P5：使用pytorch实现运动鞋识别

• 🍨 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
  我的环境
  语言环境：python 3.7.12
  编译器：pycharm
  深度学习环境：tensorflow 2.7.0
  数据：本地数据集-运动鞋
  

一、代码

# 1 设置GPU
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasetsimport os,PIL,pathlibdevice = torch.device("cuda" if torch.cuda.is_available() else "cpu")print(device)# 2 导入数据
import os,PIL,random,pathlibdata_dir = './data_sneakers/'
data_dir = pathlib.Path(data_dir)data_paths  = list(data_dir.glob('*'))
classeNames = [str(path).split("/")[1] for path in data_paths]
print(classeNames)
# 构建数据集
# 关于transforms.Compose的更多介绍可以参考：https://blog.csdn.net/qq_38251616/article/details/124878863
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_sneakers/train/",transform=train_transforms)
test_dataset  = datasets.ImageFolder("./data_sneakers/test/",transform=test_transform)train_dataset.class_to_idxbatch_size = 32train_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# 3 构建简单的CNN
import torch.nn.functional as Fclass 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*220nn.BatchNorm2d(12),nn.ReLU())self.conv2 = nn.Sequential(nn.Conv2d(12, 12, kernel_size=5, padding=0),  # 12*216*216nn.BatchNorm2d(12),nn.ReLU())self.pool3 = nn.Sequential(nn.MaxPool2d(2))  # 12*108*108self.conv4 = nn.Sequential(nn.Conv2d(12, 24, kernel_size=5, padding=0),  # 24*104*104nn.BatchNorm2d(24),nn.ReLU())self.conv5 = nn.Sequential(nn.Conv2d(24, 24, kernel_size=5, padding=0),  # 24*100*100nn.BatchNorm2d(24),nn.ReLU())self.pool6 = nn.Sequential(nn.MaxPool2d(2))  # 24*50*50self.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*50x = self.fc(x)return xdevice = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))model = Model().to(device)
print(model)# 4 训练模型
# 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losstrain_acc += (pred.argmax(1) == y).type(torch.float).sum().item()train_loss += loss.item()train_acc /= sizetrain_loss /= num_batchesreturn train_acc, train_loss# 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losstarget_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 /= sizetest_loss /= num_batchesreturn test_acc, test_loss
# 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 0.92lr = start_lr * (0.92 ** (epoch // 2))for param_group in optimizer.param_groups:param_group['lr'] = lrlearn_rate = 1e-4 # 初始学习率
optimizer  = torch.optim.SGD(model.parameters(), lr=learn_rate)# # 调用官方动态学习率接口时使用
# lambda1 = lambda epoch: (0.92 ** (epoch // 2))
# optimizer = torch.optim.SGD(model.parameters(), lr=learn_rate)
# scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda=lambda1) #选定调整方法# 5 训练
loss_fn = nn.CrossEntropyLoss()  # 创建损失函数
epochs = 40train_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')# 6 结果可视化
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()# 预测指定图片
from PIL import Imageclasses = 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_sneakers/test/adidas/1.jpg',model=model,transform=train_transforms,classes=classes)# 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))

二、结果

三、总结

3.1导入数据步骤

● 第一步：使用pathlib.Path()函数将字符串类型的文件夹路径转换为pathlib.Path对象。
● 第二步：使用glob()方法获取data_dir路径下的所有文件路径，并以列表形式存储在data_paths中。
● 第三步：通过split()函数对data_paths中的每个文件路径执行分割操作，获得各个文件所属的类别名称，并存储在classeNames中
● 第四步：打印classeNames列表，显示每个文件所属的类别名称。

3.2 模型结构

3.3训练函数与测试函数区别

由于测试不进行梯度下降对网络权重进行更新，所以不需要传入优化器

3.4动态学习率

1. torch.optim.lr_scheduler.StepLR

等间隔动态调整方法，每经过step_size个epoch，做一次学习率decay，以gamma值为缩小倍数。

函数原型：
torch.optim.lr_scheduler.StepLR(optimizer, step_size, gamma=0.1, last_epoch=-1)

关键参数详解：
● optimizer(Optimizer)：是之前定义好的需要优化的优化器的实例名
● step_size(int)：是学习率衰减的周期，每经过每个epoch，做一次学习率decay
● gamma(float)：学习率衰减的乘法因子。Default：0.1

用法示例：

optimizer = torch.optim.SGD(net.parameters(), lr=0.001 )
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.1)

2. lr_scheduler.LambdaLR

根据自己定义的函数更新学习率。

函数原型：
torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda, last_epoch=-1, verbose=False)

关键参数详解：
● optimizer(Optimizer)：是之前定义好的需要优化的优化器的实例名
● lr_lambda(function)：更新学习率的函数

用法示例：

lambda1 = lambda epoch: (0.92 ** (epoch // 2) # 第二组参数的调整方法
optimizer = torch.optim.SGD(model.parameters(), lr=learn_rate)
scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda=lambda1) #选定调整方法

3. lr_scheduler.MultiStepLR

在特定的 epoch 中调整学习率

函数原型：
torch.optim.lr_scheduler.MultiStepLR(optimizer, milestones, gamma=0.1, last_epoch=-1, verbose=False)

关键参数详解：
● optimizer(Optimizer)：是之前定义好的需要优化的优化器的实例名
● milestones(list)：是一个关于epoch数值的list，表示在达到哪个epoch范围内开始变化，必须是升序排列
● gamma(float)：学习率衰减的乘法因子。Default：0.1

用法示例：

optimizer = torch.optim.SGD(net.parameters(), lr=0.001 )
scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, milestones=[2,6,15], #调整学习率的epoch数gamma=0.1)

更多的官方动态学习率设置方式可参考：https://pytorch.org/docs/stable/optim.html
调用官方接口示例：

model = [Parameter(torch.randn(2, 2, requires_grad=True))]
optimizer = SGD(model, 0.1)
scheduler = ExponentialLR(optimizer, gamma=0.9)for epoch in range(20):for input, target in dataset:optimizer.zero_grad()output = model(input)loss = loss_fn(output, target)loss.backward()optimizer.step()scheduler.step()