把网络模型单独拎出来了，方便解耦。下一步准备把重要的配置全部拎出来。

train/food_classifier.py

@@ -9,8 +9,14 @@ import matplotlib
 import numpy as np
 from tqdm import tqdm
 import os
+import sys
 import time
 
+# 添加net目录到路径
+# sys.path.append(os.path.join(os.path.dirname(__file__), '..', 'net'))
+# from food_net import create_food_cnn
+from net import create_food_cnn
+
 # 设置matplotlib支持中文显示
 plt.rcParams['font.sans-serif'] = ['SimHei', 'Microsoft YaHei', 'DejaVu Sans']  # 指定默认字体
 plt.rcParams['axes.unicode_minus'] = False  # 解决保存图像是负号'-'显示为方块的问题
@@ -19,61 +25,7 @@ plt.rcParams['axes.unicode_minus'] = False  # 解决保存图像是负号'-'显
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 print(f"使用设备: {device}")
 
-# 定义CNN模型（基于CIFAR10结构，输出层改为3分类）
-class FoodCNN(nn.Module):
-    def __init__(self):
-        super(FoodCNN, self).__init__()
-        # 第一个卷积块
-        self.conv1 = nn.Conv2d(3, 32, 3, padding=1)
-        self.conv2 = nn.Conv2d(32, 32, 3, padding=1)
-        self.pool1 = nn.MaxPool2d(2, 2)
-        self.dropout1 = nn.Dropout2d(0.25)
-        
-        # 第二个卷积块
-        self.conv3 = nn.Conv2d(32, 64, 3, padding=1)
-        self.conv4 = nn.Conv2d(64, 64, 3, padding=1)
-        self.pool2 = nn.MaxPool2d(2, 2)
-        self.dropout2 = nn.Dropout2d(0.25)
-        
-        # 第三个卷积块
-        self.conv5 = nn.Conv2d(64, 128, 3, padding=1)
-        self.conv6 = nn.Conv2d(128, 128, 3, padding=1)
-        self.pool3 = nn.MaxPool2d(2, 2)
-        self.dropout3 = nn.Dropout2d(0.25)
-        
-        # 全连接层
-        self.fc1 = nn.Linear(128 * 4 * 4, 512)
-        self.dropout4 = nn.Dropout(0.5)
-        self.fc2 = nn.Linear(512, 3)  # 改为2分类
-        
-    def forward(self, x):
-        # 第一个卷积块
-        x = F.relu(self.conv1(x))
-        x = F.relu(self.conv2(x))
-        x = self.pool1(x)
-        x = self.dropout1(x)
-        
-        # 第二个卷积块
-        x = F.relu(self.conv3(x))
-        x = F.relu(self.conv4(x))
-        x = self.pool2(x)
-        x = self.dropout2(x)
-        
-        # 第三个卷积块
-        x = F.relu(self.conv5(x))
-        x = F.relu(self.conv6(x))
-        x = self.pool3(x)
-        x = self.dropout3(x)
-        
-        # 展平
-        x = x.view(-1, 128 * 4 * 4)
-        
-        # 全连接层
-        x = F.relu(self.fc1(x))
-        x = self.dropout4(x)
-        x = self.fc2(x)
-        
-        return x
+
 
 # 数据预处理
 transform_train = transforms.Compose([
@@ -201,7 +153,7 @@ if __name__ == '__main__':
     print(f"测试集大小: {len(test_dataset)}")
 
     # 创建模型
-    model = FoodCNN().to(device)
+    model = create_food_cnn().to(device)
     print(f"模型参数数量: {sum(p.numel() for p in model.parameters() if p.requires_grad)}")
 
     # 定义损失函数和优化器（使用与CIFAR10相同的超参数）