当前位置: 首页>>代码示例>>Python>>正文


Python lr_scheduler.MultiStepLR方法代码示例

本文整理汇总了Python中torch.optim.lr_scheduler.MultiStepLR方法的典型用法代码示例。如果您正苦于以下问题:Python lr_scheduler.MultiStepLR方法的具体用法?Python lr_scheduler.MultiStepLR怎么用?Python lr_scheduler.MultiStepLR使用的例子?那么, 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torch.optim.lr_scheduler的用法示例。


在下文中一共展示了lr_scheduler.MultiStepLR方法的15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: create_lr_scheduler

# 需要导入模块: from torch.optim import lr_scheduler [as 别名]
# 或者: from torch.optim.lr_scheduler import MultiStepLR [as 别名]
def create_lr_scheduler(optimizer, config):
    if config.lr_scheduler == 'cos':
        scheduler = lr_scheduler.CosineAnnealingLR(optimizer,
                                                   T_max=config.epochs,
                                                   eta_min=config.min_lr)
    elif config.lr_scheduler == 'multistep':
        if config.steps is None: return None
        if isinstance(config.steps, int): config.steps = [config.steps]
        scheduler = lr_scheduler.MultiStepLR(optimizer,
                                             milestones=config.steps,
                                             gamma=config.gamma)
    elif config.lr_scheduler == 'exp-warmup':
        lr_lambda = exp_warmup(config.rampup_length,
                               config.rampdown_length,
                               config.epochs)
        scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lr_lambda)
    elif config.lr_scheduler == 'none':
        scheduler = None
    else:
        raise ValueError("No such scheduler: {}".format(config.lr_scheduler))
    return scheduler 
开发者ID:iBelieveCJM,项目名称:Tricks-of-Semi-supervisedDeepLeanring-Pytorch,代码行数:23,代码来源:main.py

示例2: train

# 需要导入模块: from torch.optim import lr_scheduler [as 别名]
# 或者: from torch.optim.lr_scheduler import MultiStepLR [as 别名]
def train(args, dataloader, model):
    epoch = 1
    optimizer = optim.Adam(list(model.parameters()), lr=args.lr)
    scheduler = MultiStepLR(optimizer, milestones=LR_milestones, gamma=args.lr)

    model.train()
    for epoch in range(5000):
        for batch_idx, data in enumerate(dataloader):
            model.zero_grad()
            features = data['features'].float()
            adj_input = data['adj'].float()

            features = Variable(features).cuda()
            adj_input = Variable(adj_input).cuda()
            
            loss = model(features, adj_input)
            print('Epoch: ', epoch, ', Iter: ', batch_idx, ', Loss: ', loss)
            loss.backward()

            optimizer.step()
            scheduler.step()
            break 
开发者ID:JiaxuanYou,项目名称:graph-generation,代码行数:24,代码来源:train.py

示例3: __init__

# 需要导入模块: from torch.optim import lr_scheduler [as 别名]
# 或者: from torch.optim.lr_scheduler import MultiStepLR [as 别名]
def __init__(self):
        self.log_dir = settings.log_dir
        self.model_dir = settings.model_dir
        ensure_dir(settings.log_dir)
        ensure_dir(settings.model_dir)
        logger.info('set log dir as %s' % settings.log_dir)
        logger.info('set model dir as %s' % settings.model_dir)

        self.net = RESCAN().cuda()
        self.crit = MSELoss().cuda()
        self.ssim = SSIM().cuda()

        self.step = 0
        self.save_steps = settings.save_steps
        self.num_workers = settings.num_workers
        self.batch_size = settings.batch_size
        self.writers = {}
        self.dataloaders = {}

        self.opt = Adam(self.net.parameters(), lr=settings.lr)
        self.sche = MultiStepLR(self.opt, milestones=[15000, 17500], gamma=0.1) 
开发者ID:XiaLiPKU,项目名称:RESCAN,代码行数:23,代码来源:train.py

