如何使用Tensorboard检测消失和爆炸梯度？

import tensorflow as tf
from tensorflow import keras

model = keras.Sequential([
    keras.layers.Dense(64, activation='relu', input_shape=(784,)),
    keras.layers.Dense(64, activation='relu'),
    keras.layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir='./logs')

model.fit(train_images, train_labels, epochs=10, callbacks=[tensorboard_callback])

tensorboard --logdir=./logs

http://localhost:6006