改进代码，将测试，训练，验证，分清楚

为了更清晰地分离训练、验证和测试过程，可以将代码重构为几个独立的函数，并在主程序中调用这些函数。以下是改进后的代码：

import os
import json
import numpy as np
import pandas as pd
from PIL import Image
import tensorflow as tf
from sklearn.model_selection import train_test_split
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.optimizers import Adam
from sklearn.metrics import f1_score, accuracy_score

# 加载数据集
def load_data(data_dir, label_path):
    with open(label_path, 'r') as f:
        labels_list = json.load(f)
    
    labels = {item['文件名']: item['标签'] for item in labels_list if '文件名' in item and '标签' in item}
    images = []
    targets = []
    
    for file_name, label in labels.items():
        img_path = os.path.join(data_dir, file_name)
        if not os.path.exists(img_path):
            continue
        img = Image.open(img_path).resize((128, 128))
        img_array = np.array(img) / 255.0
        images.append(img_array)
        targets.append(label)
    
    if len(images) == 0:
        raise ValueError("No valid images found.")
    
    return np.array(images), np.array(targets)

# 创建模型
def create_model(input_shape=(128, 128, 3)):
    model = Sequential([
        Conv2D(32, (3, 3), activation='relu', input_shape=input_shape),
        MaxPooling2D((2, 2)),
        Conv2D(64, (3, 3), activation='relu'),
        MaxPooling2D((2, 2)),
        Conv2D(128, (3, 3), activation='relu'),
        MaxPooling2D((2, 2)),
        Flatten(),
        Dense(128, activation='relu'),
        Dropout(0.5),
        Dense(4, activation='softmax')
    ])
    return model

# 评估模型
def evaluate_model(model, X, y):
    predictions = model.predict(X)
    predicted_labels = np.argmax(predictions, axis=1)
    accuracy = accuracy_score(y, predicted_labels)
    f1 = f1_score(y, predicted_labels, average='weighted')
    print(f'Accuracy: {accuracy:.4f}')
    print(f'F1 Score: {f1:.4f}')
    return accuracy, f1

# 预测测试集并保存结果
def predict_and_save(model, test_data_dir, test_label_path, output_path, label_map):
    test_images = []
    test_file_names = []
    
    with open(test_label_path, 'r') as f:
        test_labels_list = json.load(f)
    test_labels = {item['文件名']: item['标签'] for item in test_labels_list if '文件名' in item and '标签' in item}
    
    for file_name in test_labels.keys():
        img_path = os.path.join(test_data_dir, file_name)
        if not os.path.exists(img_path):
            continue
        img = Image.open(img_path).resize((128, 128))
        img_array = np.array(img) / 255.0
        test_images.append(img_array)
        test_file_names.append(file_name)
    
    test_images = np.array(test_images)
    predictions = model.predict(test_images)
    predicted_labels = np.argmax(predictions, axis=1)
    
    label_map_inv = {v: k for k, v in label_map.items()}
    predicted_labels = [label_map_inv[label] for label in predicted_labels]
    
    submission_df = pd.DataFrame({'文件名': test_file_names, '标签': predicted_labels})
    submission_df.to_csv(output_path, index=False)

# 主程序
if __name__ == "__main__":
    data_dir = "C:\\Users\\24067\\Desktop\\peach_split\\train"
    label_path = "C:\\Users\\24067\\Desktop\\train_label.json"
    
    # 加载训练数据
    images, labels = load_data(data_dir, label_path)
    
    # 标签映射
    label_map = {'特级': 3, '一级': 2, '二级': 1, '三级': 0}
    labels = np.array([label_map[label] for label in labels])
    
    # 划分训练集和验证集
    X_train, X_val, y_train, y_val = train_test_split(images, labels, test_size=0.2, random_state=42)
    
    # 创建模型
    model = create_model()
    
    # 编译模型
    model.compile(optimizer=Adam(learning_rate=0.001), loss='sparse_categorical_crossentropy', metrics=['accuracy'])
    
    # 图像增强
    datagen = ImageDataGenerator(
        rotation_range=20,
        width_shift_range=0.2,
        height_shift_range=0.2,
        horizontal_flip=True,
        vertical_flip=True
    )
    
    # 训练模型
    history = model.fit(datagen.flow(X_train, y_train, batch_size=32), epochs=1, validation_data=(X_val, y_val))
    
    # 评估模型
    evaluate_model(model, X_val, y_val)
    
    # 测试集目录和标签路径
    test_data_dir = "C:\\Users\\24067\\Desktop\\peach_split\\test"
    test_label_path = "C:\\Users\\24067\\Desktop\\train_label.json"
    output_path = "C:\\Users\\24067\\Desktop\\data\\submission.csv"
    
    # 进行预测并保存结果
    predict_and_save(model, test_data_dir, test_label_path, output_path, label_map)

### 改进点说明：
1. **模块化**：将不同的功能（加载数据、创建模型、评估模型、预测并保存结果）封装成独立的函数，使代码结构更加清晰。
2. **主程序入口**：使用 `if __name__ == "__main__":` 来定义主程序入口，确保脚本作为主程序运行时才执行特定的逻辑。
3. **参数传递**：将一些常量（如数据目录、标签路径等）提取到主程序中，方便修改和维护。
4. **注释**：增加了必要的注释，帮助理解每个函数的功能和参数。

这样，代码的可读性和可维护性得到了显著提升。