PyTorch入门4

完整的模型训练套路

一般把model放到单独的.py文件中，并在文件中对模型的正确性进行验证。

import torch
from torch import nn

# 搭建神经网络
class Ceshi(nn.Module):
    def __init__(self):
        super(Ceshi, self).__init__()
        self.model = nn.Sequential(
            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),
            nn.Flatten(),
            nn.Linear(1024, 64),
            nn.Linear(64, 10)
        )

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

if __name__ == '__main__':
    ceshi = Ceshi()
    # 验证模型的正确性
    input = torch.ones((64, 3, 32, 32))
    output = ceshi(input)
    print(output.shape)

 训练代码如下：

import torchvision
from torch.utils.data import DataLoader
# 引入model
from torch.utils.tensorboard import SummaryWriter
from model import *

# 准备数据集
train_data = torchvision.datasets.CIFAR10("./data1", train=True, transform=torchvision.transforms.ToTensor(), download=True)
test_data = torchvision.datasets.CIFAR10("./data1", train=False, transform=torchvision.transforms.ToTensor(), download=True)

# 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
ceshi = Ceshi()

# 损失函数
loss_fn = nn.CrossEntropyLoss()

# 优化器
learning_rate = 1e-2
optimaize = torch.optim.SGD(ceshi.parameters(), lr=learning_rate)

# 设置一些训练网络的参数
total_train_step = 0   # 训练次数
total_test_step = 0   # 测试次数
epoch = 10   # 训练轮数

# 添加tensorboard
writer = SummaryWriter("./logs_train")

for i in range(epoch):
    print("---------第{}轮训练开始---------".format(i+1))
    # 训练步骤开始
    ceshi.train()
    for data in train_dataloader:
        imgs, targets = data
        outputs = ceshi(imgs)
        loss = loss_fn(outputs, targets)
        # 优化器优化模型
        optimaize.zero_grad()
        loss.backward()
        optimaize.step()
        total_train_step += 1
        if total_train_step % 100 == 0:
            print("训练次数：{}  损失函数：{}".format(total_train_step, loss.item()))
            writer.add_scalar("train_loss", loss.item(), total_train_step)

    # 测试步骤开始
    ceshi.eval()
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            outputs = ceshi(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss += loss.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            total_accuracy += accuracy
    print("整体测试集上的Loss：{}".format(total_test_loss))
    print("整体测试集上的正确率：{}".format(total_accuracy/len(test_data)))
    writer.add_scalar("test_loss", total_test_loss, total_test_step)
    writer.add_scalar("test_accuracy", total_accuracy/len(test_data), total_test_step)
    total_test_step += 1
    if i == 9:
        torch.save(ceshi, "ceshi_{}.pth".format(i))
        print("模型已保存")

writer.close()

训练结果如下：

保存的模型：

可视化结果如下：

下面解释下train()和eval()：

        使用model.train()的作用是把网络设置成训练的模式，它只对部分的网络层有作用，比如Dropout层。当网络模型中有Dropout等这些层的时候可以调用model.train()：

        eval()的作用是把网络设置成验证的模式，同样只对部分网络层有作用：