pytorch分布式训练（一）
pytorch分布式-初始化：
pytorch分布式-DistributedDataParallel
pytorch分布式训练（四Sampler介绍）
pytorch分布式训练（五DataLoader）
torch.utils.data.DataLoader()样例：
"""
批训练，把数据变成一小批一小批数据进行训练。
DataLoader就是用来包装所使用的数据，每次抛出一批数据
"""
import torch
import torch.utils.data as Data
BATCH_SIZE = 5
x = torch.linspace(1, 10, 10)
y = torch.linspace(10, 1, 10)
# 把数据放在数据库中
torch_dataset = Data.TensorDataset(x, y)
loader = Data.DataLoader(
# 从数据库中每次抽出batch size个样本
dataset=torch_dataset,
batch_size=BATCH_SIZE,
shuffle=True,
num_workers=2,
)
def show_batch():
for epoch in range(3):
for step, (batch_x, batch_y) in enumerate(loader):
# training
print("steop:{}, batch_x:{}, batch_y:{}".format(step, batch_x, batch_y))
if __name__ == '__main__':
show_batch()
一、 nn.DataParallel
DataParallel 可以帮助我们（使用单进程控）将模型和数据加载到多个 GPU 中，控制数据在 GPU 之间的流动，协同不同 GPU 上的模型进行并行训练（细粒度的方法有 scatter，gather 等等）。
model = nn.DataParallel(model.cuda(), device_ids=gpus, output_device=gpus[0])
DataParallel 使用起来非常方便，我们只需要用 DataParallel 包装模型，再设置一些参数即可。需要定义的参数包括：参与训练的 GPU 有哪些，device_ids=gpus；用于汇总梯度的 GPU 是哪个，output_device=gpus[0] 。DataParallel 会自动帮我们将数据切分 load 到相应 GPU，将模型复制到相应 GPU，进行正向传播计算梯度并汇总：
二、 torch.distributed
与 DataParallel 的单进程控制多 GPU 不同，在 distributed 的帮助下，我们只需要编写一份代码，torch 就会自动将其分配给 [n] 个进程，分别在 [n] 个 GPU 上运行。
在 API 层面，pytorch 为我们提供了 torch.distributed.launch 启动器，用于在命令行分布式地执行 python 文件。在执行过程中，启动器会将当前进程的（其实就是 GPU的）index 通过参数传递给 python，我们可以这样获得当前进程的 index：
parser = argparse.ArgumentParser()
parser.add_argument('--local_rank', default=-1, type=int,
help='node rank for distributed training')
args = parser.parse_args()
print(args.local_rank)
接着，使用 init_process_group 设置GPU 之间通信使用的后端和端口：
dist.init_process_group(backend='nccl')
之后，使用 DistributedSampler 对数据集进行划分。如此前我们介绍的那样，它能帮助我们将每个 batch 划分成几个 partition，在当前进程中只需要获取和 rank 对应的那个 partition 进行训练:
train_sampler = torch.utils.data.distributed.DistributedSampler(train_dataset)
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=..., sampler=train_sampler)
然后，使用 DistributedDataParallel 包装模型，它能帮助我们为不同 GPU 上求得的梯度进行 all reduce（即汇总不同 GPU 计算所得的梯度，并同步计算结果）。all reduce 后不同 GPU 中模型的梯度均为 all reduce 之前各 GPU 梯度的均值：
model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[args.local_rank])
在使用时，调用 torch.distributed.launch 启动器启动：
CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 main.py
当然可以使用pycharm进行配置：
三、 torch.multiprocessing 取代启动器
使用时，只需要调用 torch.multiprocessing.spawn，torch.multiprocessing 就会帮助我们自动创建进程。如下面的代码所示，spawn 开启了 nprocs=4 个线程，每个线程执行 main_worker 并向其中传入 local_rank（当前进程 index）和 args（即 4 和 myargs）作为参数：
import torch.multiprocessing as mp
mp.spawn(main_worker, nprocs=4, args=(4, myargs))
#需要注意的是，mp.spawn所在文件中的全局变量的id变化：解决办法将所有变量定义在main_worker（）函数中。
#以上限制部分应用，如MC，其它则不影响。
这里，我们直接将原本需要 torch.distributed.launch 管理的执行内容，封装进 main_worker 函数中，其中 proc 对应 local_rank（当前进程 index），ngpus_per_node 对应 4， args 对应 myargs：
def main_worker(proc, ngpus_per_node, args):
dist.init_process_group(backend='nccl', init_method='tcp://127.0.0.1:23456', world_size=4, rank=gpu)
torch.cuda.set_device(args.local_rank)
train_dataset = ...
