基于WIN10的64位系统演示

一、写在前面

上期我们基于TensorFlow环境做了图像识别的多分类任务建模。

本期以健康组、肺结核组、COVID-19组、细菌性（病毒性）肺炎组为数据集，基于Pytorch环境，构建SqueezeNet多分类模型，因为它建模速度快。

同样，基于GPT-4辅助编程，这次改写过程就不展示了。

二、多分类建模实战

使用胸片的数据集：肺结核病人和健康人的胸片的识别。其中，健康人900张，肺结核病人700张，COVID-19病人549张、细菌性（病毒性）肺炎组900张，分别存入单独的文件夹中。

（a）直接分享代码

######################################导入包###################################
# 导入必要的包
import copy
import torch
import torchvision
import torchvision.transforms as transforms
from torchvision import models
from torch.utils.data import DataLoader
from torch import optim, nn
from torch.optim import lr_scheduler
import os
import matplotlib.pyplot as plt
import warnings
import numpy as np

warnings.filterwarnings("ignore")
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False

# 设置GPU
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

################################导入数据集#####################################
import torch
from torchvision import datasets, transforms
import os

# 数据集路径
data_dir = "./MTB-1"

# 图像的大小
img_height = 100
img_width = 100

# 数据预处理
data_transforms = {
    'train': transforms.Compose([
        transforms.RandomResizedCrop(img_height),
        transforms.RandomHorizontalFlip(),
        transforms.RandomVerticalFlip(),
        transforms.RandomRotation(0.2),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
    'val': transforms.Compose([
        transforms.Resize((img_height, img_width)),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

# 加载数据集
full_dataset = datasets.ImageFolder(data_dir)

# 获取数据集的大小
full_size = len(full_dataset)
train_size = int(0.7 * full_size)  # 假设训练集占70%
val_size = full_size - train_size  # 验证集的大小

# 随机分割数据集
torch.manual_seed(0)  # 设置随机种子以确保结果可重复
train_dataset, val_dataset = torch.utils.data.random_split(full_dataset, [train_size, val_size])

# 将数据增强应用到训练集
train_dataset.dataset.transform = data_transforms['train']

# 创建数据加载器
batch_size = 32
train_dataloader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=4)
val_dataloader = torch.utils.data.DataLoader(val_dataset, batch_size=batch_size, shuffle=True, num_workers=4)

dataloaders = {'train': train_dataloader, 'val': val_dataloader}
dataset_sizes = {'train': len(train_dataset), 'val': len(val_dataset)}
class_names = full_dataset.classes


###############################定义SqueezeNet模型################################
# 定义SqueezeNet模型
model = models.squeezenet1_1(pretrained=True)  # 这里以SqueezeNet 1.1版本为例
num_ftrs = model.classifier[1].in_channels

# 根据分类任务修改最后一层
model.classifier[1] = nn.Conv2d(num_ftrs, len(class_names), kernel_size=(1,1))

# 修改模型最后的输出层为我们需要的类别数
model.num_classes = len(class_names)

model = model.to(device)

# 打印模型摘要
print(model)

#############################编译模型#########################################
# 定义损失函数
criterion = nn.CrossEntropyLoss()

# 定义优化器
optimizer = optim.Adam(model.parameters())

# 定义学习率调度器
exp_lr_scheduler = lr_scheduler.StepLR(optimizer, step_size=7, gamma=0.1)

# 开始训练模型
num_epochs = 50

# 初始化记录器
train_loss_history = []
train_acc_history = []
val_loss_history = []
val_acc_history = []

for epoch in range(num_epochs):
    print('Epoch {}/{}'.format(epoch, num_epochs - 1))
    print('-' * 10)

    # 每个epoch都有一个训练和验证阶段
    for phase in ['train', 'val']:
        if phase == 'train':
            model.train()  # 设置模型为训练模式
        else:
            model.eval()   # 设置模型为评估模式

        running_loss = 0.0
        running_corrects = 0

        # 遍历数据
        for inputs, labels in dataloaders[phase]:
            inputs = inputs.to(device)
            labels = labels.to(device)

            # 零参数梯度
            optimizer.zero_grad()

            # 前向
            with torch.set_grad_enabled(phase == 'train'):
                outputs = model(inputs)
                _, preds = torch.max(outputs, 1)
                loss = criterion(outputs, labels)

                # 只在训练模式下进行反向和优化
                if phase == 'train':
                    loss.backward()
                    optimizer.step()

            # 统计
            running_loss += loss.item() * inputs.size(0)
            running_corrects += torch.sum(preds == labels.data)

        epoch_loss = running_loss / dataset_sizes[phase]
        epoch_acc = (running_corrects.double() / dataset_sizes[phase]).item()

        # 记录每个epoch的loss和accuracy
        if phase == 'train':
            train_loss_history.append(epoch_loss)
            train_acc_history.append(epoch_acc)
        else:
            val_loss_history.append(epoch_loss)
            val_acc_history.append(epoch_acc)

        print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))

    print()

# 保存模型
torch.save(model.state_dict(), 'model.pth')

# 加载最佳模型权重
#model.load_state_dict(best_model_wts)
#torch.save(model, 'shufflenet_best_model.pth')
#print("The trained model has been saved.")
###########################Accuracy和Loss可视化#################################
epoch = range(1, len(train_loss_history)+1)

fig, ax = plt.subplots(1, 2, figsize=(10,4))
ax[0].plot(epoch, train_loss_history, label='Train loss')
ax[0].plot(epoch, val_loss_history, label='Validation loss')
ax[0].set_xlabel('Epochs')
ax[0].set_ylabel('Loss')
ax[0].legend()

ax[1].plot(epoch, train_acc_history, label='Train acc')
ax[1].plot(epoch, val_acc_history, label='Validation acc')
ax[1].set_xlabel('Epochs')
ax[1].set_ylabel('Accuracy')
ax[1].legend()

#plt.savefig("loss-acc.pdf", dpi=300,format="pdf")

####################################混淆矩阵可视化#############################
from sklearn.metrics import classification_report, confusion_matrix
import math
import pandas as pd
import numpy as np
import seaborn as sns
from matplotlib.pyplot import imshow

# 定义一个绘制混淆矩阵图的函数
def plot_cm(labels, predictions):
    
    # 生成混淆矩阵
    conf_numpy = confusion_matrix(labels, predictions)
    # 将矩阵转化为 DataFrame
    conf_df = pd.DataFrame(conf_numpy, index=class_names ,columns=class_names)  
    
    plt.figure(figsize=(8,7))
    
    sns.heatmap(conf_df, annot=True, fmt="d", cmap="BuPu")
    
    plt.title('Confusion matrix',fontsize=15)
    plt.ylabel('Actual value',fontsize=14)
    plt.xlabel('Predictive value',fontsize=14)
    
def evaluate_model(model, dataloader, device):
    model.eval()   # 设置模型为评估模式
    true_labels = []
    pred_labels = []
    # 遍历数据
    for inputs, labels in dataloader:
        inputs = inputs.to(device)
        labels = labels.to(device)

        # 前向
        with torch.no_grad():
            outputs = model(inputs)
            _, preds = torch.max(outputs, 1)

        true_labels.extend(labels.cpu().numpy())
        pred_labels.extend(preds.cpu().numpy())
        
    return true_labels, pred_labels

# 获取预测和真实标签
true_labels, pred_labels = evaluate_model(model, dataloaders['val'], device)

# 计算混淆矩阵
cm_val = confusion_matrix(true_labels, pred_labels)
a_val = cm_val[0,0]
b_val = cm_val[0,1]
c_val = cm_val[1,0]
d_val = cm_val[1,1]

# 计算各种性能指标
acc_val = (a_val+d_val)/(a_val+b_val+c_val+d_val)  # 准确率
error_rate_val = 1 - acc_val  # 错误率
sen_val = d_val/(d_val+c_val)  # 灵敏度
sep_val = a_val/(a_val+b_val)  # 特异度
precision_val = d_val/(b_val+d_val)  # 精确度
F1_val = (2*precision_val*sen_val)/(precision_val+sen_val)  # F1值
MCC_val = (d_val*a_val-b_val*c_val) / (np.sqrt((d_val+b_val)*(d_val+c_val)*(a_val+b_val)*(a_val+c_val)))  # 马修斯相关系数

# 打印出性能指标
print("验证集的灵敏度为：", sen_val, 
      "验证集的特异度为：", sep_val,
      "验证集的准确率为：", acc_val, 
      "验证集的错误率为：", error_rate_val,
      "验证集的精确度为：", precision_val, 
      "验证集的F1为：", F1_val,
      "验证集的MCC为：", MCC_val)

# 绘制混淆矩阵
plot_cm(true_labels, pred_labels)

    
# 获取预测和真实标签
train_true_labels, train_pred_labels = evaluate_model(model, dataloaders['train'], device)
# 计算混淆矩阵
cm_train = confusion_matrix(train_true_labels, train_pred_labels)  
a_train = cm_train[0,0]
b_train = cm_train[0,1]
c_train = cm_train[1,0]
d_train = cm_train[1,1]
acc_train = (a_train+d_train)/(a_train+b_train+c_train+d_train)
error_rate_train = 1 - acc_train
sen_train = d_train/(d_train+c_train)
sep_train = a_train/(a_train+b_train)
precision_train = d_train/(b_train+d_train)
F1_train = (2*precision_train*sen_train)/(precision_train+sen_train)
MCC_train = (d_train*a_train-b_train*c_train) / (math.sqrt((d_train+b_train)*(d_train+c_train)*(a_train+b_train)*(a_train+c_train))) 
print("训练集的灵敏度为：",sen_train, 
      "训练集的特异度为：",sep_train,
      "训练集的准确率为：",acc_train, 
      "训练集的错误率为：",error_rate_train,
      "训练集的精确度为：",precision_train, 
      "训练集的F1为：",F1_train,
      "训练集的MCC为：",MCC_train)

