​
🍨 本文为🔗365天深度学习训练营 中的学习记录博客
🍦 参考文章：Pytorch实战 | 第P5周：运动鞋识别
🍖 原作者：K同学啊|接辅导、项目定制

Z、心得体会：

• 本节的重点是：如何使用动态学习率

1. 可以定义设置动态学习率函数，加载到optimizer里面
2. 官方动态学习率接口如下：
   （1） lambda1 = lambda epoch: (0.92 ** (epoch // 20)) #第二组参数的调整方法
   （2）optimizer = torch.optim.SGD(model.parameters(), lr = learn_rate)
   （3）scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda=lambda1) #optimizer是之前定义好的优化器名称；选定调整方法
   PS： 最后使用scheduler.step()调用官方动态学习率

一、前期准备

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

device(type='cuda')

2. 导入数据

import os, PIL, random, pathlib

data_dir = 'C:/Users/Dell/Desktop/ML-K/P5/data/'
data_dir = pathlib.Path(data_dir)

data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split('\')[-1] for path in data_paths]
classeNames

['test', 'train']

train_transforms = transforms.Compose([
    transforms.Resize([224, 224]), #将图片resize成统一尺寸
    transforms.ToTensor(), #将PIL Image或numpy.ndarray转换成tensor，并归一化到[0, 1]之间
    transforms.Normalize( #标准化处理，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和std是从数据集中随机抽样计算得到的
])

test_transforms = transforms.Compose([
    transforms.Resize([224, 224]), #将图片resize成统一尺寸
    transforms.ToTensor(), #将PIL Image或numpy.ndarray转换成tensor，并归一化到[0, 1]之间
    transforms.Normalize( #标准化处理，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和std是从数据集中随机抽样计算得到的
])

train_dataset = datasets.ImageFolder('C:/Users/Dell/Desktop/ML-K/P5/data/train/', transform = train_transforms)
test_dataset = datasets.ImageFolder('C:/Users/Dell/Desktop/ML-K/P5/data/test/', transform = train_transforms)

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

二、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),
            nn.BatchNorm2d(12),
            nn.ReLU())
        
        self.conv2 = nn.Sequential(
            nn.Conv2d(12, 12, kernel_size=5, padding = 0),
            nn.BatchNorm2d(12),
            nn.ReLU())
        
        self.pool3 = nn.Sequential(
            nn.MaxPool2d(2))
        
        self.conv4 = nn.Sequential(
            nn.Conv2d(12, 24, kernel_size=5, padding = 0),
            nn.BatchNorm2d(24),
            nn.ReLU())
        
        self.conv5 = nn.Sequential(
            nn.Conv2d(24, 24, kernel_size=5, padding = 0),
            nn.BatchNorm2d(24),
            nn.ReLU())
        
        self.pool6 = nn.Sequential(
            nn.MaxPool2d(2))
        
        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)
        x = self.conv2(x)
        x = self.pool3(x)
        x = self.conv4(x)
        x = self.conv5(x)
        x = self.pool6(x)
        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） 变为(batch, -1), -1此处自动计算出的是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)
  )
)

三、训练模型

1. 编写训练函数

def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    
    train_loss, train_acc = 0, 0
    
    for X, y in dataloader:
        X, y = X.to(device), y.to(device)
        
        pred = model(X)
        loss = loss_fn(pred, y)
        
        #反向传播
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
        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

2. 编写测试函数

def test(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    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) 
            
            target_pred = model(imgs)
            loss = loss_fn(target_pred, target)
        
            test_acc += (target_pred.argmax(1) == target).type(torch.float).sum().item()
            test_loss += loss.item()
        
    test_acc /= size
    test_loss /= num_batches
    
    return test_acc, test_loss

3. 设置动态学习率

#设置动态学习率
def adjust_learning_rate(optimizer, epoch, start_lr):
    #每两个epoch衰减到原来的0.98
    lr = start_lr * (0.98 ** (epoch // 2)) # //的意思是相除后向下取整
    for param_group in optimizer.param_groups:
        param_group['lr'] = lr
        
learn_rate = 1e-4
optimizer = torch.optim.SGD(model.parameters(), lr = learn_rate)

#官方的动态学习率接口使用：
lambda1 = lambda epoch: (0.92 ** (epoch // 20))
optimizer = torch.optim.SGD(model.parameters(), lr = learn_rate)
scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda=lambda1)

4. 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
    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')

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
    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')

四、结果可视化

1. Loss和Accuracy图

import matplotlib.pyplot as plt

import warnings
warnings.filterwarnings('ignore')
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

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()

2. 指定图片进行预测

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}')

predict_one_image(image_path='C:/Users/Dell/Desktop/ML-K/P5/data/test/adidas/1.jpg',
                model = model,
                transform = train_transforms,
                classes = classes)

预测结果是：adidas

五、保存并加载模型

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

model.load_state_dict(torch.load(PATH, map_location=device))

<All keys matched successfully>