学习pytorch15 优化器

优化器

官网
如何构造一个优化器
优化器的step方法
code
[running log](#running log)
- 出现下面问题如何做反向优化？

官网

https://pytorch.org/docs/stable/optim.html

提问：优化器是什么要优化什么优化能干什么优化是为了解决什么问题

优化模型参数

如何构造一个优化器

py 复制代码

optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9)  # momentum SGD优化算法用到的参数
optimizer = optim.Adam([var1, var2], lr=0.0001)

选择一个优化器算法，如上 SGD 或者 Adam
第一个参数需要传入模型参数
第二个及后面的参数是优化器算法特定需要的，lr 学习率基本每个优化器算法都会用到

优化器的step方法

会利用模型的梯度，根据梯度每一轮更新参数
optimizer.zero_grad() # 必须做把上一轮计算的梯度清零，否则模型会有问题

py 复制代码

for input, target in dataset:
    optimizer.zero_grad()  # 必须做 把上一轮计算的梯度清零，否则模型会有问题
    output = model(input)
    loss = loss_fn(output, target)
    loss.backward()
    optimizer.step()

or 把模型梯度包装成方法再调用

py 复制代码

for input, target in dataset:
    def closure():
        optimizer.zero_grad()
        output = model(input)
        loss = loss_fn(output, target)
        loss.backward()
        return loss
    optimizer.step(closure)

code

py 复制代码

import torch
import torchvision
from torch import nn, optim
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

test_set = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor(),
                                        download=True)

dataloader = DataLoader(test_set, batch_size=1)

class MySeq(nn.Module):
    def __init__(self):
        super(MySeq, self).__init__()
        self.model1 = Sequential(Conv2d(3, 32, kernel_size=5, stride=1, padding=2),
                                 MaxPool2d(2),
                                 Conv2d(32, 32, kernel_size=5, stride=1, padding=2),
                                 MaxPool2d(2),
                                 Conv2d(32, 64, kernel_size=5, stride=1, padding=2),
                                 MaxPool2d(2),
                                 Flatten(),
                                 Linear(1024, 64),
                                 Linear(64, 10)
                                 )

    def forward(self, x):
        x = self.model1(x)
        return x

# 定义loss
loss = nn.CrossEntropyLoss()
# 搭建网络
myseq = MySeq()
print(myseq)
# 定义优化器
optmizer = optim.SGD(myseq.parameters(), lr=0.001, momentum=0.9)
for epoch in range(20):
    running_loss = 0.0
    for data in dataloader:
        imgs, targets = data
        # print(imgs.shape)
        output = myseq(imgs)
        optmizer.zero_grad()  # 每轮训练将梯度初始化为0  上一次的梯度对本轮参数优化没有用
        result_loss = loss(output, targets)
        result_loss.backward()  # 优化器需要每个参数的梯度， 所以要在backward() 之后执行
        optmizer.step()  # 根据梯度对每个参数进行调优
        # print(result_loss)
        # print(result_loss.grad)
        # print("ok")
        running_loss += result_loss
    print(running_loss)

running log

loss由小变大最后到nan的解决办法：

降低学习率
使用正则化技术
增加训练数据
检查网络架构和激活函数

出现下面问题如何做反向优化？

sh 复制代码

Files already downloaded and verified
MySeq(
  (model1): Sequential(
    (0): Conv2d(3, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (4): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (5): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (6): Flatten(start_dim=1, end_dim=-1)
    (7): Linear(in_features=1024, out_features=64, bias=True)
    (8): Linear(in_features=64, out_features=10, bias=True)
  )
)
tensor(18622.4551, grad_fn=<AddBackward0>)
tensor(16121.4092, grad_fn=<AddBackward0>)
tensor(15442.6416, grad_fn=<AddBackward0>)
tensor(16387.4531, grad_fn=<AddBackward0>)
tensor(18351.6152, grad_fn=<AddBackward0>)
tensor(20915.9785, grad_fn=<AddBackward0>)
tensor(23081.5254, grad_fn=<AddBackward0>)
tensor(24841.8359, grad_fn=<AddBackward0>)
tensor(25401.1602, grad_fn=<AddBackward0>)
tensor(26187.4961, grad_fn=<AddBackward0>)
tensor(28283.8633, grad_fn=<AddBackward0>)
tensor(30156.9316, grad_fn=<AddBackward0>)
tensor(nan, grad_fn=<AddBackward0>)
tensor(nan, grad_fn=<AddBackward0>)
tensor(nan, grad_fn=<AddBackward0>)
tensor(nan, grad_fn=<AddBackward0>)
tensor(nan, grad_fn=<AddBackward0>)
tensor(nan, grad_fn=<AddBackward0>)
tensor(nan, grad_fn=<AddBackward0>)
tensor(nan, grad_fn=<AddBackward0>)