Pytorch学习系列05 | 实现运动鞋识别

PyTorch实现运动鞋识别

原创已于 2025-11-13 12:48:30 修改 · 465 阅读

2 ·

CC 4.0 BY-SA版权

文章标签：

#pytorch #python #机器学习

于 2025-11-13 12:41:26 首次发布

Pytorch学习专栏专栏收录该内容

5 篇文章

订阅专栏

🍨 本文为🔗365天深度学习训练营中的学习记录博客
🍖 原作者：K同学啊

一、思维导图总结

二、代码实现

1、设置GPU

若设备支持GPU就使用GPU,否则使用CPU

import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import torchvision
import torchvision.transforms as transforms
from torchvision import transforms, datasets
# 忽略来自 torch.cuda 的 pynvml 弃用警告
warnings.filterwarnings(
    "ignore",
    message="The pynvml package is deprecated.*",
    category=FutureWarning,
    module="torch.cuda"
)

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

device

device(type='cuda')

2、数据准备

2.1、识别数据路径

import os
import pathlib

# 查看当前工作路径（确认路径是否正确）
print("当前工作路径：", os.getcwd())

# 定义数据目录（建议用绝对路径更稳妥，相对路径依赖当前工作路径）
data_dir = './data/运动鞋数据集/'
data_dir = pathlib.Path(data_dir)

# 获取数据目录下的所有子路径（文件夹或文件）
data_paths = list(data_dir.glob('*'))

# 提取每个子路径的名称（即类别名，自动适配系统分隔符）
classeNames = [path.name for path in data_paths]
classeNames

当前工作路径： /root/365天训练营/Pytorch实战
['test', 'train']

2.2、获取数据

data_dir = './data/运动鞋数据集/'

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("./data/运动鞋数据集/train/",transform=train_transforms)
test_dataset  = datasets.ImageFolder("./data/运动鞋数据集/test/",transform=test_transform)
train_dataset.class_to_idx

{'adidas': 0, 'nike': 1}

batch_size = 32

train_dl = torch.utils.data.DataLoader(train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True,
                                           num_workers=1)
test_dl = torch.utils.data.DataLoader(test_dataset,
                                          batch_size=batch_size,
                                          shuffle=True,
                                          num_workers=1)
for X, y in test_dl:
    print("Shape of X [N, C, H, W]: ", X.shape)
    print("Shape of y: ", y.shape, y.dtype)
    break

Shape of X [N, C, H, W]:  torch.Size([32, 3, 224, 224])
Shape of y:  torch.Size([32]) torch.int64

3、构建简单的CNN网络

import torch.nn.functional as F

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

Using cuda device

Model(
  (conv1): Sequential(
    (0): Conv2d(3, 12, kernel_size=(5, 5), stride=(1, 1))
    (1): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (2): ReLU()
  )
  (conv2): Sequential(
    (0): Conv2d(12, 12, kernel_size=(5, 5), stride=(1, 1))
    (1): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (2): ReLU()
  )
  (pool3): Sequential(
    (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (conv4): Sequential(
    (0): Conv2d(12, 24, kernel_size=(5, 5), stride=(1, 1))
    (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (2): ReLU()
  )
  (conv5): Sequential(
    (0): Conv2d(24, 24, kernel_size=(5, 5), stride=(1, 1))
    (1): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (2): ReLU()
  )
  (pool6): Sequential(
    (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (dropout): Sequential(
    (0): Dropout(p=0.2, inplace=False)
  )
  (fc): Sequential(
    (0): Linear(in_features=60000, out_features=2, bias=True)
  )
)

4、训练模型

4.1、训练函数

# 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

4.2、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

def adjust_learning_rate(optimizer, epoch, start_lr):
    # 每 2 个epoch衰减到原来的 0.92
    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)

4.3、正式训练

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')

