torch.optim.lr_scheduler.CosineAnnealingWarmRestarts

torch.optim.lr_scheduler.CosineAnnealingWarmRestarts(optimizer, T_0, T_mult=1, \
eta_min=0, last_epoch=- 1, verbose=False)

使用余弦退火来设置每个参数组的学习率.

- optimizer (Optimizer) – Wrapped optimizer. 优化器

- T_0 (int) – Number of iterations for the first restart.学习率第一次回到初始值的epoch位置

- T_mult (int, optional) – A factor increases T_{i} mult应该是multiply的意思，即T_mult=2意思是周期翻倍，第一个周期是1，则第二个周期是2，第三个周期是4。

- eta_min (float, optional) – Minimum learning rate. Default: 0.

- last_epoch (int, optional) – The index of last epoch. Default: -1.

- verbose (bool) – If True, prints a message to stdout for each update. Default: False.

import torch
from torch.optim.lr_scheduler import CosineAnnealingLR, CosineAnnealingWarmRestarts,StepLR, OneCycleLR
import torch.nn as nn
from torchvision.models import resnet18
import matplotlib.pyplot as plt

model = resnet18(pretrained=False)
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)

mode = 'cosineAnnWarm'
#mode = 'cosineAnn'
if mode == 'cosineAnn':
    scheduler = CosineAnnealingLR(optimizer, T_max=5, eta_min=0.001)
elif mode == 'cosineAnnWarm':
    scheduler = CosineAnnealingWarmRestarts(optimizer, T_0=5, T_mult=2)
plt.figure()
max_epoch = 50
iters = 200
cur_lr_list = []
for epoch in range(max_epoch):
    for batch in range(iters):
        optimizer.step()
        scheduler.step()
    cur_lr = optimizer.param_groups[-1]['lr']
    cur_lr_list.append(cur_lr)
    print('Cur lr:', cur_lr)
x_list = list(range(len(cur_lr_list)))
plt.plot(x_list, cur_lr_list)
plt.show()

mode = 'OneCycleLR'
#mode = 'cosineAnn'
max_epoch = 500
iters = 200
if mode == 'cosineAnn':
    scheduler = CosineAnnealingLR(optimizer, T_max=5, eta_min=0.001)
elif mode == 'cosineAnnWarm':
    scheduler = CosineAnnealingWarmRestarts(optimizer, T_0=5, T_mult=2)
elif mode == 'OneCycleLR':
    scheduler = OneCycleLR(optimizer, max_lr=0.5, total_steps=max_epoch*iters)
plt.figure()
cur_lr_list = []
for epoch in range(max_epoch):
    for batch in range(iters):
        optimizer.step()
        scheduler.step()
    cur_lr = optimizer.param_groups[-1]['lr']
    cur_lr_list.append(cur_lr)
    #print('Cur lr:', cur_lr)
x_list = list(range(len(cur_lr_list)))
plt.plot(x_list, cur_lr_list)
plt.show()