pointnet 第十二句 learning_rate = get_learning_rate(batch)

learning_rate = get_learning_rate(batch)

首先看具体实现

def get_learning_rate(batch):
    learning_rate = tf.train.exponential_decay(
                        BASE_LEARNING_RATE,  # Base learning rate.
                        batch * BATCH_SIZE,  # Current index into the dataset.
                        DECAY_STEP,          # Decay step.
                        DECAY_RATE,          # Decay rate.
                        staircase=True)
    learning_rate = tf.maximum(learning_rate, 0.00001) # CLIP THE LEARNING RATE!
    return learning_rate        

输入参数为batch，在目前的项目中表示train的step

与get_bn_decay（从0.5开始按照指数规则缓慢减少）相似，也是指数增加的learningrate而且从0.00001开始增加，