示例4: train_classifiers

# 需要导入模块: from torch.optim import lr_scheduler [as 别名]
# 或者: from torch.optim.lr_scheduler import MultiStepLR [as 别名]
def train_classifiers(model, learning_rate, dataset, train_loader,
                      test_loader, stat_tracker, checkpointer, log_dir, device):
    # retrain the evaluation classifiers using the trained feature encoder
    for mod in model.class_modules:
        # reset params in the evaluation classifiers
        mod.apply(weight_init)
    mods_to_opt = [m for m in model.class_modules]
    # configure optimizer
    optimizer = optim.Adam(
        [{'params': mod.parameters(), 'lr': learning_rate} for mod in mods_to_opt],
        betas=(0.8, 0.999), weight_decay=1e-5, eps=1e-8)
    # configure learning rate schedulers
    if dataset in [Dataset.C10, Dataset.C100, Dataset.STL10]:
        scheduler = MultiStepLR(optimizer, milestones=[80, 110], gamma=0.2)
        epochs = 120
    elif dataset == Dataset.IN128:
        scheduler = MultiStepLR(optimizer, milestones=[15, 25], gamma=0.2)
        epochs = 30
    elif dataset == Dataset.PLACES205:
        scheduler = MultiStepLR(optimizer, milestones=[7, 12], gamma=0.2)
        epochs = 15
    # retrain the model
    _train(model, optimizer, scheduler, checkpointer, epochs, train_loader,
           test_loader, stat_tracker, log_dir, device) 
开发者ID:Philip-Bachman,项目名称:amdim-public,代码行数:26,代码来源:task_classifiers.py

示例5: train_self_supervised

# 需要导入模块: from torch.optim import lr_scheduler [as 别名]
# 或者: from torch.optim.lr_scheduler import MultiStepLR [as 别名]
def train_self_supervised(model, learning_rate, dataset, train_loader,
                          test_loader, stat_tracker, checkpointer, log_dir, device):
    # configure optimizer
    mods_inf = [m for m in model.info_modules]
    mods_cls = [m for m in model.class_modules]
    mods_to_opt = mods_inf + mods_cls
    optimizer = optim.Adam(
        [{'params': mod.parameters(), 'lr': learning_rate} for mod in mods_to_opt],
        betas=(0.8, 0.999), weight_decay=1e-5, eps=1e-8)
    # configure learning rate schedulers for the optimizers
    if dataset in [Dataset.C10, Dataset.C100, Dataset.STL10]:
        scheduler = MultiStepLR(optimizer, milestones=[250, 280], gamma=0.2)
        epochs = 300
    else:
        # best imagenet results use longer schedules...
        # -- e.g., milestones=[60, 90], epochs=100
        scheduler = MultiStepLR(optimizer, milestones=[30, 45], gamma=0.2)
        epochs = 50
    # train the model
    _train(model, optimizer, scheduler, checkpointer, epochs,
           train_loader, test_loader, stat_tracker, log_dir, device) 
开发者ID:Philip-Bachman,项目名称:amdim-public,代码行数:23,代码来源:task_self_supervised.py

示例6: make_scheduler

# 需要导入模块: from torch.optim import lr_scheduler [as 别名]
# 或者: from torch.optim.lr_scheduler import MultiStepLR [as 别名]
def make_scheduler(args, my_optimizer):
    if args.decay_type == 'step':
        scheduler = lrs.StepLR(
            my_optimizer,
            step_size=args.lr_decay,
            gamma=args.gamma
        )
    elif args.decay_type.find('step') >= 0:
        milestones = args.decay_type.split('_')
        milestones.pop(0)
        milestones = list(map(lambda x: int(x), milestones))
        scheduler = lrs.MultiStepLR(
            my_optimizer,
            milestones=milestones,
            gamma=args.gamma
        )