train_sampler = torch.utils.data.distributed.DistributedSampler(train_dataset)
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=..., sampler=train_sampler)
model = ...
model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[args.local_rank])
optimizer = optim.SGD(model.parameters())
for epoch in range(100):
for batch_idx, (data, target) in enumerate(train_loader):
images = images.cuda(non_blocking=True)
target = target.cuda(non_blocking=True)
...
output = model(images)
loss = criterion(output, target)
...
optimizer.zero_grad()
loss.backward()
optimizer.step()
在上面的代码中值得注意的是，由于没有 torch.distributed.launch 读取的默认环境变量作为配置，我们需要手动为 init_process_group 指定参数：
dist.init_process_group(backend='nccl', init_method='tcp://127.0.0.1:23456', world_size=4, rank=gpu)
两份分布式代码：
import argparse
import os
import random
import shutil
import time
import warnings
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.multiprocessing as mp
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('-a', '--arch', 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), this is the total '
'batch size of all GPUs on the current node when '
'using Data Parallel or Distributed Data Parallel')
parser.add_argument('--lr', '--learning-rate', default=0.1, type=float,
metavar='LR', help='initial learning rate', dest='lr')
parser.add_argument('--momentum', default=0.9, type=float, metavar='M',
help='momentum')
parser.add_argument('--wd', '--weight-decay', default=1e-4, type=float,
metavar='W', help='weight decay (default: 1e-4)',
dest='weight_decay')
parser.add_argument('-p', '--print-freq', 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 nodes for distributed training')
parser.add_argument('--rank', default=-1, type=int,
help='node rank for distributed training')
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='nccl', type=str,
help='distributed backend')
parser.add_argument('--seed', default=None, type=int,
help='seed for initializing training. ')
parser.add_argument('--gpu', default=None, type=int,
help='GPU id to use.')
parser.add_argument('--multiprocessing-distributed', action='store_true',
help='Use multi-processing distributed training to launch '
'N processes per node, which has N GPUs. This is the '
'fastest way to use PyTorch for either single node or '
'multi node data parallel training')
best_acc1 = 0
def main():
args = parser.parse_args()
if args.seed is not None:
random.seed(args.seed)
torch.manual_seed(args.seed)
cudnn.deterministic = True
warnings.warn('You have chosen to seed training. '
'This will turn on the CUDNN deterministic setting, '
'which can slow down your training considerably! '
'You may see unexpected behavior when restarting '
'from checkpoints.')
if args.gpu is not None:
warnings.warn('You have chosen a specific GPU. This will completely '
'disable data parallelism.')
if args.dist_url == "env://" and args.world_size == -1:
args.world_size = int(os.environ["WORLD_SIZE"])
args.distributed = args.world_size > 1 or args.multiprocessing_distributed
ngpus_per_node = torch.cuda.device_count()
if args.multiprocessing_distributed:
# Since we have ngpus_per_node processes per node, the total world_size
# needs to be adjusted accordingly
args.world_size = ngpus_per_node * args.world_size
# Use torch.multiprocessing.spawn to launch distributed processes: the
# main_worker process function
mp.spawn(main_worker, nprocs=ngpus_per_node, args=(ngpus_per_node, args))
else:
# Simply call main_worker function
main_worker(args.gpu, ngpus_per_node, args)
def main_worker(gpu, ngpus_per_node, args):
global best_acc1
args.gpu = gpu
if args.gpu is not None:
print("Use GPU: {} for training".format(args.gpu))
if args.distributed:
if args.dist_url == "env://" and args.rank == -1:
args.rank = int(os.environ["RANK"])
if args.multiprocessing_distributed:
# For multiprocessing distributed training, rank needs to be the
# global rank among all the processes
args.rank = args.rank * ngpus_per_node + gpu
dist.init_process_group(backend=args.dist_backend, init_method=args.dist_url,
world_size=args.world_size, rank=args.rank)
# 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 torch.cuda.is_available():
print('using CPU, this will be slow')
elif args.distributed:
# For multiprocessing distributed, DistributedDataParallel constructor
# should always set the single device scope, otherwise,
# DistributedDataParallel will use all available devices.
if args.gpu is not None:
torch.cuda.set_device(args.gpu)
model.cuda(args.gpu)
# When using a single GPU per process and per
# DistributedDataParallel, we need to divide the batch size
# ourselves based on the total number of GPUs we have
args.batch_size = int(args.batch_size / ngpus_per_node)
args.workers = int((args.workers + ngpus_per_node - 1) / ngpus_per_node)
model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[args.gpu])
else:
model.cuda()
# DistributedDataParallel will divide and allocate batch_size to all
# available GPUs if device_ids are not set
model = torch.nn.parallel.DistributedDataParallel(model)
elif args.gpu is not None:
torch.cuda.set_device(args.gpu)
model = model.cuda(args.gpu)
else:
# DataParallel will divide and allocate batch_size to all available GPUs
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()
# define loss function (criterion) and optimizer
criterion = nn.CrossEntropyLoss().cuda(args.gpu)
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))
if args.gpu is None:
checkpoint = torch.load(args.resume)
else:
# Map model to be loaded to specified single gpu.
loc = 'cuda:{}'.format(args.gpu)
checkpoint = torch.load(args.resume, map_location=loc)
args.start_epoch = checkpoint['epoch']
best_acc1 = checkpoint['best_acc1']
if args.gpu is not None:
# best_acc1 may be from a checkpoint from a different GPU
best_acc1 = best_acc1.to(args.gpu)
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.RandomResizedCrop(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.Resize(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, args)
return
for epoch in range(args.start_epoch, args.epochs):
if args.distributed:
train_sampler.set_epoch(epoch)
adjust_learning_rate(optimizer, epoch, args)
# train for one epoch
train(train_loader, model, criterion, optimizer, epoch, args)
# evaluate on validation set
acc1 = validate(val_loader, model, criterion, args)
# remember best acc@1 and save checkpoint
is_best = acc1 > best_acc1
best_acc1 = max(acc1, best_acc1)
if not args.multiprocessing_distributed or (args.multiprocessing_distributed
and args.rank % ngpus_per_node == 0):
save_checkpoint({
'epoch': epoch + 1,
'arch': args.arch,
'state_dict': model.state_dict(),
'best_acc1': best_acc1,
'optimizer' : optimizer.state_dict(),
}, is_best)
def train(train_loader, model, criterion, optimizer, epoch, args):
batch_time = AverageMeter('Time', ':6.3f')
data_time = AverageMeter('Data', ':6.3f')
losses = AverageMeter('Loss', ':.4e')
top1 = AverageMeter('Acc@1', ':6.2f')
top5 = AverageMeter('Acc@5', ':6.2f')
progress = ProgressMeter(
len(train_loader),
[batch_time, data_time, losses, top1, top5],
prefix="Epoch: [{}]".format(epoch))
# switch to train mode
model.train()
end = time.time()
for i, (images, target) in enumerate(train_loader):
# measure data loading time
data_time.update(time.time() - end)
if args.gpu is not None:
images = images.cuda(args.gpu, non_blocking=True)
if torch.cuda.is_available():
target = target.cuda(args.gpu, non_blocking=True)
# compute output
output = model(images)
loss = criterion(output, target)
# measure accuracy and record loss
acc1, acc5 = accuracy(output, target, topk=(1, 5))
losses.update(loss.item(), images.size(0))
top1.update(acc1[0], images.size(0))
top5.update(acc5[0], images.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:
progress.display(i)
def validate(val_loader, model, criterion, args):
batch_time = AverageMeter('Time', ':6.3f')
