def run(args):
tag = 'bamos.smooth-topk.seed={}.{}'.format(args.seed, args.dataset)
if args.dataset == 'cifar100':
tag += '.noise={}'.format(args.noise_labels)
elif args.dataset == 'imagenet':
tag += '-{}'.format(args.train_size)
setproctitle(tag)
set_seed(args.seed)
xp = create_experiment(args)
train_loader, val_loader, test_loader = get_loaders(args)
loss = get_loss(xp, args)
model = get_model(args)
if args.load_model:
load_model(model, args.load_model)
if args.cuda:
if args.parallel_gpu:
model = torch.nn.DataParallel(model).cuda()
else:
torch.cuda.set_device(args.device)
model.cuda()
loss.cuda()
optimizer = get_optimizer(model, args.mu, args.lr_0, xp)
if args.load_optimizer:
load_optimizer(optimizer, args.load_optimizer, args.lr_0)
with logger.stdout_to("{}_log.txt".format(args.out_name)):
clock = -time.time()
for _ in range(args.epochs):
xp.Epoch.update(1).log()
optimizer = update_optimizer(args.lr_schedule, optimizer,
model, loss, xp)
xp.Learning_Rate.update().log()
xp.Mu.update().log()
xp.Temperature.update().log()
train(model, loss, optimizer, train_loader, xp, args)
test(model, loss, val_loader, xp, args)
test(model, loss, test_loader, xp, args)
clock += time.time()
print("\nEvaluation time: \t {0:.2g} min".format(clock * 1. / 60))
def main(args):
set_seed(args)
dataset_train, dataset_val, dataset_test = get_datasets(args)
optimizer = get_optimizer(args)
obj = get_objective(args, optimizer.hparams)
xp = get_xp(args, optimizer)
for i in range(args.epochs):
xp.Epoch.update(1).log()
train(obj, optimizer, dataset_train, xp, args, i)
test(obj, optimizer, dataset_val, xp, args, i)
test(obj, optimizer, dataset_test, xp, args, i)
print_total_time(xp)
def run(args):
set_seed(args.seed)
xp = create_experiment(args)
train_loader, val_loader, test_loader = get_loaders(args)
loss = get_loss(xp, args)
model = get_model(args)
if args.load_model:
load_model(model, args.load_model)
if args.cuda:
if args.parallel_gpu:
model = torch.nn.DataParallel(model).cuda()
else:
torch.cuda.set_device(args.device)
model.cuda()
loss.cuda()
optimizer = get_optimizer(model, args.mu, args.lr_0, xp)
if args.load_optimizer:
load_optimizer(optimizer, args.load_optimizer, args.lr_0)
with logger.stdout_to("{}_log.txt".format(args.out_name)):
clock = -time.time()
for _ in range(args.epochs):
xp.Epoch.update(1).log()
optimizer = update_optimizer(args.lr_schedule, optimizer, model,
loss, xp)
xp.Learning_Rate.update().log()
xp.Mu.update().log()
xp.Temperature.update().log()
train(model, loss, optimizer, train_loader, xp, args)
test(model, loss, val_loader, xp, args)
test(model, loss, test_loader, xp, args)
clock += time.time()
print("\nEvaluation time: \t {0:.2g} min".format(clock * 1. / 60))
def main(args):
set_cuda(args)
set_seed(args)
loader_train, loader_val, loader_test = get_data_loaders(args)
loss = get_loss(args)
model = get_model(args)
optimizer = get_optimizer(args, parameters=model.parameters())
xp = get_xp(args, model, optimizer)
for i in range(args.epochs):
xp.Epoch.update(1).log()
train(model, loss, optimizer, loader_train, xp, args)
test(model, loader_val, xp, args)
if (i + 1) in args.T:
decay_optimizer(optimizer, args.decay_factor)
load_best_model(model, xp)
test(model, loader_test, xp, args)
def main(args):
set_cuda(args)
set_seed(args)
loader_train, loader_val, loader_test = get_data_loaders(args)
loss = get_loss(args)
model = get_model(args)
optimizer = get_optimizer(args, model, loss, parameters=model.parameters())
xp = setup_xp(args, model, optimizer)
for i in range(args.epochs):
xp.epoch.update(i)
train(model, loss, optimizer, loader_train, args, xp)
test(model, optimizer, loader_val, args, xp)
if (i + 1) in args.T:
decay_optimizer(optimizer, args.decay_factor)
load_best_model(model, '{}/best_model.pkl'.format(args.xp_name))
test(model, optimizer, loader_val, args, xp)
test(model, optimizer, loader_test, args, xp)