    return scheduler 
开发者ID:ofsoundof,项目名称:3D_Appearance_SR,代码行数:20,代码来源:utility.py

示例7: get_lr_scheduler

# 需要导入模块: from torch.optim import lr_scheduler [as 别名]
# 或者: from torch.optim.lr_scheduler import MultiStepLR [as 别名]
def get_lr_scheduler(optimizer_conf, scheduler_name, optimizer, initial_epoch=-1):
  if scheduler_name == 'multistep':
    return lr_scheduler.MultiStepLR(optimizer,
                                    optimizer_conf.decay_steps,
                                    optimizer_conf.decay_factor,
                                    initial_epoch)
  elif scheduler_name == 'linear' or scheduler_name == 'polynomial':
    power = 1.0 if scheduler_name == 'linear' else optimizer_conf.decay_power
    lr_lambda = _get_polynomial_decay(optimizer_conf.learning_rate,
                                      optimizer_conf.end_learning_rate,
                                      optimizer_conf.decay_steps,
                                      optimizer_conf.get_attr('start_decay',
                                                              default=0),
                                      power)
    return lr_scheduler.LambdaLR(optimizer, lr_lambda, initial_epoch)
  else:
    raise ValueError('Unknown learning rate scheduler {}'.format(scheduler_name)) 
开发者ID:mseitzer,项目名称:srgan,代码行数:19,代码来源:lr_schedulers.py

示例8: Baseline_train

# 需要导入模块: from torch.optim import lr_scheduler [as 别名]
# 或者: from torch.optim.lr_scheduler import MultiStepLR [as 别名]
def Baseline_train(model, train_loader, eva_loader, args):
    optimizer = SGD(model.parameters(), lr=args.lr, momentum=args.momentum, weight_decay=args.weight_decay)
    exp_lr_scheduler = lr_scheduler.MultiStepLR(optimizer, milestones=args.milestones, gamma=args.gamma)
    for epoch in range(args.epochs):
        loss_record = AverageMeter()
        model.train()
        exp_lr_scheduler.step()
        for batch_idx, (x, label, idx) in enumerate(tqdm(train_loader)):
            x = x.to(device)
            feat = model(x)
            prob = feat2prob(feat, model.center)
            loss = F.kl_div(prob.log(), args.p_targets[idx].float().to(device))
            loss_record.update(loss.item(), x.size(0))
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
        print('Train Epoch: {} Avg Loss: {:.4f}'.format(epoch, loss_record.avg))
        _, _, _, probs = test(model, eva_loader, args)
        if epoch % args.update_interval==0:
            print('updating target ...')
            args.p_targets = target_distribution(probs) 
    torch.save(model.state_dict(), args.model_dir)
    print("model saved to {}.".format(args.model_dir)) 
开发者ID:k-han,项目名称:DTC,代码行数:25,代码来源:imagenet2cifar_DTC.py

示例9: train

# 需要导入模块: from torch.optim import lr_scheduler [as 别名]
# 或者: from torch.optim.lr_scheduler import MultiStepLR [as 别名]
def train(model, train_loader, args):
    optimizer = Adam(model.parameters(), lr=args.lr)
    exp_lr_scheduler = lr_scheduler.MultiStepLR(optimizer, milestones=args.milestones, gamma=args.gamma)
    criterion=nn.CrossEntropyLoss().cuda(device)
    for epoch in range(args.epochs):
        loss_record = AverageMeter()
        acc_record = AverageMeter()
        model.train()
        exp_lr_scheduler.step()
        for batch_idx, (x, label, _) in enumerate(train_loader):
            x, target = x.to(device), label.to(device)
            optimizer.zero_grad()
            _, output= model(x)
            loss = criterion(output, target) 
            acc = accuracy(output, target)
            loss.backward()
            optimizer.step()
            acc_record.update(acc[0].item(), x.size(0))
            loss_record.update(loss.item(), x.size(0))
        print('Train Epoch: {} Avg Loss: {:.4f} \t Avg Acc: {:.4f}'.format(epoch, loss_record.avg, acc_record.avg))
        test(model, eva_loader, args)
    torch.save(model.state_dict(), args.model_dir)
    print("model saved to {}.".format(args.model_dir)) 
开发者ID:k-han,项目名称:DTC,代码行数:25,代码来源:cifar100_classif.py