losses = AverageMeter('Loss', ':.4e')
top1 = AverageMeter('Acc@1', ':6.2f')
top5 = AverageMeter('Acc@5', ':6.2f')
progress = ProgressMeter(
len(val_loader),
[batch_time, losses, top1, top5],
prefix='Test: ')
# switch to evaluate mode
model.eval()
with torch.no_grad():
end = time.time()
for i, (images, target) in enumerate(val_loader):
if args.gpu is not None:
images = images.cuda(args.gpu, non_blocking=True)
if torch.cuda.is_available():
target = target.cuda(args.gpu, non_blocking=True)
# compute output
output = model(images)
loss = criterion(output, target)
# measure accuracy and record loss
acc1, acc5 = accuracy(output, target, topk=(1, 5))
losses.update(loss.item(), images.size(0))
top1.update(acc1[0], images.size(0))
top5.update(acc5[0], images.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % args.print_freq == 0:
progress.display(i)
# TODO: this should also be done with the ProgressMeter
print(' * Acc@1 {top1.avg:.3f} Acc@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, name, fmt=':f'):
self.name = name
self.fmt = fmt
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 __str__(self):
fmtstr = '{name} {val' + self.fmt + '} ({avg' + self.fmt + '})'
return fmtstr.format(**self.__dict__)
class ProgressMeter(object):
def __init__(self, num_batches, meters, prefix=""):
self.batch_fmtstr = self._get_batch_fmtstr(num_batches)
self.meters = meters
self.prefix = prefix
def display(self, batch):
entries = [self.prefix + self.batch_fmtstr.format(batch)]
entries += [str(meter) for meter in self.meters]
print('\t'.join(entries))
def _get_batch_fmtstr(self, num_batches):
num_digits = len(str(num_batches // 1))
fmt = '{:' + str(num_digits) + 'd}'
return '[' + fmt + '/' + fmt.format(num_batches) + ']'
def adjust_learning_rate(optimizer, epoch, args):
"""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 accuracy over the k top predictions for the specified values of k"""
with torch.no_grad():
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()
# https://github.com/pytorch/examples/blob/master/imagenet/main.py
import csv
import argparse
import os
import random
import shutil
import time
import warnings
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.multiprocessing as mp
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', default='/home/zhangzhi/Data/ImageNet2012', help='path to dataset')
parser.add_argument('-a',
'--arch',
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), this is the total '
'batch size of all GPUs on the current node when '
'using Data Parallel or Distributed Data Parallel')
parser.add_argument('--lr',
'--learning-rate',
default=0.1,
type=float,
metavar='LR',
help='initial learning rate',
dest='lr')
parser.add_argument('--momentum', default=0.9, type=float, metavar='M', help='momentum')
parser.add_argument('--wd',
'--weight-decay',
default=1e-4,
type=float,
metavar='W',
help='weight decay (default: 1e-4)',
dest='weight_decay')
parser.add_argument('-p', '--print-freq', default=10, type=int, metavar='N', help='print frequency (default: 10)')
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('--seed', default=None, type=int, help='seed for initializing training. ')
best_acc1 = 0
def main():
args = parser.parse_args()
mp.spawn(main_worker, nprocs=4, args=(4, args))
def main_worker(gpu, ngpus_per_node, args):
if args.seed is not None:
random.seed(args.seed)
torch.manual_seed(args.seed)
cudnn.deterministic = True
warnings.warn('You have chosen to seed training. '
'This will turn on the CUDNN deterministic setting, '
'which can slow down your training considerably! '
'You may see unexpected behavior when restarting '
'from checkpoints.')
