Pytorch学习--神经网络--优化器

一、头文件

torch.optim.Optimizer(params, defaults)
optim文档

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

二、代码

不带优化器的代码框架

import torch
import torchvision
from torch import nn
from torch.nn import MaxPool2d, Conv2d, Flatten, Linear
from torch.utils.data import DataLoader

dataset = torchvision.datasets.CIFAR10("datasets",train=False,transform=torchvision.transforms.ToTensor(),download=True)
dataloader = DataLoader(dataset,batch_size=1)

class Mary(nn.Module):
    def __init__(self):
        super(Mary,self).__init__()
        self.model1 = nn.Sequential(
            Conv2d(3, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 64, 5, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            Linear(64, 10)
        )
    def forward(self,x):
        x = self.model1(x)
        return x

Yorelee = Mary()
loss = nn.CrossEntropyLoss()
optim = torch.optim.SGD(Yorelee.parameters(),lr=0.01)


for epoch in range(20):
    total_loss = 0
    for data in dataloader:
        img,target = data
        output = Yorelee(img)
        # print(output)
        # print(target)

        result_loss = loss(output,target)
        # print(result_loss)
        # print("***********************")

        optim.zero_grad()
        result_loss.backward()
        optim.step()
        total_loss += result_loss
    print(total_loss)

输出：

tensor(18861.5215, grad_fn=<AddBackward0>)
tensor(16226.8633, grad_fn=<AddBackward0>)
tensor(15367.2148, grad_fn=<AddBackward0>)