class torch.optim.lr_scheduler.MultiplicativeLR

参考链接: class torch.optim.lr_scheduler.MultiplicativeLR(optimizer, lr_lambda, last_epoch=-1, verbose=False)
配套代码下载链接: 测试学习率调度器.zip

实验代码展示:

# torch.optim.lr_scheduler.MultiplicativeLR

import matplotlib.pyplot as plt
import numpy as np 
import torch
from torch.utils.data import Dataset, DataLoader
from torch import nn
from torch.autograd import Function
import random
import os
seed = 20200910
os.environ['PYTHONHASHSEED'] = str(seed)
torch.manual_seed(seed)
torch.cuda.manual_seed(seed)
torch.cuda.manual_seed_all(seed)  # if you are using multi-GPU.
np.random.seed(seed)  # Numpy module.
random.seed(seed)  # Python random module.
torch.manual_seed(seed)
torch.backends.cudnn.benchmark = False
torch.backends.cudnn.deterministic = True

class Dataset4cxq(Dataset):
    def __init__(self, length):
        self.length = length

    def __len__(self):
        return self.length
        
    def __getitem__(self, index):
        if type(index) != type(2) and type(index) != (slice):
           raise  TypeError('索引类型错误,程序退出...')
        
        # index 是单个数
        if type(index) == type(2):
            if index >= self.length or index < -1 * self.length:
                # print("索引越界,程序退出...")
                raise IndexError("索引越界,程序退出...")
            elif index < 0:
                index = index + self.length 
            
            Celsius = torch.randn(1,1,dtype=torch.float).item()
            Fahrenheit = 32.0 + 1.8 * Celsius
            return Celsius, Fahrenheit 
    
        
def collate_fn4cxq(batch):
    list_c = []
    list_f = []
    for c, f in batch:
        list_c.append(c)
        list_f.append(f)
    list_c = torch.tensor(list_c)
    list_f = torch.tensor(list_f)
    return list_c, list_f



if __name__ == "__main__":
    my_dataset = Dataset4cxq(32)
    # for c,f in my_dataset:
    #     print(type(c),type(f))
    dataloader4cxq = torch.utils.data.DataLoader(
        dataset=my_dataset, 
        batch_size=8,
        # batch_size=2,
        drop_last=True,
        # drop_last=False,
        shuffle=True,  #  True   False
        # shuffle=False,  #  True   False
        collate_fn=collate_fn4cxq,
        # collate_fn=None,
    )

    # for cnt, data in enumerate(dataloader4cxq, 0):
    #     # pass
    #     sample4cxq, label4cxq = data
    #     print('sample4cxq的类型: ',type(sample4cxq),'\tlabel4cxq的类型: ',type(label4cxq))
    #     print('迭代次数:', cnt, '  sample4cxq:', sample4cxq, '  label4cxq:', label4cxq)

    
    
    
    
    print('开始创建模型'.center(80,'-'))
    model = torch.nn.Linear(in_features=1, out_features=1, bias=True)  # True # False
    model.cuda()
    optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
    # 模拟华氏度与摄氏度之间的转换  
    # Fahrenheit = 32 + 1.8 * Celsius
    model.train()
    cost_function = torch.nn.MSELoss()
    epochs = 100001  # 100001
    epochs = 10001  # 100001
    print('\n')
    print('开始训练模型'.center(80,'-'))
    list4delta = list()
    list4epoch = list()
    
    # scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda=(lambda epoch: 0.99 ** (epoch//1000)))
    scheduler = torch.optim.lr_scheduler.MultiplicativeLR(optimizer, lr_lambda=lambda epoch: 0.9999)
    
    for epoch in range(epochs):
        # with torch.no_grad():
        #     Celsius = torch.randn(10,1,dtype=torch.float).cuda()
        #     Fahrenheit = 32.0 + 1.8 * Celsius
        #     Fahrenheit = Fahrenheit.cuda()

