def main():
global args, config
args = parser.parse_args()
with open(args.config) as rPtr:
config = EasyDict(yaml.load(rPtr))
config.save_path = os.path.dirname(args.config)
# Random seed
torch.manual_seed(config.seed)
torch.cuda.manual_seed(config.seed)
np.random.seed(config.seed)
random.seed(config.seed)
# Datasets
train_transform = transforms.Compose([
transforms.RandomCrop((32, 32), padding=4),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.491, 0.482, 0.447), (0.247, 0.243, 0.262))
])
val_transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.491, 0.482, 0.447), (0.247, 0.243, 0.262))
])
trainset = Datasets.CIFAR10(root='data', train=True, download=True, transform=train_transform)
trainloader = Data.DataLoader(trainset, batch_size=config.batch_size, shuffle=True, num_workers=config.workers)
testset = Datasets.CIFAR10(root='data', train=False, download=True, transform=val_transform)
testloader = Data.DataLoader(testset, batch_size=config.batch_size, shuffle=False, num_workers=config.workers)
# Model
model = resnet32()
if config.zerogamma:
print('all BN layers weights that sit at the end of a residual block are set 0.0')
Zerogamma(model, last_bn_name='bn2')
model = model.cuda()
# Optimizer
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=config.lr_scheduler.base_lr, momentum=config.momentum,
weight_decay=config.weight_decay)
# LR scheduler
# lr_scheduler = get_scheduler(optimizer, config.lr_scheduler)
lr_scheduler = CosineAnnealing(optimizer, config.max_iter * len(trainloader))
global PCA, Writer
PCA = PerClassAccuracy(num_classes=config.num_classes)
Writer = SummaryWriter(config.save_path + '/events')
for iter_idx in range(config.max_iter):
train(model, iter_idx, criterion, lr_scheduler, optimizer, trainloader)
val(model, iter_idx, criterion, testloader)
Writer.close()
def main():
global args, config
args = parser.parse_args()
with open(args.config) as rPtr:
config = EasyDict(yaml.load(rPtr))
config.save_path = os.path.dirname(args.config)
# Random seed
torch.manual_seed(config.seed)
torch.cuda.manual_seed(config.seed)
np.random.seed(config.seed)
random.seed(config.seed)
# Datasets
train_transform = transforms.Compose([
transforms.RandomCrop((32, 32), padding=4),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.491, 0.482, 0.447), (0.247, 0.243, 0.262))
])
val_transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.491, 0.482, 0.447), (0.247, 0.243, 0.262))
])
trainset = Datasets.CIFAR10(root='data', train=True, download=True, transform=train_transform)
trainloader = Data.DataLoader(trainset, batch_size=config.batch_size, shuffle=True, num_workers=config.workers)
testset = Datasets.CIFAR10(root='data', train=False, download=True, transform=val_transform)
testloader = Data.DataLoader(testset, batch_size=config.batch_size, shuffle=False, num_workers=config.workers)
# Model
model = resnet32()
model = model.cuda()
# Optimizer
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=config.lr_scheduler.base_lr, momentum=config.momentum)
global lr_warmup_scheduler
lr_warmup_scheduler = Warmup(optimizer, config.warmup.warup_times)
# LR scheduler
lr_scheduler = get_scheduler(optimizer, config.lr_scheduler)
global PCA, Writer
PCA = PerClassAccuracy(num_classes=config.num_classes)
Writer = SummaryWriter(config.save_path + '/events')
for iter_idx in range(config.max_iter):
if config.warmup.type == 'epoch' and iter_idx < config.warmup.warup_times:
lr_warmup_scheduler.step()
train(model, iter_idx, criterion, lr_scheduler, optimizer, trainloader)
val(model, iter_idx, criterion, testloader)
Writer.close()
def main():
# global args, config
#
# args = parser.parse_args()
#
# with open(args.config) as rPtr:
# config = EasyDict(yaml.load(rPtr))
#
# config.save_path = os.path.dirname(args.config)
#
# # Random seed
# torch.manual_seed(config.seed)
# torch.cuda.manual_seed(config.seed)
# np.random.seed(config.seed)
# random.seed(config.seed)
# Datasets
train_transform = transforms.Compose([
transforms.RandomCrop((32, 32), padding=4),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.491, 0.482, 0.447), (0.247, 0.243, 0.262))
])
val_transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.491, 0.482, 0.447), (0.247, 0.243, 0.262))
])
trainset = Datasets.CIFAR10(root='data', train=True, download=True, transform=train_transform)
trainloader = Data.DataLoader(trainset, batch_size=config.batch_size, shuffle=True, num_workers=config.workers)
testset = Datasets.CIFAR10(root='data', train=False, download=True, transform=val_transform)
testloader = Data.DataLoader(testset, batch_size=config.batch_size, shuffle=False, num_workers=config.workers)
# Model
model = resnet32()
model = model.cuda()
# Optimizer
criterion = LabelSmoothing(config.label_smoothing)
optimizer = optim.SGD(model.parameters(), lr=config.lr_scheduler.base_lr, momentum=config.momentum,
weight_decay=config.weight_decay)
# LR scheduler
lr_scheduler = CosineAnnealing(optimizer, len(trainloader) * config.max_iter)
global PCA, Writer
PCA = PerClassAccuracy(num_classes=config.num_classes)
Writer = SummaryWriter(config.save_path + '/events')
BEST_mAP = 0.0
for iter_idx in range(config.max_iter):
train(model, iter_idx, criterion, lr_scheduler, optimizer, trainloader)
mAP = val(model, iter_idx, criterion, testloader)
if mAP > BEST_mAP:
BEST_mAP = mAP
nni.report_intermediate_result(mAP)
nni.report_final_result(BEST_mAP)
Writer.close()