P4 Pytorch入门实战——猴痘病识别

• 🍨 本文為🔗365天深度學習訓練營 中的學習紀錄博客
• 🍖 原作者：K同学啊 | 接輔導、項目定制

一、前期准备

1. 设置device

# import the necessary libraries
import torch 
import torch.nn as nn
import torch.nn.functional as F
from torchinfo import summary
import torchvision
import torchvision.transforms as transforms
from torchvision import transforms, datasets
import numpy as np
import matplotlib.pyplot as plt
import os,PIL,pathlib,random
from PIL import Image
#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

# 设置硬件设备，如果有GPU则使用，没有则使用cpu
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device

 2. 导入数据 

# load the data
data_dir = './data/4_data/'
data_dir = pathlib.Path(data_dir)

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

 3. 数据样例可视化

total_datadir = './data/4_data/'

train_transforms = 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。
])

total_data = datasets.ImageFolder(total_datadir,transform=train_transforms)
total_data

total_data.class_to_idx是一个存储了数据集类别和对应索引的字典。在PyTorch的ImageFolder数据加载器中，根据数据集文件夹的组织结构，每个文件夹代表一个类别，class_to_idx字典将每个类别名称映射为一个数字索引。

具体来说，如果数据集文件夹包含两个子文件夹，比如Monkeypox和Others，class_to_idx字典将返回类似以下的映射关系：{'Monkeypox': 0, 'Others': 1}

total_data.class_to_idx

4. 划分数据集

# Split the data into training and testing
train_size = int(0.8 * len(total_data))
test_size  = len(total_data) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size])
train_dataset, test_dataset

train_size, test_size

# Create the dataloaders
batch_size = 32

train_dl = torch.utils.data.DataLoader(train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True,
                                           num_workers=0)
test_dl = torch.utils.data.DataLoader(test_dataset,
                                          batch_size=batch_size,
                                          shuffle=True,
                                          num_workers=0)

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

二、构建简单的CNN网络  

class Network_bn(nn.Module):
    def __init__(self):
        super(Network_bn, self).__init__()
        """
        nn.Conv2d()函数：
        第一个参数（in_channels）是输入的channel数量
        第二个参数（out_channels）是输出的channel数量
        第三个参数（kernel_size）是卷积核大小
        第四个参数（stride）是步长，默认为1
        第五个参数（padding）是填充大小，默认为0
        """
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=5, stride=1, padding=0)
        self.bn1 = nn.BatchNorm2d(12)
        self.conv2 = nn.Conv2d(in_channels=12, out_channels=12, kernel_size=5, stride=1, padding=0)
        self.bn2 = nn.BatchNorm2d(12)
        self.pool = nn.MaxPool2d(2,2)
        self.conv4 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=5, stride=1, padding=0)
        self.bn4 = nn.BatchNorm2d(24)
        self.conv5 = nn.Conv2d(in_channels=24, out_channels=24, kernel_size=5, stride=1, padding=0)
        self.bn5 = nn.BatchNorm2d(24)
        self.fc1 = nn.Linear(24*50*50, len(classeNames))

    def forward(self, x):
        x = F.relu(self.bn1(self.conv1(x)))      
        x = F.relu(self.bn2(self.conv2(x)))     
        x = self.pool(x)                        
        x = F.relu(self.bn4(self.conv4(x)))     
        x = F.relu(self.bn5(self.conv5(x)))  
        x = self.pool(x)                        
        x = x.view(-1, 24*50*50)
        x = self.fc1(x)

        return x

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

model = Network_bn().to(device)
model

三、 训练模型

1. 设置超参数

# Define the loss function and optimizer
loss_fn    = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 1e-4 # 学习率
opt        = torch.optim.SGD(model.parameters(),lr=learn_rate)

 2. 编写训练函数

# Train the model
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  # 训练集的大小，一共1713张图片
    num_batches = len(dataloader)   # 批次数目，54（1713/32）

