个运行CUDA_VISIBLE_DEVICES=0,1 python ddp_test.py，另一个运行CUDA_VISIBLE_DEVICES=2,3 python ddp_test.py（节点上有4 gpu），则会发生错误。 PermissionError，有时是ImportError。

我是ddp的新手，这个问题使我困惑了好几天。谁能告诉我问题出在哪里以及如何解决。非常感谢！