我在代码中稍作修改，以便不使用 default_app_config = 'streams.apps.StreamsConfig'
和DataParallel。代码如下：
DistributedDataParallel而且，当我在一组具有import argparse
import os
import shutil
import time
import torch
import torch.nn as nn
import torch.nn.parallel
import torch.backends.cudnn as cudnn
import torch.distributed as dist
import torch.optim
import torch.utils.data
import torch.utils.data.distributed
import torchvision.transforms as transforms
import torchvision.datasets as datasets
import torchvision.models as models
model_names = sorted(name for name in models.__dict__
if name.islower() and not name.startswith("__")
and callable(models.__dict__[name]))
parser = argparse.ArgumentParser(description='PyTorch ImageNet Training')
parser.add_argument('data', metavar='DIR',
help='path to dataset')
parser.add_argument('--arch', '-a', metavar='ARCH', default='resnet18',
choices=model_names,
help='model architecture: ' +
' | '.join(model_names) +
' (default: resnet18)')
parser.add_argument('-j', '--workers', default=4, type=int, metavar='N',
help='number of data loading workers (default: 4)')
parser.add_argument('--epochs', default=90, type=int, metavar='N',
help='number of total epochs to run')
parser.add_argument('--start-epoch', default=0, type=int, metavar='N',
help='manual epoch number (useful on restarts)')
parser.add_argument('-b', '--batch-size', default=256, type=int,
metavar='N', help='mini-batch size (default: 256)')
parser.add_argument('--lr', '--learning-rate', default=0.1, type=float,
metavar='LR', help='initial learning rate')
parser.add_argument('--momentum', default=0.9, type=float, metavar='M',
help='momentum')
parser.add_argument('--weight-decay', '--wd', default=1e-4, type=float,
metavar='W', help='weight decay (default: 1e-4)')
parser.add_argument('--print-freq', '-p', default=10, type=int,
metavar='N', help='print frequency (default: 10)')
parser.add_argument('--resume', default='', type=str, metavar='PATH',
help='path to latest checkpoint (default: none)')
parser.add_argument('-e', '--evaluate', dest='evaluate', action='store_true',
help='evaluate model on validation set')
parser.add_argument('--pretrained', dest='pretrained', action='store_true',
help='use pre-trained model')
parser.add_argument('--world-size', default=1, type=int,
help='number of distributed processes')
parser.add_argument('--dist-url', default='tcp://224.66.41.62:23456', type=str,
help='url used to set up distributed training')
parser.add_argument('--dist-backend', default='gloo', type=str,
help='distributed backend')
best_prec1 = 0
def main():
global args, best_prec1
args = parser.parse_args()
args.distributed = args.world_size > 1
if args.distributed:
dist.init_process_group(backend=args.dist_backend, init_method=args.dist_url,
world_size=args.world_size)
# create model
if args.pretrained:
print("=> using pre-trained model '{}'".format(args.arch))
model = models.__dict__[args.arch](pretrained=True)
else:
print("=> creating model '{}'".format(args.arch))
model = models.__dict__[args.arch]()
if not args.distributed:
if args.arch.startswith('alexnet') or args.arch.startswith('vgg'):
#model.features = torch.nn.DataParallel(model.features)
model.cuda()
#else:
#model = torch.nn.DataParallel(model).cuda()
else:
model.cuda()
#model = torch.nn.parallel.DistributedDataParallel(model)
# define loss function (criterion) and optimizer
criterion = nn.CrossEntropyLoss().cuda()
optimizer = torch.optim.SGD(model.parameters(), args.lr,
momentum=args.momentum,
weight_decay=args.weight_decay)
# optionally resume from a checkpoint
if args.resume:
if os.path.isfile(args.resume):
print("=> loading checkpoint '{}'".format(args.resume))
checkpoint = torch.load(args.resume)
args.start_epoch = checkpoint['epoch']
best_prec1 = checkpoint['best_prec1']
model.load_state_dict(checkpoint['state_dict'])
optimizer.load_state_dict(checkpoint['optimizer'])
print("=> loaded checkpoint '{}' (epoch {})"
.format(args.resume, checkpoint['epoch']))
else:
print("=> no checkpoint found at '{}'".format(args.resume))
cudnn.benchmark = True
# Data loading code
traindir = os.path.join(args.data, 'train')
valdir = os.path.join(args.data, 'val')
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
train_dataset = datasets.ImageFolder(
traindir,
transforms.Compose([
transforms.RandomSizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
normalize,
]))
if args.distributed:
train_sampler = torch.utils.data.distributed.DistributedSampler(train_dataset)
else:
train_sampler = None
train_loader = torch.utils.data.DataLoader(
train_dataset, batch_size=args.batch_size, shuffle=(train_sampler is None),
num_workers=args.workers, pin_memory=True, sampler=train_sampler)
val_loader = torch.utils.data.DataLoader(
datasets.ImageFolder(valdir, transforms.Compose([
transforms.Scale(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
normalize,
])),
batch_size=args.batch_size, shuffle=False,
num_workers=args.workers, pin_memory=True)
if args.evaluate:
validate(val_loader, model, criterion)
return
for epoch in range(args.start_epoch, args.epochs):
if args.distributed:
train_sampler.set_epoch(epoch)
adjust_learning_rate(optimizer, epoch)
# train for one epoch
train(train_loader, model, criterion, optimizer, epoch)
# evaluate on validation set
prec1 = validate(val_loader, model, criterion)
# remember best prec@1 and save checkpoint
is_best = prec1 > best_prec1
best_prec1 = max(prec1, best_prec1)
save_checkpoint({
'epoch': epoch + 1,
'arch': args.arch,
'state_dict': model.state_dict(),
'best_prec1': best_prec1,
'optimizer' : optimizer.state_dict(),
}, is_best)
def train(train_loader, model, criterion, optimizer, epoch):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
top1 = AverageMeter()
top5 = AverageMeter()
# switch to train mode
model.train()
end = time.time()
for i, (input, target) in enumerate(train_loader):
# measure data loading time
data_time.update(time.time() - end)
target = target.cuda(async=True)
input_var = torch.autograd.Variable(input)
target_var = torch.autograd.Variable(target)
# compute output
output = model(input_var)
loss = criterion(output, target_var)
# measure accuracy and record loss
prec1, prec5 = accuracy(output.data, target, topk=(1, 5))
losses.update(loss.data[0], input.size(0))
top1.update(prec1[0], input.size(0))
top5.update(prec5[0], input.size(0))
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
optimizer.step()
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % args.print_freq == 0:
print('Epoch: [{0}][{1}/{2}]\t'
'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
'Data {data_time.val:.3f} ({data_time.avg:.3f})\t'
'Loss {loss.val:.4f} ({loss.avg:.4f})\t'
'Prec@1 {top1.val:.3f} ({top1.avg:.3f})\t'
'Prec@5 {top5.val:.3f} ({top5.avg:.3f})'.format(
epoch, i, len(train_loader), batch_time=batch_time,
data_time=data_time, loss=losses, top1=top1, top5=top5))
def validate(val_loader, model, criterion):
batch_time = AverageMeter()
losses = AverageMeter()
top1 = AverageMeter()
top5 = AverageMeter()
# switch to evaluate mode
model.eval()
end = time.time()
for i, (input, target) in enumerate(val_loader):
target = target.cuda(async=True)
input_var = torch.autograd.Variable(input, volatile=True)
target_var = torch.autograd.Variable(target, volatile=True)
# compute output
output = model(input_var)
