class torch.optim.lr_scheduler.LambdaLR
参考链接: class torch.optim.lr_scheduler.LambdaLR(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:
# torch.optim.lr_scheduler.LambdaLR
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)))
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 926 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' '49464' '--' 'c:\Users\chenxuqi\Desktop\News4cxq\测试学习率调度器\test06.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:1.129050374031066895 bias:2.955143213272094727
epoch: 1000/10001 weight:1.249524116516113281 bias:4.898723125457763672
epoch: 1500/10001 weight:1.320719122886657715 bias:6.810392856597900391
epoch: 2000/10001 weight:1.434252023696899414 bias:8.715221405029296875
epoch: 2500/10001 weight:1.468232393264770508 bias:10.594973564147949219
epoch: 3000/10001 weight:1.536670327186584473 bias:12.468175888061523438
epoch: 3500/10001 weight:1.680503368377685547 bias:14.315374374389648438
epoch: 4000/10001 weight:1.758755326271057129 bias:16.153095245361328125
epoch: 4500/10001 weight:1.769892215728759766 bias:17.961753845214843750
epoch: 5000/10001 weight:1.744580507278442383 bias:19.756875991821289062
epoch: 5500/10001 weight:1.757981419563293457 bias:21.517288208007812500
epoch: 6000/10001 weight:1.790049910545349121 bias:23.255580902099609375
epoch: 6500/10001 weight:1.826546669006347656 bias:24.947116851806640625
epoch: 7000/10001 weight:1.756798028945922852 bias:26.596363067626953125
epoch: 7500/10001 weight:1.809650421142578125 bias:28.166427612304687500
epoch: 8000/10001 weight:1.825483560562133789 bias:29.631296157836914062
epoch: 8500/10001 weight:1.800792336463928223 bias:30.888553619384765625
epoch: 9000/10001 weight:1.800277113914489746 bias:31.746377944946289062
epoch: 9500/10001 weight:1.799844503402709961 bias:31.993532180786132812
epoch: 10000/10001 weight:1.800002932548522949 bias:31.999877929687500000
运行结果截图:
