如何在tensorflow中进行架构分析？

import tensorflow as tf

model = tf.keras.Sequential([
    tf.keras.layers.Dense(64, activation='relu', input_shape=(input_dim,)),
    tf.keras.layers.Dense(10, activation='softmax')
])

# 创建TensorBoard回调
tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1)

# 训练模型并将TensorBoard回调传递给fit函数
model.fit(x_train, y_train, epochs=10, callbacks=[tensorboard_callback])

# 在TensorBoard中添加性能指标
tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1, write_graph=True, write_images=True)

# 训练模型并将TensorBoard回调传递给fit函数
model.fit(x_train, y_train, epochs=10, callbacks=[tensorboard_callback])

# 启动TensorBoard
tensorboard --logdir=path/to/log_directory

# 在浏览器中打开TensorBoard的URL，浏览模型的架构分析结果