tensorflow exponential_decay使用 Posted on 2018-01-Sun Edited on 2018-04-Sun Views: Views: 12345678exponential_decay( learning_rate, global_step, decay_steps, decay_rate, staircase=False, name=None)一般用法123456learning_rate = tf.train.exponential_decay( LEARNING_RATE_BASE, global_step, mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY)因为每次train会使用BATCH_SIZE多的数据