Epoch: 1, Train_acc:52.8%, Train_loss:0.739, Test_acc:51.3%, Test_loss:0.690, Lr:1.00E-04
Epoch: 2, Train_acc:60.2%, Train_loss:0.675, Test_acc:63.2%, Test_loss:0.660, Lr:1.00E-04
Epoch: 3, Train_acc:65.9%, Train_loss:0.641, Test_acc:59.2%, Test_loss:0.704, Lr:9.20E-05
Epoch: 4, Train_acc:70.5%, Train_loss:0.589, Test_acc:67.1%, Test_loss:0.628, Lr:9.20E-05
Epoch: 5, Train_acc:73.3%, Train_loss:0.561, Test_acc:72.4%, Test_loss:0.617, Lr:8.46E-05
Epoch: 6, Train_acc:74.9%, Train_loss:0.521, Test_acc:72.4%, Test_loss:0.539, Lr:8.46E-05
Epoch: 7, Train_acc:74.5%, Train_loss:0.515, Test_acc:71.1%, Test_loss:0.561, Lr:7.79E-05
Epoch: 8, Train_acc:78.3%, Train_loss:0.483, Test_acc:68.4%, Test_loss:0.558, Lr:7.79E-05
Epoch: 9, Train_acc:80.7%, Train_loss:0.461, Test_acc:71.1%, Test_loss:0.522, Lr:7.16E-05
Epoch:10, Train_acc:82.1%, Train_loss:0.448, Test_acc:73.7%, Test_loss:0.531, Lr:7.16E-05
Epoch:11, Train_acc:82.5%, Train_loss:0.449, Test_acc:73.7%, Test_loss:0.528, Lr:6.59E-05
Epoch:12, Train_acc:85.1%, Train_loss:0.427, Test_acc:73.7%, Test_loss:0.510, Lr:6.59E-05
Epoch:13, Train_acc:85.9%, Train_loss:0.404, Test_acc:71.1%, Test_loss:0.540, Lr:6.06E-05
Epoch:14, Train_acc:87.5%, Train_loss:0.402, Test_acc:76.3%, Test_loss:0.504, Lr:6.06E-05
Epoch:15, Train_acc:88.4%, Train_loss:0.380, Test_acc:68.4%, Test_loss:0.503, Lr:5.58E-05
Epoch:16, Train_acc:86.3%, Train_loss:0.393, Test_acc:77.6%, Test_loss:0.483, Lr:5.58E-05
Epoch:17, Train_acc:88.6%, Train_loss:0.374, Test_acc:76.3%, Test_loss:0.513, Lr:5.13E-05
Epoch:18, Train_acc:89.8%, Train_loss:0.363, Test_acc:69.7%, Test_loss:0.511, Lr:5.13E-05
Epoch:19, Train_acc:90.6%, Train_loss:0.349, Test_acc:77.6%, Test_loss:0.489, Lr:4.72E-05
Epoch:20, Train_acc:89.8%, Train_loss:0.352, Test_acc:77.6%, Test_loss:0.492, Lr:4.72E-05
Epoch:21, Train_acc:89.4%, Train_loss:0.357, Test_acc:77.6%, Test_loss:0.458, Lr:4.34E-05
Epoch:22, Train_acc:90.4%, Train_loss:0.340, Test_acc:76.3%, Test_loss:0.512, Lr:4.34E-05
Epoch:23, Train_acc:91.4%, Train_loss:0.335, Test_acc:71.1%, Test_loss:0.536, Lr:4.00E-05
Epoch:24, Train_acc:91.4%, Train_loss:0.329, Test_acc:71.1%, Test_loss:0.514, Lr:4.00E-05
Epoch:25, Train_acc:92.2%, Train_loss:0.320, Test_acc:78.9%, Test_loss:0.543, Lr:3.68E-05
Epoch:26, Train_acc:91.2%, Train_loss:0.326, Test_acc:72.4%, Test_loss:0.510, Lr:3.68E-05
Epoch:27, Train_acc:92.0%, Train_loss:0.323, Test_acc:78.9%, Test_loss:0.451, Lr:3.38E-05
Epoch:28, Train_acc:93.4%, Train_loss:0.310, Test_acc:78.9%, Test_loss:0.520, Lr:3.38E-05
Epoch:29, Train_acc:92.8%, Train_loss:0.312, Test_acc:73.7%, Test_loss:0.517, Lr:3.11E-05
Epoch:30, Train_acc:93.8%, Train_loss:0.308, Test_acc:73.7%, Test_loss:0.487, Lr:3.11E-05
Epoch:31, Train_acc:92.4%, Train_loss:0.306, Test_acc:78.9%, Test_loss:0.447, Lr:2.86E-05
Epoch:32, Train_acc:93.4%, Train_loss:0.298, Test_acc:78.9%, Test_loss:0.491, Lr:2.86E-05
Epoch:33, Train_acc:94.6%, Train_loss:0.298, Test_acc:73.7%, Test_loss:0.494, Lr:2.63E-05
Epoch:34, Train_acc:92.6%, Train_loss:0.299, Test_acc:77.6%, Test_loss:0.482, Lr:2.63E-05
Epoch:35, Train_acc:92.6%, Train_loss:0.304, Test_acc:78.9%, Test_loss:0.478, Lr:2.42E-05
Epoch:36, Train_acc:93.8%, Train_loss:0.299, Test_acc:78.9%, Test_loss:0.565, Lr:2.42E-05
Epoch:37, Train_acc:93.4%, Train_loss:0.293, Test_acc:77.6%, Test_loss:0.485, Lr:2.23E-05
Epoch:38, Train_acc:92.8%, Train_loss:0.292, Test_acc:78.9%, Test_loss:0.473, Lr:2.23E-05
Epoch:39, Train_acc:94.6%, Train_loss:0.284, Test_acc:73.7%, Test_loss:0.466, Lr:2.05E-05
Epoch:40, Train_acc:94.8%, Train_loss:0.276, Test_acc:78.9%, Test_loss:0.506, Lr:2.05E-05
Done

5、结果可视化

5.1、Loss与Accuracy图

import matplotlib.pyplot as plt
#隐藏警告
import logging
logging.getLogger('matplotlib.font_manager').setLevel(logging.ERROR)
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

from datetime import datetime
current_time = datetime.now() # 获取当前时间

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.xlabel(current_time) # 打卡请带上时间戳，否则代码截图无效

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()

5.2、图片预测

from PIL import Image 

classes = list(train_dataset.class_to_idx)

def predict_one_image(image_path, model, transform, classes):
    
    test_img = Image.open(image_path).convert('RGB')
    # plt.imshow(test_img)  # 展示预测的图片

    test_img = transform(test_img)
    img = test_img.to(device).unsqueeze(0)
    
    model.eval()
    output = model(img)

    _,pred = torch.max(output,1)
    pred_class = classes[pred]
    print(f'预测结果是：{pred_class}')

# 预测训练集中的某张照片
predict_one_image(image_path='./data/运动鞋数据集/test/adidas/1.jpg', 
                  model=model, 
                  transform=train_transforms, 
                  classes=classes)

预测结果是：adidas

6、模型保存

# 模型保存
PATH = './model/model_p5.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))