完整的模型训练套路

最新推荐文章于 2024-06-27 10:13:18 发布

JpegMaf1a

最新推荐文章于 2024-06-27 10:13:18 发布

阅读量320

点赞数 3

文章标签： python 深度学习机器学习

本文链接：https://blog.csdn.net/2301_79718375/article/details/138869852

版权

以CIFAR10数据集为例

搭建神经网络，作为一个模块

model.py

import torch
from torch import nn


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.model = nn.Sequential(
            # 进行卷积和池化
            nn.Conv2d(3, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, 5, 1, 2),
            nn.MaxPool2d(2),
            # 展平
            nn.Flatten(),
            # 全连接层
            nn.Linear(64 * 4 * 4, 64),
            nn.Linear(64, 10)
        )

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


if __name__ == '__main__':
    net = Net()
    input = torch.ones((64, 3, 32, 32))
    output = net(input)
    print(output.shape)

train.py

import torch
import torchvision
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

from model1 import *

train_data = torchvision.datasets.CIFAR10(root="data", train=True, transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10(root="data", train=False, transform=torchvision.transforms.ToTensor(),
                                         download=True)
# length长度
train_data_size = len(train_data)
test_data_size = len(test_data)
# 如果train_data_size=10，训练数据集的长度为：10
print(f"训练数据集的长度为:{train_data_size}")
print(f"训练数据集的长度为：{test_data_size}")

# 利用DataLoader来加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)

# 创建网络模型
net = Net()

# 损失函数
loss_fn = nn.CrossEntropyLoss()

# 优化器
# learning_rate = 0.01
# 1e-2=1 x (10)^(-2) = 1/100 = 0.01
learning_rate = 1e-2
optimizer = torch.optim.SGD(net.parameters(), lr=learning_rate)

# 设置训练网络的一些参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练的轮次
epoch = 10

# 添加TensorBoard
writer = SummaryWriter("logs_train")

for i in range(epoch):
    print(f"------第{i+1}轮训练开始------")

    # 训练步骤开始
    # 把网络设置为训练模式
    net.train()
    for data in train_dataloader:
        imgs, targets = data
        outputs = net(imgs)
        #计算损失值
        loss = loss_fn(outputs, targets)
        #梯度清零
        optimizer.zero_grad()
        #反向传播
        loss.backward()
        optimizer.step()

        total_train_step = total_train_step + 1
        # 每训练100次再输出
        if total_train_step % 100 == 0:
            print(f"训练次数：{total_train_step},Loss：{loss}")
            writer.add_scalar("train_loss", loss.item(), total_train_step)

    # 测试步骤开始
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            outputs = net(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss = total_test_loss + loss.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            total_accuracy = total_accuracy + accuracy

        print(f"整体测试集上的Loss：{total_test_loss}")
        print(f"整体测试集上的正确率：{total_accuracy/test_data_size}")
        writer.add_scalar("test_loss", total_test_loss, total_test_step)
        writer.add_scalar("test_accuracy", total_accuracy/test_data_size, total_test_step)
        total_test_step += 1
        #每轮训练结束保存模型
        torch.save(net, f"net_{i}.pth")
        print("模型已保存")

writer.close()