CIFAR-10模型训练

利用上一篇文章搭建的卷积神经网络进行模型训练。

将搭建的卷积神经网络放在model.py中。

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


class Gao(nn.Module):
    def __init__(self):
        super(Gao, self).__init__()
        self.model = nn.Sequential(
            Conv2d(3, 32, 5, stride=1, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, stride=1, padding=2),
            MaxPool2d(2),
            Conv2d(32, 64, 5, stride=1, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            Linear(64, 10)
        )
    def forward(self, x):
        x = self.model(x)
        return x

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

下面是训练模型的主要代码：

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

from model import *
# 训练数据集
from torch import nn
from torch.utils.data import DataLoader

train_data = torchvision.datasets.CIFAR10(root="./data", train=True,
                                          transform=torchvision.transforms.ToTensor(),
                                          download=True)
# 测试数据集
test_data = torchvision.datasets.CIFAR10(root="./data", train=False,
                                         transform=torchvision.transforms.ToTensor(),
                                         download=True)

train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集的长度为：{}".format(train_data_size))
print("测试数据集的长度为：{}".format(test_data_size))
# 将数据加载进Dataloader
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)
# 创建神经网路
gao = Gao()
# 损失函数
loss_fn = nn.CrossEntropyLoss()
# 学习速率
learning_rate = 1e-2
# 优化器
optim = torch.optim.SGD(params=gao.parameters(), lr=learning_rate)
# 记录训练次数
total_train_step = 0
# 记录测试次数
total_test_step = 0
# 训练轮数
epoch = 10
# 添加tensorboard
writer = SummaryWriter("D:\\DeepLearning\\gao\\deep\\learning\\logs")
for i in range(epoch):
    print("--------第{}轮开始--------".format(i+1))
    # 训练步骤开始
    for data in train_dataloader:
        images, targets = data
        # 根据输出值计算损失函数
        outputs = gao(images)
        loss = loss_fn(outputs, targets)
        # 优化器调优模型
        optim.zero_grad()
        loss.backward()
        optim.step()
        total_train_step += 1
        if total_train_step % 100 == 0:
            print("训练次数{}，loss:{}".format(total_train_step, loss.item()))
            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:
            images, targets = data
            outputs = gao(images)
            loss = loss_fn(outputs, targets)
            total_test_loss += loss
            accuracy = (outputs.argmax(1) == targets).sum()
            total_accuracy += accuracy
    print("整体测试集上的loss:{}".format(total_test_loss))
    print("整体测试集上的accuracy:{}".format(total_accuracy/train_data_size))
    writer.add_scalar("test_loss", total_test_loss, total_test_step)
    writer.add_scalar("test_accuracy", total_accuracy/train_data_size, total_test_step)
    total_test_step += 1
    # torch.save(gao, "gao_{}".format(i))
    # print("模型已保存")

writer.close()

控制台输出如下：

打开tensorboard查看模型训练途中的具体数据变化情况：

下面分别是训练集的Loss、测试集的Loss、以及正确率的变化情况：