tf.train.exponential_decay电流LR的获取

Question

我正在进行指数重量衰减的训练，类似于Tensorflow docs (衰变)的例子：

global_step = tf.Variable(0, trainable=False)
starter_learning_rate = 0.1
learning_rate = tf.train.exponential_decay(starter_learning_rate, global_step,
                                       100000, 0.96, staircase=True)
# Passing global_step to minimize() will increment it at each step.
learning_step = (
    tf.train.GradientDescentOptimizer(learning_rate)
    .minimize(...my loss..., global_step=global_step)
)

如何在培训期间获得当前的学习速度(例如打印出来)？

Answer 1

只需在run时间调用它：

_, loss, lr = sess.run([learning_step, model_loss, learning_rate], feed_dict={...})

您还可以用坦氏板绘制它的演化图。