NN第一个网络训练模型

本文的主要目的是针对初学者，完成第一个网络模型训练的操作示意，在此基础上，后学者可以按照套路训练不同的模型。 代码如下：

import torch
import torch.nn as nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Linear, Flatten


# 定义网络
class MyCifar10(nn.Module):
    def __init__(self):
        super(MyCifar10, self).__init__()
        self.model = Sequential(
            Conv2d(3, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, kernel_size=5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 64, kernel_size=5, padding=2),
            MaxPool2d(2),
            Flatten(),
            # 64*4*4
            Linear(64 * 4 * 4, 64),
            Linear(64, 10)
        )

    def forward(self, x):
        return self.model(x)

# 测试网络
if __name__ == '__main__':
    model = MyCifar10()
    input = torch.ones(64, 3, 32, 32)
    output = model(input)
    print(output.shape)

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

import torch.nn as nn
from torch.utils.tensorboard import SummaryWriter

from MyCifar10Model import MyCifar10

# 用cifar10的测试和训练集数据
train_data = torchvision.datasets.CIFAR10("cifar10", train=True, transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10("cifar10", train=False, transform=torchvision.transforms.ToTensor(),
                                         download=True)

train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)

# create net model
model = MyCifar10()

# define loss func
loss_fn = nn.CrossEntropyLoss()

# optimizer
learn_rate = 1e-2
optimizer = torch.optim.SGD(model.parameters(), learn_rate)

epochs = 2
train_step = 0
test_step = 0

# 画图
writer = SummaryWriter("log7")

# 只针对一些特殊的层起作用
model.train()
for i in range(epochs):
    print(">>>>>>>>>>>>>>>>第{}轮训练开始".format(i+1))

    for data in train_dataloader:
        imgs, targets = data
        outputs = model(imgs)

        #  优化器
        loss = loss_fn(outputs, targets)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        train_step +=1
        if train_step % 100 == 0:
            print("----------训练次数{}, loss:{}".format(train_step, loss.item()))
            writer.add_scalar("train_loss", loss.item(), train_step)

    # 测试
    # eval也只是针对特殊的层起作用
    model.eval()
    total_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            outputs = model(imgs)
            loss = loss_fn(outputs, targets)
            total_loss += loss.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            total_accuracy += accuracy
    print("测试集上的loss:{}".format(total_loss))
    writer.add_scalar("test_loss", total_loss, test_step)
    writer.add_scalar("accuracy", total_accuracy, test_step)
    test_step +=1

    # 保存每一轮训练的模型
    torch.save(model, "modules/my_model_{}".format(i))

writer.close()

参考：完整的模型训练套路（三）_哔哩哔哩_bilibili