in main_lincls.py [0:0]
def main_worker(gpu, ngpus_per_node, args):
global best_acc1
args.gpu = gpu
# suppress printing if not master
if args.multiprocessing_distributed and args.gpu != 0:
def print_pass(*args):
pass
builtins.print = print_pass
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)
torch.distributed.barrier()
# create model
print("=> creating model '{}'".format(args.arch))
if args.arch.startswith('vit'):
model = vits.__dict__[args.arch]()
linear_keyword = 'head'
else:
model = torchvision_models.__dict__[args.arch]()
linear_keyword = 'fc'
# freeze all layers but the last fc
for name, param in model.named_parameters():
if name not in ['%s.weight' % linear_keyword, '%s.bias' % linear_keyword]:
param.requires_grad = False
# init the fc layer
getattr(model, linear_keyword).weight.data.normal_(mean=0.0, std=0.01)
getattr(model, linear_keyword).bias.data.zero_()
# load from pre-trained, before DistributedDataParallel constructor
if args.pretrained:
if os.path.isfile(args.pretrained):
print("=> loading checkpoint '{}'".format(args.pretrained))
checkpoint = torch.load(args.pretrained, map_location="cpu")
# rename moco pre-trained keys
state_dict = checkpoint['state_dict']
for k in list(state_dict.keys()):
# retain only base_encoder up to before the embedding layer
if k.startswith('module.base_encoder') and not k.startswith('module.base_encoder.%s' % linear_keyword):
# remove prefix
state_dict[k[len("module.base_encoder."):]] = state_dict[k]
# delete renamed or unused k
del state_dict[k]
args.start_epoch = 0
msg = model.load_state_dict(state_dict, strict=False)
assert set(msg.missing_keys) == {"%s.weight" % linear_keyword, "%s.bias" % linear_keyword}
print("=> loaded pre-trained model '{}'".format(args.pretrained))
else:
print("=> no checkpoint found at '{}'".format(args.pretrained))
# infer learning rate before changing batch size
init_lr = args.lr * args.batch_size / 256
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 / args.world_size)
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)
# optimize only the linear classifier
parameters = list(filter(lambda p: p.requires_grad, model.parameters()))
assert len(parameters) == 2 # weight, bias
optimizer = torch.optim.SGD(parameters, init_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=256, 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, init_lr, 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 == 0): # only the first GPU saves checkpoint
save_checkpoint({
'epoch': epoch + 1,
'arch': args.arch,
'state_dict': model.state_dict(),
'best_acc1': best_acc1,
'optimizer' : optimizer.state_dict(),
}, is_best)
if epoch == args.start_epoch:
sanity_check(model.state_dict(), args.pretrained, linear_keyword)