如何使用tflearn进行交叉验证？

import tflearn
from tflearn.data_utils import to_categorical
from sklearn.model_selection import StratifiedKFold

# 假设X为特征数据，Y为标签数据
# 将标签转换为独热编码
Y = to_categorical(Y, nb_classes=num_classes)

def create_model():
    # 定义模型结构
    net = tflearn.input_data(shape=[None, input_size])
    net = tflearn.fully_connected(net, 64, activation='relu')
    net = tflearn.fully_connected(net, num_classes, activation='softmax')
    net = tflearn.regression(net)
    
    # 创建模型
    model = tflearn.DNN(net)
    return model

# 创建交叉验证对象
kfold = StratifiedKFold(n_splits=num_folds, shuffle=True)

# 进行交叉验证
for train_index, val_index in kfold.split(X, Y):
    # 划分训练集和验证集
    X_train, X_val = X[train_index], X[val_index]
    Y_train, Y_val = Y[train_index], Y[val_index]
    
    # 创建模型
    model = create_model()
    
    # 训练模型
    model.fit(X_train, Y_train, validation_set=(X_val, Y_val), n_epoch=num_epochs, batch_size=batch_size)
    
    # 在验证集上评估模型性能
    accuracy = model.evaluate(X_val, Y_val)
    print("Validation Accuracy:", accuracy)