        # Celsius = torch.randn(1,1,dtype=torch.float,requires_grad=False).cuda()  # requires_grad=False  True
        # Fahrenheit = 32.0 + 1.8 * Celsius
        # Fahrenheit = Fahrenheit.cuda()        # requires_grad=False
        total_loss = 0.0
        for cnt, data in enumerate(dataloader4cxq, 0):
            Celsius, Fahrenheit = data
            Celsius, Fahrenheit = Celsius.cuda().view(-1,1), Fahrenheit.cuda().view(-1,1)
            output = model(Celsius)
            loss = cost_function(output, Fahrenheit)
            total_loss += loss.item()
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
        scheduler.step()
            
        if epoch % 100 == 0:  # if epoch % 1000 == 0:
            list4delta.append(total_loss)
            list4epoch.append(epoch)
            
        if epoch % 500 == 0:
            info = '\nepoch:{0:>6}/{1:<6}\t'.format(epoch,epochs)
            for k, v in model.state_dict().items():
                info += str(k)+ ':' + '{0:<.18f}'.format(v.item()) + '\t'
                # info += str(k)+ ':' + str(v.item()) + '\t'
            print(info)

    fig, ax = plt.subplots() 
    # ax.plot(10*np.random.randn(100),10*np.random.randn(100),'o')
    ax.plot(list4epoch, list4delta, 'r.-', markersize=8)
    ax.set_title("Visualization For My Model's Errors")
    plt.show()

控制台下输出:

Windows PowerShell
版权所有 (C) Microsoft Corporation。保留所有权利。

尝试新的跨平台 PowerShell https://aka.ms/pscore6

加载个人及系统配置文件用了 975 毫秒。
(base) PS C:\Users\chenxuqi\Desktop\News4cxq\测试学习率调度器>  & 'D:\Anaconda3\envs\pytorch_1.7.1_cu102\python.exe' 'c:\Users\chenxuqi\.vscode\extensions\ms-python.python-2021.1.502429796\pythonFiles\lib\python\debugpy\launcher' '49632' '--' 'c:\Users\chenxuqi\Desktop\News4cxq\测试学习率调度器\test07.py'
-------------------------------------开始创建模型-------------------------------------


-------------------------------------开始训练模型-------------------------------------

epoch:     0/10001      weight:0.962383031845092773     bias:0.980020046234130859       

epoch:   500/10001      weight:1.124128341674804688     bias:2.907210111618041992       

epoch:  1000/10001      weight:1.236593961715698242     bias:4.713542938232421875       

epoch:  1500/10001      weight:1.301697134971618652     bias:6.423601627349853516       

epoch:  2000/10001      weight:1.402245521545410156     bias:8.047979354858398438

epoch:  2500/10001      weight:1.433801174163818359     bias:9.591878890991210938

epoch:  3000/10001      weight:1.493452310562133789     bias:11.059674263000488281

epoch:  3500/10001      weight:1.611043691635131836     bias:12.455177307128906250

epoch:  4000/10001      weight:1.680250406265258789     bias:13.781544685363769531

epoch:  4500/10001      weight:1.701939225196838379     bias:15.042306900024414062

epoch:  5000/10001      weight:1.692690372467041016     bias:16.240627288818359375

epoch:  5500/10001      weight:1.709789514541625977     bias:17.379470825195312500

epoch:  6000/10001      weight:1.737799644470214844     bias:18.461750030517578125

epoch:  6500/10001      weight:1.771233677864074707     bias:19.490177154541015625

epoch:  7000/10001      weight:1.735638380050659180     bias:20.467247009277343750

epoch:  7500/10001      weight:1.764834642410278320     bias:21.395524978637695312

epoch:  8000/10001      weight:1.794731974601745605     bias:22.277175903320312500

epoch:  8500/10001      weight:1.788748979568481445     bias:23.114400863647460938

epoch:  9000/10001      weight:1.805634975433349609     bias:23.909339904785156250

epoch:  9500/10001      weight:1.778897523880004883     bias:24.663894653320312500

epoch: 10000/10001      weight:1.785784006118774414     bias:25.379871368408203125

运行结果截图: