使用pytorch对CIFAR-10数据集练习完整的模型训练，测试

训练过程

代码

1. nn.py

import torch
import torchvision.datasets
from torch.nn import CrossEntropyLoss
from torch.optim import SGD
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

from model import *
# 定义训练的设备
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# 1.获取数据
train_data = torchvision.datasets.CIFAR10('data', True, torchvision.transforms.ToTensor(), download=True)
test_data = torchvision.datasets.CIFAR10('data', False, torchvision.transforms.ToTensor(), download=True)
# 获取训练、测试数据的长度
train_data_size = len(train_data)
test_data_size = len(test_data)

# 2.加载数据
train_dataloader = DataLoader(train_data, 64)
test_dataloader = DataLoader(test_data, 64)

# 创建网络模型
tudui = Tudui()
tudui.to(device)

# 创建损失函数
loss_fn = CrossEntropyLoss()
loss_fn.to(device)
# 创建优化器
learning_rate = 0.01
optimizer = SGD(tudui.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
# 训练的轮数
epoch = 10

# 添加tensorboard
writer = SummaryWriter('logs')

for i in range(epoch):
    print('-------第{}轮训练开始-------'.format(i))
    # 训练步骤开始
    tudui.train()
    for data in train_dataloader:
        imgs, targets = data
        imgs = imgs.to(device)
        targets = targets.to(device)
        outputs = tudui(imgs)
        # 计算损失
        loss = loss_fn(outputs, targets)
        # 优化器优化模型
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        # 使用print和tensorboard显示效果
        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
    tudui.eval()
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            imgs = imgs.to(device)
        	targets = targets.to(device)
            outputs = tudui(imgs)
            loss = loss_fn(outputs, targets)  # tensor类型
            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 / test_data_size))
    writer.add_scalar('test_loss', total_test_loss, total_test_step)
    total_test_step += 1

    # 整体一轮训练保存一次模型
    torch.save(tudui, 'tudui_{}.pth'.format(i))
writer.close()

2. model.py

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

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

if __name__ == '__main__':
    # 测试
    tudui = Tudui()
    input = torch.ones((64, 3, 32, 32))
    output = tudui(input)
    print(output)

3. 最后我们可以在tensorboard上查看，则在Terminal控制台输入命令：tensorboard --logdir "logs"

测试、验证

1. test.py

'''
    模型验证
'''
import torch
import torchvision.transforms
from PIL import Image
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Linear, Flatten

# 准备测试的图片
img_path = 'imgs/airplane.png'
image = Image.open(img_path)
# print(image)
# torchvision.transforms.Resize((32,32)是为了与训练模型图片大小相对应
transform = torchvision.transforms.Compose([torchvision.transforms.Resize((32,32)),
                                            torchvision.transforms.ToTensor()])
image = transform(image)
# print(image.shape)

# class Tudui(nn.Module):
#     def __init__(self):
#         super(Tudui, self).__init__()
#         self.model = Sequential(
#             Conv2d(3, 32, 5, padding=2),
#             MaxPool2d(kernel_size=2),
#             Conv2d(32, 32, 5, padding=2),
#             MaxPool2d(kernel_size=2),
#             Conv2d(32, 64, 5, padding=2),
#             MaxPool2d(kernel_size=2),
#             Flatten(),
#             Linear(1024, 64),
#             Linear(64, 10)
#         )
#     def forward(self, input):
#         return self.model(input)
# 加载模型，已经训练好的模型，但由于训练次数少，可能结果不准确
# map_location：当我们训练模型使用GPU，此时使用CPU测试，则需要添加这个参数
model = torch.load('tudui_9.pth', map_location=torch.device('cpu'))
# print(model)
# 继续调图片格式
image = torch.reshape(image, (1, 3, 32, 32))
# 开始测试
model.eval()
with torch.no_grad():
    output = model(image)
# print(output)
print(output.argmax(1))