for num in num_types:
num_wl = getattr(args, "wl_{}".format(num))
number_dict[num] = BlockFloatingPoint(wl=num_wl, dim=0)
print("{:10}: {}".format(num, number_dict[num]))
quant_dict = dict()
for num in ["weight", "momentum", "grad"]:
quant_dict[num] = quantizer(forward_number=number_dict[num],
forward_rounding=args.rounding)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = models.__dict__['vgg'](dataset=args.dataset, depth=args.depth)
# automatically insert quantization modules
model = sequential_lower(model,
layer_types=["conv", "linear"],
forward_number=number_dict["activate"],
backward_number=number_dict["error"],
forward_rounding=args.rounding,
backward_rounding=args.rounding)
# removing the final quantization module
model.classifier = model.classifier[0]
if args.model:
if os.path.isfile(args.model):
print("=> loading checkpoint '{}'".format(args.model))
checkpoint = torch.load(args.model)
# args.start_epoch = checkpoint['epoch']
# best_prec1 = checkpoint['best_prec1']
try:
model.load_state_dict(checkpoint['state_dict'])
except:
model = torch.nn.DataParallel(model,
param.data = weight_quantizer(param.data)
elif args.quantize_method == 'static_quant_int8':
print("Using static_quant_int8 model")
mtcnn = auto_low.sequential_lower(mtcnn,
static_quant.Quantizer,
layer_types=['conv', 'linear'],
device=device)
mtcnn.load_state_dict(torch.load("model"))
static_quant.lower(mtcnn)
static_quant.show(mtcnn)
elif args.quantize_method == 'float_quant':
print("Using float_quant model")
forward_num = FloatingPoint(exp=5, man=3)
mtcnn = sequential_lower(mtcnn,
layer_types=['conv', 'linear'],
forward_number=forward_num,
forward_rounding="nearest")
weight_quantizer = lambda x: float_quantize(
x, exp=5, man=3, rounding="nearest")
for name, param in mtcnn.named_parameters():
param.data = weight_quantizer(param.data)
else:
print("Using original model")
print(mtcnn)
video = mmcv.VideoReader('video.mp4')
frames = [
Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
for frame in video
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 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()
forward_num = FloatingPoint(exp=5, man=3)
#backward_num = FloatingPoint(exp=5, man=3)
model = sequential_lower(model,
layer_types=['linear'],
forward_number=forward_num,
forward_rounding="nearest")
# 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)
weight_quant = lambda x: float_quantize(
x, exp=5, man=3, rounding="nearest")
optimizer = OptimLP(optimizer, weight_quant=weight_quant)
# 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)