【问题标题】:Batch normalization in tensorflow: variables and performance张量流中的批量标准化:变量和性能
【发布时间】:2019-04-02 12:23:26
【问题描述】:

我想在批量标准化层的变量上添加条件操作。具体来说,在浮点数中训练,然后在微调二次训练阶段进行量化。为此,我想在变量上添加一个 tf.cond 操作(均值和 var 的 scale、shift 和 exp 移动平均值)。

我将 tf.layers.batch_normalization 替换为我编写的 batchnorm 层(见下文)。

此函数完美运行(即,我使用两个函数获得相同的指标),并且我可以将任何管道添加到变量(在 batchnorm 操作之前)。 问题在于性能(运行时)急剧下降(即,只需将 layers.batchnorm 替换为我自己的函数,就会产生 x2 因子,如下所述)。

def batchnorm(self, x, name, epsilon=0.001, decay=0.99):
    epsilon = tf.to_float(epsilon)
    decay = tf.to_float(decay)
    with tf.variable_scope(name):
        shape = x.get_shape().as_list()
        channels_num = shape[3]
        # scale factor
        gamma = tf.get_variable("gamma", shape=[channels_num], initializer=tf.constant_initializer(1.0), trainable=True)
        # shift value
        beta = tf.get_variable("beta", shape=[channels_num], initializer=tf.constant_initializer(0.0), trainable=True)
        moving_mean = tf.get_variable("moving_mean", channels_num, initializer=tf.constant_initializer(0.0), trainable=False)
        moving_var = tf.get_variable("moving_var", channels_num, initializer=tf.constant_initializer(1.0), trainable=False)
        batch_mean, batch_var = tf.nn.moments(x, axes=[0, 1, 2]) # per channel

        update_mean = moving_mean.assign((decay * moving_mean) + ((1. - decay) * batch_mean))
        update_var = moving_var.assign((decay * moving_var) + ((1. - decay) * batch_var))

        tf.add_to_collection(tf.GraphKeys.UPDATE_OPS, update_mean)
        tf.add_to_collection(tf.GraphKeys.UPDATE_OPS, update_var)

        bn_mean = tf.cond(self.is_training, lambda: tf.identity(batch_mean), lambda: tf.identity(moving_mean))
        bn_var = tf.cond(self.is_training, lambda: tf.identity(batch_var), lambda: tf.identity(moving_var))

        with tf.variable_scope(name + "_batchnorm_op"):
            inv = tf.math.rsqrt(bn_var + epsilon)
            inv *= gamma
            output = ((x*inv) - (bn_mean*inv)) + beta

    return output

如果有以下任何问题,我将不胜感激:

  • 关于如何提高我的解决方案的性能(减少运行时间)的任何想法?
  • 是否可以在batchnorm操作之前将我自己的运算符添加到layers.batchnorm的变量管道中?
  • 对于同一问题还有其他解决方案吗?

【问题讨论】:

    标签: python tensorflow batch-normalization


    【解决方案1】:

    tf.nn.fused_batch_norm 已经过优化并成功了。

    我必须创建两个子图,每个模式一个,因为fused_batch_norm 的接口不采用条件训练/测试模式(is_training 是布尔值而不是张量,所以它的图不是条件的)。我在之后添加了条件(见下文)。然而,即使有两个子图,它的运行时间也大致相同 tf.layers.batch_normalization

    这是最终的解决方案(如果有任何改进意见或建议,我仍将不胜感激):

    def batchnorm(self, x, name, epsilon=0.001, decay=0.99):
        with tf.variable_scope(name):
            shape = x.get_shape().as_list()
            channels_num = shape[3]
            # scale factor
            gamma = tf.get_variable("gamma", shape=[channels_num], initializer=tf.constant_initializer(1.0), trainable=True)
            # shift value
            beta = tf.get_variable("beta", shape=[channels_num], initializer=tf.constant_initializer(0.0), trainable=True)
            moving_mean = tf.get_variable("moving_mean", channels_num, initializer=tf.constant_initializer(0.0), trainable=False)
            moving_var = tf.get_variable("moving_var", channels_num, initializer=tf.constant_initializer(1.0), trainable=False)
    
            (output_train, batch_mean, batch_var) = tf.nn.fused_batch_norm(x,
                                                                     gamma,
                                                                     beta,  # pylint: disable=invalid-name
                                                                     mean=None,
                                                                     variance=None,
                                                                     epsilon=epsilon,
                                                                     data_format="NHWC",
                                                                     is_training=True,
                                                                     name="_batchnorm_op")
            (output_test, _, _) = tf.nn.fused_batch_norm(x,
                                                         gamma,
                                                         beta,  # pylint: disable=invalid-name
                                                         mean=moving_mean,
                                                         variance=moving_var,
                                                         epsilon=epsilon,
                                                         data_format="NHWC",
                                                         is_training=False,
                                                         name="_batchnorm_op")
    
            output = tf.cond(self.is_training, lambda: tf.identity(output_train), lambda: tf.identity(output_test))
    
            update_mean = moving_mean.assign((decay * moving_mean) + ((1. - decay) * batch_mean))
            update_var = moving_var.assign((decay * moving_var) + ((1. - decay) * batch_var))
            tf.add_to_collection(tf.GraphKeys.UPDATE_OPS, update_mean)
            tf.add_to_collection(tf.GraphKeys.UPDATE_OPS, update_var)
    
        return output
    

    【讨论】:

      猜你喜欢
      • 1970-01-01
      • 1970-01-01
      • 2020-04-03
      • 1970-01-01
      • 1970-01-01
      • 2017-04-14
      • 1970-01-01
      • 1970-01-01
      • 2018-04-09
      相关资源
      最近更新 更多