365天深度学习训练营-第P5周：运动鞋识别

目录

一、前言

 二、我的环境

三、代码实现

1、设置GPU

2、导入数据

3、构建CNN网络

4、训练代码

5、测试函数

6、设置动态学习率

7、开始训练

8、数据可视化

9、模型保存

四、代码优化

---

一、前言

>- ** 本文为[365天深度学习训练营](https://mp.weixin.qq.com/s/xLjALoOD8HPZcH563En8bQ) 中的学习记录博客**
>- ** 参考文章：365天深度学习训练营-第P5周：运动鞋识别（训练营内部成员可读）**
>- ** 原作者：[K同学啊|接辅导、项目定制](https://mtyjkh.blog.csdn.net/)**

● 难度：夯实基础⭐⭐
● 语言：Python3、Pytorch3
● 时间：12月15日-12月23日
要求：

了解如何设置动态学习率（重点）
调整代码使测试集accuracy到达84%。

拔高（可选）：

保存训练过程中的最佳模型权重
调整代码使测试集accuracy到达86%。

 二、我的环境

语言环境：Python3.7

编译器：jupyter notebook

深度学习环境：TensorFlow2

三、代码实现

1、设置GPU

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets

import os, PIL, pathlib

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

device

2、导入数据

# 导入数据
import os, PIL, random, pathlib

data_dir = './hy-tmp/5-data/'
data_dir = pathlib.Path(data_dir)

data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("\\")[2] for path in data_paths]
classeNames

train_transforms = transforms.Compose([
    transforms.Resize([224, 224]),  # 将输入图片resize成统一尺寸
    # transforms.RandomHorizontalFlip(), # 随机水平翻转
    transforms.ToTensor(),  # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
    transforms.Normalize(  # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛
        mean=[0.485, 0.456, 0.406],
        std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])

test_transform = transforms.Compose([
    transforms.Resize([224, 224]),  # 将输入图片resize成统一尺寸
    transforms.ToTensor(),  # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
    transforms.Normalize(  # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛
        mean=[0.485, 0.456, 0.406],
        std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])

train_dataset = datasets.ImageFolder("./hy-tmp/5-data/train/", transform=train_transforms)
test_dataset = datasets.ImageFolder("./hy-tmp/5-data/test/", transform=train_transforms)

train_dataset.class_to_idx

3、构建CNN网络

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 12, kernel_size=5, padding=0),  # 12*220*220
            nn.BatchNorm2d(12),
            nn.ReLU())

        self.conv2 = nn.Sequential(
            nn.Conv2d(12, 12, kernel_size=5, padding=0),  # 12*216*216
            nn.BatchNorm2d(12),
            nn.ReLU())

        self.pool3 = nn.Sequential(
            nn.MaxPool2d(2))  # 12*108*108

        self.conv4 = nn.Sequential(
            nn.Conv2d(12, 24, kernel_size=5, padding=0),  # 24*104*104
            nn.BatchNorm2d(24),
            nn.ReLU())

        self.conv5 = nn.Sequential(
            nn.Conv2d(24, 24, kernel_size=5, padding=0),  # 24*100*100
            nn.BatchNorm2d(24),
            nn.ReLU())

        self.pool6 = nn.Sequential(
            nn.MaxPool2d(2))  # 24*50*50

        self.dropout = nn.Sequential(
            nn.Dropout(0.2))

        self.fc = nn.Sequential(
            nn.Linear(24 * 50 * 50, len(classeNames)))

    def forward(self, x):
        batch_size = x.size(0)
        x = self.conv1(x)  # 卷积-BN-激活
        x = self.conv2(x)  # 卷积-BN-激活
        x = self.pool3(x)  # 池化
        x = self.conv4(x)  # 卷积-BN-激活
        x = self.conv5(x)  # 卷积-BN-激活
        x = self.pool6(x)  # 池化
        x = self.dropout(x)
        x = x.view(batch_size, -1)  # flatten 变成全连接网络需要的输入 (batch, 24*50*50) ==> (batch, -1), -1 此处自动算出的是24*50*50
        x = self.fc(x)

        return x


device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))

model = Model().to(device)
model

4、训练代码

# 训练循环
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  # 训练集的大小
    num_batches = len(dataloader)  # 批次数目, (size/batch_size，向上取整)

    train_loss, train_acc = 0, 0  # 初始化训练损失和正确率

    for X, y in dataloader:  # 获取图片及其标签
        X, y = X.to(device), y.to(device)

