[十八]深度学习Pytorch-学习率Learning Rate调整策略

0. 往期内容

[一]深度学习Pytorch-张量定义与张量创建

[二]深度学习Pytorch-张量的操作：拼接、切分、索引和变换

[三]深度学习Pytorch-张量数学运算

[四]深度学习Pytorch-线性回归

[五]深度学习Pytorch-计算图与动态图机制

[六]深度学习Pytorch-autograd与逻辑回归

[七]深度学习Pytorch-DataLoader与Dataset(含人民币二分类实战)

[八]深度学习Pytorch-图像预处理transforms

[九]深度学习Pytorch-transforms图像增强(剪裁、翻转、旋转)

[十]深度学习Pytorch-transforms图像操作及自定义方法

[十一]深度学习Pytorch-模型创建与nn.Module

[十二]深度学习Pytorch-模型容器与AlexNet构建

[十三]深度学习Pytorch-卷积层(1D/2D/3D卷积、卷积nn.Conv2d、转置卷积nn.ConvTranspose)

[十四]深度学习Pytorch-池化层、线性层、激活函数层

[十五]深度学习Pytorch-权值初始化

[十六]深度学习Pytorch-18种损失函数loss function

[十七]深度学习Pytorch-优化器Optimizer

[十八]深度学习Pytorch-学习率Learning Rate调整策略

1. 学习率调整

前期学习率大，后期学习率小。

2. class _LRScheduler

学习率的调整是以epoch为周期的。

3. 6种学习率调整策略

3.1 optim.lr_scheduler.StepLR(optimizer, step_size, gamma=0.1, last_epoch=- 1)

optim.lr_scheduler.StepLR(optimizer, step_size, gamma=0.1, last_epoch=- 1, verbose=False)

代码示例：

LR = 0.1
iteration = 10
max_epoch = 200
# ------------------------------ fake data and optimizer  ------------------------------

weights = torch.randn((1), requires_grad=True)
target = torch.zeros((1))

optimizer = optim.SGD([weights], lr=LR, momentum=0.9)

# ------------------------------ 1 Step LR ------------------------------
flag = 0
# flag = 1
if flag:

    scheduler_lr = optim.lr_scheduler.StepLR(optimizer, step_size=50, gamma=0.1)  # 设置学习率下降策略

    lr_list, epoch_list = list(), list()
    for epoch in range(max_epoch):

        lr_list.append(scheduler_lr.get_lr())
        epoch_list.append(epoch)

        for i in range(iteration):

            loss = torch.pow((weights - target), 2)
            loss.backward()

            optimizer.step()
            optimizer.zero_grad()

        scheduler_lr.step() #更新当前学习率

    plt.plot(epoch_list, lr_list, label="Step LR Scheduler")
    plt.xlabel("Epoch")
    plt.ylabel("Learning rate")
    plt.legend()
    plt.show()

官方示例：

# Assuming optimizer uses lr = 0.05 for all groups
# lr = 0.05     if epoch < 30
# lr = 0.005    if 30 <= epoch < 60
# lr = 0.0005   if 60 <= epoch < 90
# ...
scheduler = StepLR(optimizer, step_size=30, gamma=0.1)
for epoch in range(100):
    train(...)
    validate(...)
    scheduler.step()

3.2 optim.lr_scheduler.MultiStepLR(optimizer, milestones, gamma=0.1, last_epoch=- 1)

optim.lr_scheduler.MultiStepLR(optimizer, milestones, gamma=0.1, last_epoch=- 1, verbose=False)

代码示例：

LR = 0.1
iteration = 10
max_epoch = 200
# ------------------------------ fake data and optimizer  ------------------------------

weights = torch.randn((1), requires_grad=True)
target = torch.zeros((1))

optimizer = optim.SGD([weights], lr=LR, momentum=0.9)

# ------------------------------ 2 Multi Step LR ------------------------------
flag = 0
# flag = 1
if flag:

    milestones = [50, 125, 160]
    scheduler_lr = optim.lr_scheduler.MultiStepLR(optimizer, milestones=milestones, gamma=0.1)

    lr_list, epoch_list = list(), list()
    for epoch in range(max_epoch):

        lr_list.append(scheduler_lr.get_lr())
        epoch_list.append(epoch)

        for i in range(iteration):

            loss = torch.pow((weights - target), 2)
            loss.backward()

            optimizer.step()
            optimizer.zero_grad()

        scheduler_lr.step()

    plt.plot(epoch_list, lr_list, label="Multi Step LR Scheduler\nmilestones:{}".format(milestones))
    plt.xlabel("Epoch")
    plt.ylabel("Learning rate")
    plt.legend()
    plt.show()

官方示例：

# 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(optimizer, milestones=[30,80], gamma=0.1)
for epoch in range(100):
    train(...)
    validate(...)
    scheduler.step()

3.3 optim.lr_scheduler.ExponentialLR(optimizer, gamma, last_epoch=- 1)

optim.lr_scheduler.ExponentialLR(optimizer, gamma, last_epoch=- 1, verbose=False)

代码示例：

# ------------------------------ 3 Exponential LR ------------------------------
flag = 0
# flag = 1
if flag:

    gamma = 0.95
    scheduler_lr = optim.lr_scheduler.ExponentialLR(optimizer, gamma=gamma)

    lr_list, epoch_list = list(), list()
    for epoch in range(max_epoch):

        lr_list.append(scheduler_lr.get_lr())
        epoch_list.append(epoch)

        for i in range(iteration):

            loss = torch.pow((weights - target), 2)
            loss.backward()

            optimizer.step()
            optimizer.zero_grad