深度学习基础知识 学习率调度器的用法解析

1、自定义学习率调度器**：**torch.optim.lr_scheduler.LambdaLR

实验代码：

import torch
import torch.nn as nndef lr_lambda(x):return x*2net=nn.Sequential(nn.Conv2d(3,16,3,1,1))optimizer=torch.optim.SGD(net.parameters(),lr=0.01,momentum=0.9)lr_scheduler=torch.optim.lr_scheduler.LambdaLR(optimizer,lr_lambda=lr_lambda)for _ in range(10):optimizer.step()lr_scheduler.step()print(optimizer.param_groups[0]['lr'])

打印结果：

分析数据变化如下图所示：

2、正儿八经的模型搭建流程以及学习率调度器的使用设置

代码：

import torch
import torch.nn as nn
import numpy as npdef create_lr_scheduler(optimizer,num_step:int,epochs:int,warmup=True,warmup_epochs=1,warmup_factor=1e-3):assert num_step>0 and epochs>0if warmup is False:warmup_epochs=0def f(x):"""根据step数,返回一个学习率倍率因子，注意在训练开始之前,pytorch会提前调用一次create_lr_scheduler.step()方法"""if warmup is True and x <= (warmup_epochs * num_step):alpha=float(x) / (warmup_epochs * num_step)# warmup过程中，学习率因子(learning rate factor)：warmup_factor -----> 1return warmup_factor * (1-alpha) + alphaelse:# warmup后，学习率因子(learning rate factor)：warmup_factor -----> 0return (1-(x - warmup_epochs * num_step) / (epochs-warmup_epochs * num_step)) ** 0.9return torch.optim.lr_scheduler.LambdaLR(optimizer,lr_lambda=f)net=nn.Sequential(nn.Conv2d(3,16,1,1))
optimizer=torch.optim.SGD(net.parameters(),lr=0.01,momentum=0.9)lr_scheduler=create_lr_scheduler(optimizer=optimizer,num_step=5,epochs=20,warmup=True)image=(np.random.rand(1,3,64,64)).astype(np.float32)
image_tensor=torch.tensor(image.copy(),dtype=torch.float32)
print(image.dtype)for epoch in range(20):net.train()predict=net(image_tensor)optimizer.zero_grad()optimizer.step()lr_scheduler.step()print(optimizer.param_groups[0]['lr'])   # 打印学习率变化情况