        # 计算预测误差
        pred = model(X)  # 网络输出
        loss = loss_fn(pred, y)  # 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失

        # 反向传播
        optimizer.zero_grad()  # grad属性归零
        loss.backward()  # 反向传播
        optimizer.step()  # 每一步自动更新

        # 记录acc与loss
        train_acc += (pred.argmax(1) == y).type(torch.float).sum().item()
        train_loss += loss.item()

    train_acc /= size
    train_loss /= num_batches

    return train_acc, train_loss

5、测试函数

# 测试函数
def test(dataloader, model, loss_fn):
    size = len(dataloader.dataset)  # 测试集的大小
    num_batches = len(dataloader)  # 批次数目, (size/batch_size，向上取整)
    test_loss, test_acc = 0, 0

    # 当不进行训练时，停止梯度更新，节省计算内存消耗
    with torch.no_grad():
        for imgs, target in dataloader:
            imgs, target = imgs.to(device), target.to(device)

            # 计算loss
            target_pred = model(imgs)
            loss = loss_fn(target_pred, target)

            test_loss += loss.item()
            test_acc += (target_pred.argmax(1) == target).type(torch.float).sum().item()

    test_acc /= size
    test_loss /= num_batches

    return test_acc, test_loss

6、设置动态学习率

# 设置动态学习率
def adjust_learning_rate(optimizer, epoch, start_lr):
    # 每 2 个epoch衰减到原来的 0.98
    lr = start_lr * (0.92 ** (epoch // 2))
    for param_group in optimizer.param_groups:
        param_group['lr'] = lr


learn_rate = 1e-4  # 初始学习率
optimizer = torch.optim.SGD(model.parameters(), lr=learn_rate)

7、开始训练

# 开始训练
loss_fn = nn.CrossEntropyLoss()  # 创建损失函数
epochs = 40

train_loss = []
train_acc = []
test_loss = []
test_acc = []

for epoch in range(epochs):
    # 更新学习率（使用自定义学习率时使用）
    adjust_learning_rate(optimizer, epoch, learn_rate)

    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
    # scheduler.step() # 更新学习率（调用官方动态学习率接口时使用）

    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)

    train_acc.append(epoch_train_acc)
    train_loss.append(epoch_train_loss)
    test_acc.append(epoch_test_acc)
    test_loss.append(epoch_test_loss)

    # 获取当前的学习率
    lr = optimizer.state_dict()['param_groups'][0]['lr']

    template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:.2E}')
    print(template.format(epoch + 1, epoch_train_acc * 100, epoch_train_loss,
                          epoch_test_acc * 100, epoch_test_loss, lr))
print('Done')

8、数据可视化

# 数据可视化
import matplotlib.pyplot as plt
#隐藏警告
import warnings
warnings.filterwarnings("ignore")               #忽略警告信息
plt.rcParams['font.sans-serif']    = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False      # 用来正常显示负号
plt.rcParams['figure.dpi']         = 100        #分辨率

epochs_range = range(epochs)

plt.figure(figsize=(12, 3))
plt.subplot(1, 2, 1)

plt.plot(epochs_range, train_acc, label='Training Accuracy')
plt.plot(epochs_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, label='Training Loss')
plt.plot(epochs_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

9、模型保存

# 模型保存
PATH = './model.pth'  # 保存的参数文件名
torch.save(model.state_dict(), PATH)

# 将参数加载到model当中
model.load_state_dict(torch.load(PATH, map_location=device))

四、代码优化

1、在中间一层池化层后加dropout，并将dropout的值改为0.15

2、改变初始学习率lr=2e-4

3、加卷积层和池化层多次训练