本文整理汇总了Python中torch.utils.save方法的典型用法代码示例。如果您正苦于以下问题：Python utils.save方法的具体用法？Python utils.save怎么用？Python utils.save使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类torch.utils的用法示例。
在下文中一共展示了utils.save方法的14个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: train
# 需要导入模块: from torch import utils [as 别名]
# 或者: from torch.utils import save [as 别名]
def train():
best_test_acc = 0.
class_acc_best = 0.
for epoch in range(args.epochs):
logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
model.drop_path_prob = args.drop_path_prob * epoch / args.epochs
train_overall_acc, train_class_acc, train_obj = train_step(train_queue, model, criterion, optimizer, args)
test_overall_acc, test_class_acc, test_obj = infer(test_queue, model, criterion)
if test_overall_acc > best_test_acc:
best_test_acc = test_overall_acc
class_acc_best = test_class_acc
utils.save(model, os.path.join(args.save, 'best_weights.pt'))
logging.info(
'train_overall_acc %f\t train_class_acc %f\t test_overall_acc %f\t test_class_acc %f\t best_test_overall_acc %f\t test_class_acc_when_best %f',
train_overall_acc, train_class_acc, test_overall_acc, test_class_acc, best_test_acc, class_acc_best)
utils.save(model, os.path.join(args.save, 'weights.pt'))
scheduler.step()
logging.info(
'Finish! best_test_overall_acc %f\t test_class_acc_when_best %f', best_test_acc, class_acc_best) 示例2: train
# 需要导入模块: from torch import utils [as 别名]
# 或者: from torch.utils import save [as 别名]
def train():
best_val_acc = 0.
best_test_acc = 0.
for epoch in range(args.epochs):
logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
model.drop_path_prob = args.drop_path_prob * epoch / args.epochs
train_acc, train_obj = train_step(train_queue, model, criterion, optimizer)
valid_acc, valid_obj = infer(valid_queue, model, criterion)
test_acc, test_obj = infer(test_queue, model, criterion)
if valid_acc > best_val_acc:
best_val_acc = valid_acc
test_acc_when_best_val = test_acc
utils.save(model, os.path.join(args.save, 'best_weights.pt'))
if test_acc > best_test_acc:
best_test_acc = test_acc
logging.info('train_acc %f\tvalid_acc %f\tbest_val_acc %f\ttest_acc %f\tbest_test_acc %f\tfinal_best_test %f',
train_acc, valid_acc, best_val_acc, test_acc, best_test_acc, test_acc_when_best_val)
utils.save(model, os.path.join(args.save, 'weights.pt'))
scheduler.step()
logging.info(
'Finish! best_val_acc %f\t test_class_acc_when_best %f \t best test %f',
best_test_acc, test_acc_when_best_val, best_test_acc) 示例3: main
# 需要导入模块: from torch import utils [as 别名]
# 或者: from torch.utils import save [as 别名]
def main():
if not torch.cuda.is_available():
logging.info('No GPU found!')
sys.exit(1)
np.random.seed(args.seed)
torch.manual_seed(args.seed)
torch.cuda.manual_seed(args.seed)
torch.cuda.manual_seed_all(args.seed)
cudnn.enabled = True
cudnn.benchmark = True
logging.info("Args = %s", args)
_, model_state_dict, epoch, step, optimizer_state_dict, best_acc_top1 = utils.load(args.output_dir)
train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler = build_imagenet(model_state_dict, optimizer_state_dict, epoch=epoch-1)
while epoch < args.epochs:
scheduler.step()
logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
train_acc, train_obj, step = train(train_queue, model, optimizer, step, train_criterion)
logging.info('train_acc %f', train_acc)
valid_acc_top1, valid_acc_top5, valid_obj = valid(valid_queue, model, eval_criterion)
logging.info('valid_acc_top1 %f', valid_acc_top1)
logging.info('valid_acc_top5 %f', valid_acc_top5)
epoch += 1
is_best = False
if valid_acc_top1 > best_acc_top1:
best_acc_top1 = valid_acc_top1
is_best = True
utils.save(args.output_dir, args, model, epoch, step, optimizer, best_acc_top1, is_best) 示例4: main
# 需要导入模块: from torch import utils [as 别名]
# 或者: from torch.utils import save [as 别名]
def main():
if not torch.cuda.is_available():
logging.info('No GPU found!')
sys.exit(1)
random.seed(args.seed)
np.random.seed(args.seed)
torch.manual_seed(args.seed)
torch.cuda.manual_seed(args.seed)
torch.cuda.manual_seed_all(args.seed)
cudnn.enabled = True
cudnn.benchmark = False
cudnn.deterministic = True
args.steps = int(np.ceil(50000 / args.batch_size)) * args.epochs
logging.info("Args = %s", args)
_, model_state_dict, epoch, step, optimizer_state_dict, best_acc_top1 = utils.load(args.output_dir)
build_fn = get_builder(args.dataset)
train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler = build_fn(model_state_dict, optimizer_state_dict, epoch=epoch-1)
while epoch < args.epochs:
scheduler.step()
logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
train_acc, train_obj, step = train(train_queue, model, optimizer, step, train_criterion)
logging.info('train_acc %f', train_acc)
valid_acc_top1, valid_obj = valid(valid_queue, model, eval_criterion)
logging.info('valid_acc %f', valid_acc_top1)
epoch += 1
is_best = False
if valid_acc_top1 > best_acc_top1:
best_acc_top1 = valid_acc_top1
is_best = True
utils.save(args.output_dir, args, model, epoch, step, optimizer, best_acc_top1, is_best) 示例5: main
# 需要导入模块: from torch import utils [as 别名]
# 或者: from torch.utils import save [as 别名]
def main():
if not torch.cuda.is_available():
logging.info('No GPU found!')
sys.exit(1)
np.random.seed(args.seed)
torch.manual_seed(args.seed)
torch.cuda.manual_seed(args.seed)
torch.cuda.manual_seed_all(args.seed)
cudnn.enabled = True
cudnn.benchmark = True
args.steps = int(np.ceil(50000 / args.batch_size)) * args.epochs
logging.info("Args = %s", args)
_, model_state_dict, epoch, step, optimizer_state_dict, best_acc_top1 = utils.load(args.output_dir)
build_fn = get_builder(args.dataset)
train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler = build_fn(model_state_dict, optimizer_state_dict, epoch=epoch-1)
while epoch < args.epochs:
scheduler.step()
logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
train_acc, train_obj, step = train(train_queue, model, optimizer, step, train_criterion)
logging.info('train_acc %f', train_acc)
valid_acc_top1, valid_obj = valid(valid_queue, model, eval_criterion)
logging.info('valid_acc %f', valid_acc_top1)
epoch += 1
is_best = False
if valid_acc_top1 > best_acc_top1:
best_acc_top1 = valid_acc_top1
is_best = True
utils.save(args.output_dir, args, model, epoch, step, optimizer, best_acc_top1, is_best) 示例6: main
# 需要导入模块: from torch import utils [as 别名]
# 或者: from torch.utils import save [as 别名]
def main():
if not torch.cuda.is_available():
logging.info('No GPU found!')
sys.exit(1)
np.random.seed(args.seed)
torch.manual_seed(args.seed)
torch.cuda.manual_seed(args.seed)
torch.cuda.manual_seed_all(args.seed)
cudnn.enabled = True
cudnn.benchmark = False
cudnn.deterministic = True
logging.info("Args = %s", args)
_, model_state_dict, epoch, step, optimizer_state_dict, best_acc_top1 = utils.load(args.output_dir)
train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler = build_imagenet(model_state_dict, optimizer_state_dict, epoch=epoch-1)
while epoch < args.epochs:
scheduler.step()
logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
train_acc, train_obj, step = train(train_queue, model, optimizer, step, train_criterion)
logging.info('train_acc %f', train_acc)
valid_acc_top1, valid_acc_top5, valid_obj = valid(valid_queue, model, eval_criterion)
logging.info('valid_acc_top1 %f', valid_acc_top1)
logging.info('valid_acc_top5 %f', valid_acc_top5)
epoch += 1
is_best = False
if valid_acc_top1 > best_acc_top1:
best_acc_top1 = valid_acc_top1
is_best = True
utils.save(args.output_dir, args, model, epoch, step, optimizer, best_acc_top1, is_best) 示例7: main
# 需要导入模块: from torch import utils [as 别名]
# 或者: from torch.utils import save [as 别名]
def main():
if not torch.cuda.is_available():
logging.info('No GPU found!')
sys.exit(1)
np.random.seed(args.seed)
torch.manual_seed(args.seed)
torch.cuda.manual_seed(args.seed)
torch.cuda.manual_seed_all(args.seed)
cudnn.enabled = True
cudnn.benchmark = False
cudnn.deterministic = True
args.steps = int(np.ceil(50000 / args.batch_size)) * args.epochs
logging.info("Args = %s", args)
_, model_state_dict, epoch, step, optimizer_state_dict, best_acc_top1 = utils.load(args.output_dir)
build_fn = get_builder(args.dataset)
train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler = build_fn(model_state_dict, optimizer_state_dict, epoch=epoch-1)
while epoch < args.epochs:
scheduler.step()
logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
train_acc, train_obj, step = train(train_queue, model, optimizer, step, train_criterion)
logging.info('train_acc %f', train_acc)
valid_acc_top1, valid_obj = valid(valid_queue, model, eval_criterion)
logging.info('valid_acc %f', valid_acc_top1)
epoch += 1
is_best = False
if valid_acc_top1 > best_acc_top1:
best_acc_top1 = valid_acc_top1
is_best = True
utils.save(args.output_dir, args, model, epoch, step, optimizer, best_acc_top1, is_best) 示例8: main
# 需要导入模块: from torch import utils [as 别名]
# 或者: from torch.utils import save [as 别名]
def main():
if not torch.cuda.is_available():
logging.info('No GPU found!')
sys.exit(1)
np.random.seed(args.seed)
torch.manual_seed(args.seed)
cudnn.enabled = True
cudnn.benchmark = False
cudnn.deterministic = True
torch.cuda.manual_seed(args.seed)
logging.info("Args = %s", args)
_, model_state_dict, epoch, step, optimizer_state_dict, best_acc_top1 = utils.load(args.output_dir)
train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler = build_imagenet(model_state_dict, optimizer_state_dict, epoch=epoch-1)
while epoch < args.epochs:
scheduler.step()
logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
train_acc, train_obj, step = train(train_queue, model, optimizer, step, train_criterion)
logging.info('train_acc %f', train_acc)
valid_acc_top1, valid_acc_top5, valid_obj = valid(valid_queue, model, eval_criterion)
logging.info('valid_acc_top1 %f', valid_acc_top1)
logging.info('valid_acc_top5 %f', valid_acc_top5)
epoch += 1
is_best = False
if valid_acc_top1 > best_acc_top1:
best_acc_top1 = valid_acc_top1
is_best = True
utils.save(args.output_dir, args, model, epoch, step, optimizer, best_acc_top1, is_best) 示例9: main
# 需要导入模块: from torch import utils [as 别名]
# 或者: from torch.utils import save [as 别名]
def main():
if not torch.cuda.is_available():
logging.info('No GPU found!')
sys.exit(1)
np.random.seed(args.seed)
cudnn.benchmark = False
torch.manual_seed(args.seed)
cudnn.enabled = True
torch.cuda.manual_seed(args.seed)
args.steps = int(np.ceil(50000 / args.batch_size)) * args.epochs
logging.info("Args = %s", args)
_, model_state_dict, epoch, step, optimizer_state_dict, best_acc_top1 = utils.load(args.output_dir)
build_fn = get_builder(args.dataset)
train_queue, valid_queue, model, train_criterion, eval_criterion, optimizer, scheduler = build_fn(model_state_dict, optimizer_state_dict, epoch=epoch-1)
while epoch < args.epochs:
scheduler.step()
logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
train_acc, train_obj, step = train(train_queue, model, optimizer, step, train_criterion)
logging.info('train_acc %f', train_acc)
valid_acc_top1, valid_obj = valid(valid_queue, model, eval_criterion)
logging.info('valid_acc %f', valid_acc_top1)
epoch += 1
is_best = False
if valid_acc_top1 > best_acc_top1:
best_acc_top1 = valid_acc_top1
is_best = True
utils.save(args.output_dir, args, model, epoch, step, optimizer, best_acc_top1, is_best) 示例10: main
# 需要导入模块: from torch import utils [as 别名]
# 或者: from torch.utils import save [as 别名]
def main():
if not torch.cuda.is_available():
logging.info('no gpu device available')
sys.exit(1)
np.random.seed(args.seed)
torch.cuda.set_device(args.gpu)
cudnn.benchmark = True
torch.manual_seed(args.seed)
cudnn.enabled = True
torch.cuda.manual_seed(args.seed)
logging.info('gpu device = %d' % args.gpu)
logging.info("args = %s", args)
genotype = eval("genotypes.%s" % args.arch)
model = Network(args.init_channels, CIFAR_CLASSES, args.layers, args.auxiliary, genotype)
model = model.cuda()
logging.info("param size = %fMB", utils.count_parameters_in_MB(model))
criterion = nn.CrossEntropyLoss()
criterion = criterion.cuda()
optimizer = torch.optim.SGD(
model.parameters(),
args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay
)
train_transform, valid_transform = utils._data_transforms_cifar10(args)
train_data = dset.CIFAR10(root=args.data, train=True, download=True, transform=train_transform)
valid_data = dset.CIFAR10(root=args.data, train=False, download=True, transform=valid_transform)
train_queue = torch.utils.data.DataLoader(
train_data, batch_size=args.batch_size, shuffle=True, pin_memory=True, num_workers=2)
valid_queue = torch.utils.data.DataLoader(
valid_data, batch_size=args.batch_size, shuffle=False, pin_memory=True, num_workers=2)
scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, float(args.epochs))
for epoch in range(args.epochs):
scheduler.step()
logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
model.drop_path_prob = args.drop_path_prob * epoch / args.epochs
train_acc, train_obj = train(train_queue, model, criterion, optimizer)
logging.info('train_acc %f', train_acc)
valid_acc, valid_obj = infer(valid_queue, model, criterion)
logging.info('valid_acc %f', valid_acc)
utils.save(model, os.path.join(args.save, 'weights.pt')) 示例11: main
# 需要导入模块: from torch import utils [as 别名]
# 或者: from torch.utils import save [as 别名]
def main():
if not torch.cuda.is_available():
logging.info('no gpu device available')
sys.exit(1)
np.random.seed(args.seed)
torch.cuda.set_device(args.gpu)
cudnn.benchmark = True
torch.manual_seed(args.seed)
cudnn.enabled=True
torch.cuda.manual_seed(args.seed)
logging.info('gpu device = %d' % args.gpu)
logging.info("args = %s", args)
genotype = eval("genotypes.%s" % args.arch)
model = Network(args.init_channels, CIFAR_CLASSES, args.layers, args.auxiliary, genotype)
model = model.cuda()
logging.info("param size = %fMB", utils.count_parameters_in_MB(model))
criterion = nn.CrossEntropyLoss()
criterion = criterion.cuda()
optimizer = torch.optim.SGD(
model.parameters(),
args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay
)
train_transform, valid_transform = utils._data_transforms_cifar10(args)
train_data = dset.CIFAR10(root=args.data, train=True, download=True, transform=train_transform)
valid_data = dset.CIFAR10(root=args.data, train=False, download=True, transform=valid_transform)
train_queue = torch.utils.data.DataLoader(
train_data, batch_size=args.batch_size, shuffle=True, pin_memory=True, num_workers=2)
valid_queue = torch.utils.data.DataLoader(
valid_data, batch_size=args.batch_size, shuffle=False, pin_memory=True, num_workers=2)
scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, float(args.epochs))
for epoch in range(args.epochs):
scheduler.step()
logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
model.drop_path_prob = args.drop_path_prob * epoch / args.epochs
train_acc, train_obj = train(train_queue, model, criterion, optimizer)
logging.info('train_acc %f', train_acc)
valid_acc, valid_obj = infer(valid_queue, model, criterion)
logging.info('valid_acc %f', valid_acc)
utils.save(model, os.path.join(args.save, 'weights.pt')) 示例12: main
# 需要导入模块: from torch import utils [as 别名]
# 或者: from torch.utils import save [as 别名]
def main():
if not torch.cuda.is_available():
logging.info('no gpu device available')
sys.exit(1)
np.random.seed(args.seed)
torch.cuda.set_device(args.gpu)
cudnn.benchmark = True
torch.manual_seed(args.seed)
cudnn.enabled=True
torch.cuda.manual_seed(args.seed)
logging.info('gpu device = %d' % args.gpu)
logging.info("args = %s", args)
genotype = eval("genotypes.%s" % args.arch)
model = Network(args.init_channels, CIFAR_CLASSES, args.layers, args.auxiliary, genotype)
model = model.cuda()
logging.info("param size = %fMB", utils.count_parameters_in_MB(model))
criterion = nn.CrossEntropyLoss()
criterion = criterion.cuda()
optimizer = torch.optim.SGD(
model.parameters(),
args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay
)
train_transform, valid_transform = utils._data_transforms_cifar10(args)
train_data = dset.CIFAR10(root=args.data, train=True, download=True, transform=train_transform)
valid_data = dset.CIFAR10(root=args.data, train=False, download=True, transform=valid_transform)