    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

3. 编写测试函数

# Test the model
def test (dataloader, model, loss_fn):
    size        = len(dataloader.dataset)  # 测试集的大小，一共429张图片
    num_batches = len(dataloader)          # 批次数目，14（429/32=13.4，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

4. 正式训练

epochs     = 20
train_loss = []
train_acc  = []
test_loss  = []
test_acc   = []

for epoch in range(epochs):
    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)
    
    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)
    
    template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%，Test_loss:{:.3f}')
    print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))
print('Done')

四、 结果可视化

1. Loss与Accuracy图

# Plot the loss and accuracy
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

# Predict the class of an image
classes = list(total_data.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/4_data/Monkeypox/M01_01_00.jpg', 
                  model=model, 
                  transform=train_transforms, 
                  classes=classes)

五、保存并加载模型 

# Save and load the model
# 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))

六、模型改进

1. 训练模型调整

此处使用了Resnet18, 并保存了最好的测试集结果

from torchvision import models

model = models.resnet18(pretrained=True)

# Modify the final layer to match the number of classes
num_ftrs = model.fc.in_features
model.fc = nn.Linear(num_ftrs, len(classeNames))
model = model.to(device)

2. 添加动态学习率

利用lr_scheduler，让学习率每10个epoch减少到原来的50%

# Adding a learning rate scheduler
import torch.optim as optim
from torch.optim import lr_scheduler

model = ImprovedNetwork().to(device)
loss_fn = nn.CrossEntropyLoss()
opt = torch.optim.SGD(model.parameters(), lr=learn_rate, momentum=0.9, weight_decay=5e-4)

# Decay LR by a factor of 0.1 every 10 epochs
scheduler = lr_scheduler.StepLR(opt, step_size=10, gamma=0.5)

3. 训练新的模型

测试集结果得到了很大的提升，准确率达到了95%

import copy
def train_model(model, dataloaders, loss_fn, optimizer, scheduler, num_epochs=25):
    best_model_wts = copy.deepcopy(model.state_dict())
    best_acc = 0.0
    train_acc_history = []
    val_acc_history = []
    
    for epoch in range(num_epochs):
        print(f'Epoch {epoch+1}/{num_epochs}')
        print('-' * 10)
        
        # Each epoch has a training and validation phase
        for phase in ['train', 'val']:
            if phase == 'train':
                model.train()  # Training mode
                dataloader = dataloaders['train']
            else:
                model.eval()   # Evaluation mode
                dataloader = dataloaders['val']
                
            running_loss = 0.0
            running_corrects = 0
            
            # Iterate over data
            for inputs, labels in dataloader:
                inputs = inputs.to(device)
                labels = labels.to(device)
                
                # Zero the parameter gradients
                optimizer.zero_grad()
                
                # Forward pass
                with torch.set_grad_enabled(phase == 'train'):
                    outputs = model(inputs)
                    _, preds = torch.max(outputs, 1)
                    loss = loss_fn(outputs, labels)
                    
                    # Backward and optimize only if in training phase
                    if phase == 'train':
                        loss.backward()
                        optimizer.step()
                        
                # Statistics
                running_loss += loss.item() * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)
                
            if phase == 'train':
                scheduler.step()
                
            epoch_loss = running_loss / len(dataloader.dataset)
            epoch_acc = running_corrects.double() / len(dataloader.dataset)
            
            print(f'{phase} Loss: {epoch_loss:.4f} Acc: {epoch_acc:.4f}')
            
            # Deep copy the model if it has better accuracy
            if phase == 'val' and epoch_acc > best_acc:
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict())
                
            if phase == 'train':
                train_acc_history.append(epoch_acc)
            else:
                val_acc_history.append(epoch_acc)
                
        print()
    
    print(f'Best Validation Accuracy: {best_acc:.4f}')
    
    # Load best model weights
    model.load_state_dict(best_model_wts)
    return model, train_acc_history, val_acc_history


dataloaders = {
    'train': train_dl,
    'val': test_dl
}

num_epochs = 20
model, train_acc_history, val_acc_history = train_model(
    model, dataloaders, loss_fn, optimizer, scheduler, num_epochs=num_epochs)