• 🍨 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

1. 简介 & 数据集介绍

实验搭建 VGG-16 模型通过对马铃薯叶子健康情况建模，进行病害识别。
数据集分为三类：健康 healthy, 早疫病 Early_blight, 晚疫病 Late_blight。其中健康叶子有 152 张图片，早疫病和晚疫病叶子各有 1000 张图片。

2. 环境

• 语言环境：Python 3.12.7
• 编译器：Jupyter Notebook
• 深度学习环境：torch—2.8.0 + cu126 / torchvision—0.23.1+cu126

3. 代码实现

3.1 前期准备

3.1.1 设置GPU & 导入库

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os,PIL,pathlib,warnings, pathlib
import torch.nn.functional as F
import torchsummary as summary
import copy
from PIL import Image
import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings("ignore") 
plt.rcParams['font.sans-serif']    = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
plt.rcParams['figure.dpi']         = 100 

from datetime import datetime

warnings.filterwarnings("ignore")

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

3.1.2 标签查看

data_dir = './Data/PotatoPlants/'
data_dir = pathlib.Path(data_dir)

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

3.2 VGG-16 模型

3.2.1 图片转换读取

train_transforms = transforms.Compose([
    transforms.Resize([224, 224]),
    
    transforms.ToTensor(),   
    transforms.Normalize(    
        mean=[0.485, 0.456, 0.406], 
        std=[0.229, 0.224, 0.225])  
])

test_transform = transforms.Compose([
    transforms.Resize([224, 224]), 
    transforms.ToTensor(), 
    transforms.Normalize(
        mean=[0.485, 0.456, 0.406], 
        std=[0.229, 0.224, 0.225])
])

total_data = datasets.ImageFolder("./Data/PotatoPlants/",transform=train_transforms)
total_data

total_data.class_to_idx

3.2.2 数据集划分

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

3.2.3 VGG-16 模型建立

class vgg16(nn.Module):
    def __init__(self):
        super(vgg16, self).__init__()
        # 卷积块1
        self.block1 = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2))
        )
        # 卷积块2
        self.block2 = nn.Sequential(
            nn.Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2))
        )
        # 卷积块3
        self.block3 = nn.Sequential(
            nn.Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2))
        )
        # 卷积块4
        self.block4 = nn.Sequential(
            nn.Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2))
        )
        # 卷积块5
        self.block5 = nn.Sequential(
            nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2))
        )
      

        # 全连接网络层，用于分类
        self.classifier = nn.Sequential(
            nn.Linear(in_features=512*7*7, out_features=4096),
            nn.ReLU(),
            nn.Linear(in_features=4096, out_features=4096),
            nn.ReLU(),
            nn.Linear(in_features=4096, out_features=3)
        )

    def forward(self, x):

        x = self.block1(x)
        x = self.block2(x)
        x = self.block3(x)
        x = self.block4(x)
        x = self.block5(x)
        x = torch.flatten(x, start_dim=1)
        x = self.classifier(x)

        return x

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

model = vgg16().to(device)
model

summary.summary(model, (3, 224, 224))

3.2.4 训练 & 测试函数

# 训练循环
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) 
      

        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

# 测试循环
def test (dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)  
    test_loss, test_acc = 0, 0
  

    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

3.2.5 参数设定 & 正式训练

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)

optimizer  = torch.optim.Adam(model.parameters(), lr= 1e-4)
loss_fn = nn.CrossEntropyLoss() 

epochs = 20

train_loss = []
train_acc  = []
test_loss  = []
test_acc   = []

best_acc = 0 

for epoch in range(epochs):
  

    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)
  

    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
  

    if epoch_test_acc > best_acc:
        best_acc   = epoch_test_acc
        best_model = copy.deepcopy(model)
  

    train_acc.append(epoch_train_acc)
    train_loss.append(epoch_train_loss)
    test_acc.append(epoch_test_acc)
    test_loss.append(epoch_test_loss)

    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))

PATH = './best_model.pth'
torch.save(model.state_dict(), PATH)

print('Done')

3.2.6 结果可视化

current_time = datetime.now() 
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) 

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()

4. 模型应用 & 评估

4.1 预测指定本地照片

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)

    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='./Data/PotatoPlants/Late_blight/1.JPG', 
                  model=model, 
                  transform=train_transforms, 
                  classes=classes)

4.2 模型评估

best_model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, best_model, loss_fn)
epoch_test_acc, epoch_test_loss