示例10: Baseline_train

# 需要导入模块: from torch.optim import lr_scheduler [as 别名]
# 或者: from torch.optim.lr_scheduler import MultiStepLR [as 别名]
def Baseline_train(model, train_loader, eva_loader, args):
    optimizer = SGD(model.parameters(), lr=args.lr, momentum=args.momentum, weight_decay=args.weight_decay)
    exp_lr_scheduler = lr_scheduler.MultiStepLR(optimizer, milestones=args.milestones, gamma=args.gamma)
    for epoch in range(args.epochs):
        loss_record = AverageMeter()
        model.train()
        exp_lr_scheduler.step()
        for batch_idx, ((x, _), label, idx) in enumerate(tqdm(train_loader)):
            x = x.to(device)
            _, feat = model(x)
            prob = feat2prob(feat, model.center)
            loss = F.kl_div(prob.log(), args.p_targets[idx].float().to(device))
            loss_record.update(loss.item(), x.size(0))
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
        print('Train Epoch: {} Avg Loss: {:.4f}'.format(epoch, loss_record.avg))
        _, _, _, probs = test(model, eva_loader, args, epoch)

        if epoch % args.update_interval==0:
            print('updating target ...')
            args.p_targets = target_distribution(probs) 
    torch.save(model.state_dict(), args.model_dir)
    print("model saved to {}.".format(args.model_dir)) 
开发者ID:k-han,项目名称:DTC,代码行数:26,代码来源:cifar100_DTC.py

示例11: train

# 需要导入模块: from torch.optim import lr_scheduler [as 别名]
# 或者: from torch.optim.lr_scheduler import MultiStepLR [as 别名]
def train(model, train_loader, args):
    optimizer = Adam(model.parameters(), lr=args.lr)
    exp_lr_scheduler = lr_scheduler.MultiStepLR(optimizer, milestones=args.milestones, gamma=args.gamma)
    criterion=nn.CrossEntropyLoss().cuda(device)
    for epoch in range(args.epochs):
        loss_record = AverageMeter()
        acc_record = AverageMeter()
        model.train()
        exp_lr_scheduler.step()
        for batch_idx, (x, label, _) in enumerate(train_loader):
            x, target = x.to(device), label.to(device)
            optimizer.zero_grad()
            output= model(x)
            loss = criterion(output, target) 
            acc = accuracy(output, target)
            loss.backward()
            optimizer.step()
            acc_record.update(acc[0].item(), x.size(0))
            loss_record.update(loss.item(), x.size(0))
        print('Train Epoch: {} Avg Loss: {:.4f} \t Avg Acc: {:.4f}'.format(epoch, loss_record.avg, acc_record.avg))
        test(model, eva_loader, args)
    torch.save(model.state_dict(), args.model_dir)
    print("model saved to {}.".format(args.model_dir)) 
开发者ID:k-han,项目名称:DTC,代码行数:25,代码来源:cifar10_classif.py

示例12: make_scheduler

# 需要导入模块: from torch.optim import lr_scheduler [as 别名]
# 或者: from torch.optim.lr_scheduler import MultiStepLR [as 别名]
def make_scheduler(args, my_optimizer):
    if args.decay_type == 'step':
        scheduler = lrs.StepLR(
            my_optimizer,
            step_size=args.lr_decay,
            gamma=args.gamma
        )
    if args.decay_type.find('step') >= 0:
        milestones = args.decay_type.split('_')
        milestones.pop(0)
        milestones = list(map(lambda x: int(x), milestones))
        print(milestones)
        scheduler = lrs.MultiStepLR(
            my_optimizer,
            milestones=milestones,
            gamma=args.gamma
        )
        
    if args.decay_type == 'restart':
        scheduler = lrs.LambdaLR(my_optimizer, lambda epoch: multistep_restart(args.period, epoch))

    return scheduler 
开发者ID:ChaofWang,项目名称:AWSRN,代码行数:24,代码来源:utility.py

示例13: __init__

# 需要导入模块: from torch.optim import lr_scheduler [as 别名]
# 或者: from torch.optim.lr_scheduler import MultiStepLR [as 别名]
def __init__(self, *, milestones, gamma=0.1, last_epoch=-1):
        """Decays the learning rate of each parameter group by gamma once the
        number of epoch reaches one of the milestones. Notice that such decay can
        happen simultaneously with other changes to the learning rate from outside
        this scheduler. When last_epoch=-1, sets initial lr as lr.

