使用张量流执行批量归一化

Question

我正试图在tensor-flow中实现批量归一化层。我没有问题，使用tf.moments来运行火车这一步，得到的意思是和方差。

对于测试时间，我想设置一个指数移动平均值来跟踪均值和方差。我试图做这样的：

def batch_normalized_linear_layer(state_below, scope_name, n_inputs, n_outputs, stddev, wd, eps=.0001): 
    with tf.variable_scope(scope_name) as scope: 
    weight = _variable_with_weight_decay(
     "weights", shape=[n_inputs, n_outputs], 
     stddev=stddev, wd=wd 
    ) 
    act = tf.matmul(state_below, weight) 
    # get moments 
    act_mean, act_variance = tf.nn.moments(act, [0]) 
    # get mean and variance variables 
    mean = _variable_on_cpu('bn_mean', [n_outputs], tf.constant_initializer(0.0)) 
    variance = _variable_on_cpu('bn_variance', [n_outputs], tf.constant_initializer(1.0)) 
    # assign the moments 
    assign_mean = mean.assign(act_mean) 
    assign_variance = variance.assign(act_variance) 

    act_bn = tf.mul((act - mean), tf.rsqrt(variance + eps), name=scope.name+"_bn") 

    beta = _variable_on_cpu("beta", [n_outputs], tf.constant_initializer(0.0)) 
    gamma = _variable_on_cpu("gamma", [n_outputs], tf.constant_initializer(1.0)) 
    bn = tf.add(tf.mul(act_bn, gamma), beta) 
    output = tf.nn.relu(bn, name=scope.name) 
    _activation_summary(output) 
    return output, mean, variance 

凡_variable_on_cpu被定义为：

def _variable_on_cpu(name, shape, initializer): 
    """Helper to create a Variable stored on CPU memory. 

    Args: 
    name: name of the variable 
    shape: list of ints 
    initializer: initializer for Variable 

    Returns: 
    Variable Tensor 
    """ 
    with tf.device('/cpu:0'): 
    var = tf.get_variable(name, shape, initializer=initializer) 
    return var 

我相信，我设置

assign_mean = mean.assign(act_mean) 
assign_variance = variance.assign(act_variance) 

错误，但我不知道如何。当我使用张量板来跟踪这些均值和方差变量时，他们只是平坦的初始值。

Answer 1

Rafal的评论得到了问题的核心：您没有运行分配节点。您可以尝试使用我在另一个答案 - How could I use Batch Normalization in TensorFlow?中发布的蝙蝠科帮手，或者您可以通过添加with_dependencies来强制分配，正如他所建议的。

一般原则是，如果数据或控制依赖关系流经“通过”它，则只应该指望正在运行的节点。 with_dependencies确保在使用输出操作之前，指定的依赖项已完成。