train_queue = torch.utils.data.DataLoader(
train_data, batch_size=args.batch_size, shuffle=True, pin_memory=True, num_workers=2)
valid_queue = torch.utils.data.DataLoader(
valid_data, batch_size=args.batch_size, shuffle=False, pin_memory=True, num_workers=2)
scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, float(args.epochs))
for epoch in range(args.epochs):
scheduler.step()
logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
model.drop_path_prob = args.drop_path_prob * epoch / args.epochs
train_acc, train_obj = train(train_queue, model, criterion, optimizer)
logging.info('train_acc %f', train_acc)
valid_acc, valid_obj = infer(valid_queue, model, criterion)
logging.info('valid_acc %f', valid_acc)
utils.save(model, os.path.join(args.save, 'weights.pt')) 示例13: main
# 需要导入模块: from torch import utils [as 别名]
# 或者: from torch.utils import save [as 别名]
def main():
if not torch.cuda.is_available():
logging.info('no gpu device available')
sys.exit(1)
random.seed(args.seed)
np.random.seed(args.seed)
torch.cuda.set_device(args.gpu)
torch.backends.cudnn.benchmark = True
torch.manual_seed(args.seed)
torch.cuda.manual_seed(args.seed)
logging.info('gpu device = %d' % args.gpu)
logging.info("args = %s", args)
model = CNN(args)
model.cuda()
controller = Controller(args)
controller.cuda()
baseline = None
optimizer = torch.optim.SGD(
model.parameters(),
args.child_lr_max,
momentum=args.momentum,
weight_decay=args.weight_decay,
)
controller_optimizer = torch.optim.Adam(
controller.parameters(),
args.controller_lr,
betas=(0.1,0.999),
eps=1e-3,
)
train_loader, reward_loader, valid_loader = get_loaders(args)
scheduler = utils.LRScheduler(optimizer, args)
for epoch in range(args.epochs):
lr = scheduler.update(epoch)
logging.info('epoch %d lr %e', epoch, lr)
# training
train_acc = train(train_loader, model, controller, optimizer)
logging.info('train_acc %f', train_acc)
train_controller(reward_loader, model, controller, controller_optimizer)
# validation
valid_acc = infer(valid_loader, model, controller)
logging.info('valid_acc %f', valid_acc)
utils.save(model, os.path.join(args.save, 'weights.pt')) 示例14: main
# 需要导入模块: from torch import utils [as 别名]
# 或者: from torch.utils import save [as 别名]
def main():
if not torch.cuda.is_available():
logging.info('no gpu device available')
sys.exit(1)
np.random.seed(args.seed)
torch.cuda.set_device(args.gpu)
cudnn.benchmark = True
torch.manual_seed(args.seed)
cudnn.enabled=True
torch.cuda.manual_seed(args.seed)
logging.info('gpu device = %d' % args.gpu)
logging.info("args = %s", args)
genotype = eval("genotypes.%s" % args.arch)
model = Network(args.init_channels, CIFAR_CLASSES, args.layers, args.auxiliary, genotype)
model = model.cuda()
logging.info("param size = %fMB", utils.count_parameters_in_MB(model))
criterion = nn.CrossEntropyLoss()
criterion = criterion.cuda()
optimizer = torch.optim.SGD(
model.parameters(),
args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay
)
train_transform, valid_transform = utils._data_transforms_cifar10(args)
train_data = dset.CIFAR10(root=args.data, train=True, download=True, transform=train_transform)
valid_data = dset.CIFAR10(root=args.data, train=False, download=True, transform=valid_transform)
train_queue = torch.utils.data.DataLoader(
train_data, batch_size=args.batch_size, shuffle=True, pin_memory=True, num_workers=2)
valid_queue = torch.utils.data.DataLoader(
valid_data, batch_size=args.batch_size, shuffle=False, pin_memory=True, num_workers=2)
scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, float(args.epochs))
best_val_acc = 0.
for epoch in range(args.epochs):
scheduler.step()
logging.info('epoch %d lr %e', epoch, scheduler.get_lr()[0])
model.drop_path_prob = args.drop_path_prob * epoch / args.epochs
train_acc, train_obj = train(train_queue, model, criterion, optimizer)
logging.info('train_acc %f', train_acc)
with torch.no_grad():
valid_acc, valid_obj = infer(valid_queue, model, criterion)
if valid_acc > best_val_acc:
best_val_acc = valid_acc
utils.save(model, os.path.join(args.save, 'best_weights.pt'))
logging.info('valid_acc %f\tbest_val_acc %f', valid_acc, best_val_acc)
utils.save(model, os.path.join(args.save, 'weights.pt'))