global best_acc1
dist.init_process_group(backend='nccl', init_method='tcp://127.0.0.1:23456', world_size=4, rank=gpu)
# 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]()
torch.cuda.set_device(gpu)
model.cuda(gpu)
# When using a single GPU per process and per
# DistributedDataParallel, we need to divide the batch size
# ourselves based on the total number of GPUs we have
args.batch_size = int(args.batch_size / ngpus_per_node)
model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[gpu])
# define loss function (criterion) and optimizer
criterion = nn.CrossEntropyLoss().cuda(gpu)
optimizer = torch.optim.SGD(model.parameters(), args.lr, momentum=args.momentum, weight_decay=args.weight_decay)
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.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
normalize,
]))
train_sampler = torch.utils.data.distributed.DistributedSampler(train_dataset)
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=args.batch_size,
shuffle=(train_sampler is None),
num_workers=2,
pin_memory=True,
sampler=train_sampler)
val_loader = torch.utils.data.DataLoader(datasets.ImageFolder(
valdir,
transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
normalize,
])),
batch_size=args.batch_size,
shuffle=False,
num_workers=2,
pin_memory=True)
if args.evaluate:
validate(val_loader, model, criterion, gpu, args)
return
log_csv = "multiprocessing_distributed.csv"
for epoch in range(args.start_epoch, args.epochs):
epoch_start = time.time()
train_sampler.set_epoch(epoch)
adjust_learning_rate(optimizer, epoch, args)
# train for one epoch
train(train_loader, model, criterion, optimizer, epoch, gpu, args)
# evaluate on validation set
acc1 = validate(val_loader, model, criterion, gpu, args)
# remember best acc@1 and save checkpoint
is_best = acc1 > best_acc1
best_acc1 = max(acc1, best_acc1)
epoch_end = time.time()
with open(log_csv, 'a+') as f:
csv_write = csv.writer(f)
data_row = [time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(epoch_start)), epoch_end - epoch_start]
csv_write.writerow(data_row)
save_checkpoint(
{
'epoch': epoch + 1,
'arch': args.arch,
'state_dict': model.module.state_dict(),
'best_acc1': best_acc1,
}, is_best)
def train(train_loader, model, criterion, optimizer, epoch, gpu, args):
batch_time = AverageMeter('Time', ':6.3f')
data_time = AverageMeter('Data', ':6.3f')
losses = AverageMeter('Loss', ':.4e')
top1 = AverageMeter('Acc@1', ':6.2f')
top5 = AverageMeter('Acc@5', ':6.2f')
progress = ProgressMeter(len(train_loader), [batch_time, data_time, losses, top1, top5],
prefix="Epoch: [{}]".format(epoch))
# switch to train mode
model.train()
end = time.time()
for i, (images, target) in enumerate(train_loader):
# measure data loading time
data_time.update(time.time() - end)
images = images.cuda(gpu, non_blocking=True)
target = target.cuda(gpu, non_blocking=True)
# compute output
output = model(images)
loss = criterion(output, target)
# measure accuracy and record loss
acc1, acc5 = accuracy(output, target, topk=(1, 5))
losses.update(loss.item(), images.size(0))
top1.update(acc1[0], images.size(0))
top5.update(acc5[0], images.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:
progress.display(i)
def validate(val_loader, model, criterion, gpu, args):
batch_time = AverageMeter('Time', ':6.3f')
losses = AverageMeter('Loss', ':.4e')
top1 = AverageMeter('Acc@1', ':6.2f')
top5 = AverageMeter('Acc@5', ':6.2f')
progress = ProgressMeter(len(val_loader), [batch_time, losses, top1, top5], prefix='Test: ')
# switch to evaluate mode
model.eval()
with torch.no_grad():
end = time.time()
for i, (images, target) in enumerate(val_loader):
images = images.cuda(gpu, non_blocking=True)
target = target.cuda(gpu, non_blocking=True)
# compute output
output = model(images)
loss = criterion(output, target)
# measure accuracy and record loss
acc1, acc5 = accuracy(output, target, topk=(1, 5))
losses.update(loss.item(), images.size(0))
top1.update(acc1[0], images.size(0))
top5.update(acc5[0], images.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % args.print_freq == 0:
progress.display(i)
# TODO: this should also be done with the ProgressMeter
print(' * Acc@1 {top1.avg:.3f} Acc@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, name, fmt=':f'):
self.name = name
self.fmt = fmt
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 __str__(self):
fmtstr = '{name} {val' + self.fmt + '} ({avg' + self.fmt + '})'
return fmtstr.format(**self.__dict__)
class ProgressMeter(object):
def __init__(self, num_batches, meters, prefix=""):
self.batch_fmtstr = self._get_batch_fmtstr(num_batches)
self.meters = meters
self.prefix = prefix
def display(self, batch):
entries = [self.prefix + self.batch_fmtstr.format(batch)]
entries += [str(meter) for meter in self.meters]
print('\t'.join(entries))
def _get_batch_fmtstr(self, num_batches):
num_digits = len(str(num_batches // 1))
fmt = '{:' + str(num_digits) + 'd}'
return '[' + fmt + '/' + fmt.format(num_batches) + ']'
def adjust_learning_rate(optimizer, epoch, args):
"""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 accuracy over the k top predictions for the specified values of k"""
with torch.no_grad():
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()
参考文献：
- pytorch/Apex /HOV 分布式
- 分布式细节计算
- pytorch中dist具体api使用
- https://github.com/tczhangzhi/pytorch-distributed/blob/master/README.md
- github demo1
- github demo2