        Args:
            milestones (list): List of epoch indices. Must be increasing.
            gamma (float): Multiplicative factor of learning rate decay.
                Default: 0.1.
            last_epoch (int): The index of last epoch. Default: -1.

        Example:
            >>> # Assuming optimizer uses lr = 0.05 for all groups
            >>> # lr = 0.05     if epoch < 30
            >>> # lr = 0.005    if 30 <= epoch < 80
            >>> # lr = 0.0005   if epoch >= 80
            >>> scheduler = MultiStepLR(milestones=[30,80], gamma=0.1)
            >>> scheduler(optimizer)
            >>> for epoch in range(100):
            >>>     train(...)
            >>>     validate(...)
            >>>     scheduler.step(),
        """
        super().__init__(lr_scheduler.MultiStepLR, milestones=milestones, gamma=gamma, last_epoch=last_epoch) 
开发者ID:yoshida-lab,项目名称:XenonPy,代码行数:27,代码来源:lr_scheduler.py

示例14: create_scheduler

# 需要导入模块: from torch.optim import lr_scheduler [as 别名]
# 或者: from torch.optim.lr_scheduler import MultiStepLR [as 别名]
def create_scheduler(args, optimizer, datasets):
    if args.scheduler == 'step':
        scheduler = lr_scheduler.MultiStepLR(optimizer, milestones=eval(args.milestones), gamma=args.lr_decay)
    elif args.scheduler == 'poly':
        total_step = (len(datasets['train']) / args.batch + 1) * args.epochs
        scheduler = lr_scheduler.LambdaLR(optimizer, lambda x: (1-x/total_step) ** args.power)
    elif args.scheduler == 'plateau':
        scheduler = lr_scheduler.ReduceLROnPlateau(optimizer, mode='max', factor=args.lr_decay, patience=args.patience)
    elif args.scheduler == 'constant':
        scheduler = lr_scheduler.LambdaLR(optimizer, lambda x: 1)
    elif args.scheduler == 'cosine':
        scheduler = lr_scheduler.CosineAnnealingLR(optimizer, args.T_max, args.min_lr)
    return scheduler 
开发者ID:miraiaroha,项目名称:ACAN,代码行数:15,代码来源:scheduler.py

示例15: configure_lr_scheduler

# 需要导入模块: from torch.optim import lr_scheduler [as 别名]
# 或者: from torch.optim.lr_scheduler import MultiStepLR [as 别名]
def configure_lr_scheduler(self, optimizer, cfg):
        if cfg.SCHEDULER == 'step':
            scheduler = lr_scheduler.StepLR(optimizer, step_size=cfg.STEPS[0], gamma=cfg.GAMMA)
        elif cfg.SCHEDULER == 'multi_step':
            scheduler = lr_scheduler.MultiStepLR(optimizer, milestones=cfg.STEPS, gamma=cfg.GAMMA)
        elif cfg.SCHEDULER == 'exponential':
            scheduler = lr_scheduler.ExponentialLR(optimizer, gamma=cfg.GAMMA)
        elif cfg.SCHEDULER == 'SGDR':
            scheduler = lr_scheduler.CosineAnnealingLR(optimizer, T_max=cfg.MAX_EPOCHS)
        else:
            AssertionError('scheduler can not be recognized.')
        return scheduler 
开发者ID:ShuangXieIrene,项目名称:ssds.pytorch,代码行数:14,代码来源:ssds_train.py


注:本文中的torch.optim.lr_scheduler.MultiStepLR方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。