loss = criterion(output, target_var)
# measure accuracy and record loss
prec1, prec5 = accuracy(output.data, target, topk=(1, 5))
losses.update(loss.data[0], input.size(0))
top1.update(prec1[0], input.size(0))
top5.update(prec5[0], input.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % args.print_freq == 0:
print('Test: [{0}/{1}]\t'
'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
'Loss {loss.val:.4f} ({loss.avg:.4f})\t'
'Prec@1 {top1.val:.3f} ({top1.avg:.3f})\t'
'Prec@5 {top5.val:.3f} ({top5.avg:.3f})'.format(
i, len(val_loader), batch_time=batch_time, loss=losses,
top1=top1, top5=top5))
print(' * Prec@1 {top1.avg:.3f} Prec@5 {top5.avg:.3f}'
.format(top1=top1, top5=top5))
return top1.avg
def save_checkpoint(state, is_best, filename='checkpoint.pth.tar'):
torch.save(state, filename)
if is_best:
shutil.copyfile(filename, 'model_best.pth.tar')
class AverageMeter(object):
"""Computes and stores the average and current value"""
def __init__(self):
self.reset()
def reset(self):
self.val = 0
self.avg = 0
self.sum = 0
self.count = 0
def update(self, val, n=1):
self.val = val
self.sum += val * n
self.count += n
self.avg = self.sum / self.count
def adjust_learning_rate(optimizer, epoch):
"""Sets the learning rate to the initial LR decayed by 10 every 30 epochs"""
lr = args.lr * (0.1 ** (epoch // 30))
for param_group in optimizer.param_groups:
param_group['lr'] = lr
def accuracy(output, target, topk=(1,)):
"""Computes the precision@k for the specified values of k"""
maxk = max(topk)
batch_size = target.size(0)
_, pred = output.topk(maxk, 1, True, True)
pred = pred.t()
correct = pred.eq(target.view(1, -1).expand_as(pred))
res = []
for k in topk:
correct_k = correct[:k].view(-1).float().sum(0, keepdim=True)
res.append(correct_k.mul_(100.0 / batch_size))
return res
if __name__ == '__main__':
main()
神经网络架构的图像上运行此代码时，它会产生一个奇怪的cuda错误，如下所示：
alexnet用于运行代码的命令：=> creating model 'alexnet'
THCudaCheck FAIL file=/pytorch/torch/lib/THC/THCGeneral.c line=70 error=30 : unknown error
Traceback (most recent call last):
File "imagenet2.py", line 319, in <module>
main()
File "imagenet2.py", line 87, in main
model.cuda()
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 147, in cuda
return self._apply(lambda t: t.cuda(device_id))
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 118, in _apply
module._apply(fn)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 118, in _apply
module._apply(fn)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 118, in _apply
module._apply(fn)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 124, in _apply
param.data = fn(param.data)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 147, in <lambda>
return self._apply(lambda t: t.cuda(device_id))
File "/usr/local/lib/python2.7/dist-packages/torch/_utils.py", line 66, in _cuda
return new_type(self.size()).copy_(self, async)
File "/usr/local/lib/python2.7/dist-packages/torch/cuda/__init__.py", line 266, in _lazy_new
_lazy_init()
File "/usr/local/lib/python2.7/dist-packages/torch/cuda/__init__.py", line 85, in _lazy_init
torch._C._cuda_init()
RuntimeError: cuda runtime error (30) : unknown error at /pytorch/torch/lib/THC/THCGeneral.c:70
我哪里出错了？
PS：在AWS python imagenet.py --world-size 1 --arch 'alexnet' <image_folder> Ubuntu实例上运行。
CUDA版本如下：
g2.2xlarge答案 0 :(得分：1)
CUDNN提供无用的错误消息。对于调试，请使用net.cpu()在CPU上测试您的网络，或者只需删除net.cuda()。您必须对训练，验证和输出变量进行相同的操作。
接缝问题是你在尺寸不同于224x224的图像上使用了预先训练过的AlexNet。根据文档，它应该工作，只要图像大小至少224x224。
由于pytorch实施AlexNet中的硬编码参数，这可能是一个张量整形问题。在第44行的vision/torchvision/models/alexnet.py中，它说
x = x.view(x.size(0), 256 * 6 * 6)
将其更改为
x = x.view(x.size(0), -1)
这应该允许它使用不同的图像大小。