# 绘制混淆矩阵
plot_cm(train_true_labels, train_pred_labels)

################################模型性能参数计算################################
from sklearn import metrics

def test_accuracy_report(model, dataloader, device):
    true_labels, pred_labels = evaluate_model(model, dataloader, device)
    print(metrics.classification_report(true_labels, pred_labels, target_names=class_names)) 
    
test_accuracy_report(model, dataloaders['val'], device)

def train_accuracy_report(model, dataloader, device):
    true_labels, pred_labels = evaluate_model(model, dataloader, device)
    print(metrics.classification_report(true_labels, pred_labels, target_names=class_names)) 
    
train_accuracy_report(model, dataloaders['train'], device)


################################AUC曲线绘制####################################
from sklearn import metrics
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.pyplot import imshow
from sklearn.metrics import classification_report, confusion_matrix
import seaborn as sns
import pandas as pd
import math
from sklearn.metrics import roc_auc_score, auc
from sklearn.preprocessing import LabelBinarizer

def multiclass_roc_auc_score(y_test, y_pred, average="macro"):
    # 判断 y_test 是否需要进行标签二值化
    if len(np.unique(y_test)) > 2:  # 假设 y_test 是类别标签，且类别数大于 2
        lb = LabelBinarizer()
        lb.fit(y_test)
        y_test = lb.transform(y_test)
    return roc_auc_score(y_test, y_pred, average=average)


def plot_roc(name, labels, predictions, **kwargs):
    lb = LabelBinarizer()
    labels = lb.fit_transform(labels)  # one-hot 编码
    # predictions 不需要进行标签二值化
    # 计算ROC曲线和AUC值
    fpr = dict()
    tpr = dict()
    roc_auc = dict()
    class_num = len(class_names)
    for i in range(class_num):  # class_num是类别数目
        fpr[i], tpr[i], _ = metrics.roc_curve(labels[:, i], predictions[:, i])
        roc_auc[i] = metrics.auc(fpr[i], tpr[i])

    for i in range(class_num):
        plt.plot(fpr[i], tpr[i], label='ROC curve of class {0} (area = {1:0.2f})' ''.format(i, roc_auc[i]))

    plt.plot([0, 1], [0, 1], 'k--')
    plt.xlim([0.0, 1.0])
    plt.ylim([0.0, 1.05])
    plt.xlabel('False Positive Rate')
    plt.ylabel('True Positive Rate')
    plt.title('Receiver operating characteristic example')
    plt.legend(loc="lower right")
    plt.show()


# 确保模型处于评估模式
model.eval()

def evaluate_model_pre(model, data_loader, device):
    model.eval()
    predictions = []
    labels = []
    with torch.no_grad():
        for inputs, targets in data_loader:
            inputs = inputs.to(device)
            targets = targets.to(device)
            outputs = model(inputs)
            # 使用 softmax 函数，转换成概率值
            prob_outputs = torch.nn.functional.softmax(outputs, dim=1)
            predictions.append(prob_outputs.detach().cpu().numpy())
            labels.append(targets.detach().cpu().numpy())
    return np.concatenate(predictions, axis=0), np.concatenate(labels, axis=0)

val_pre_auc, val_label_auc = evaluate_model_pre(model, dataloaders['val'], device)
train_pre_auc, train_label_auc = evaluate_model_pre(model, dataloaders['train'], device)

auc_score_val = multiclass_roc_auc_score(val_label_auc, val_pre_auc)
auc_score_train = multiclass_roc_auc_score(train_label_auc, train_pre_auc)


plot_roc('validation AUC: {0:.4f}'.format(auc_score_val), val_label_auc, val_pre_auc, color="red", linestyle='--')
plot_roc('training AUC: {0:.4f}'.format(auc_score_train), train_label_auc, train_pre_auc, color="blue", linestyle='--')

print("训练集的AUC值为：",auc_score_train, "验证集的AUC值为：",auc_score_val)

（b）输出结果：学习曲线

 （c）输出结果：混淆矩阵

 （d）输出结果：性能参数

 （e）输出结果：ROC曲线

三、数据

链接：https://pan.baidu.com/s/1rqu15KAUxjNBaWYfEmPwgQ?pwd=xfyn

提取码：xfyn