tensorflow旧版本0.11的初始化问题 zeros_initializer() got multiple values for argument……

立个flag，找个工具把代码升级成1.0之后的版本，尽快。

使用tf.get_variable时，initializer的问题

使用zeros_initializer和ones_initializer时，不要加小括号，那是新版本的用法

根据网上的答案，将zeros_initialier换成constant_initialier(0.0)依然报错

去掉括号之后依然有问题，但多试了几遍就不报错了…… 不解

我不知道为什么，多试了几遍就好了……十分不解

所以还是，换新版本。旧版本好多问题查不到。

参考https://github.com/ry/tensorflow-resnet/blob/master/resnet.py，实现微调resnet50时的bn层时，遇到的问题

略………………
moving_mean = _get_variable('moving_mean',
                                params_shape,
                                initializer=tf.zeros_initializer,
                                trainable=False)
moving_variance = _get_variable('moving_variance',
                                    params_shape,
                                    initializer=tf.ones_initializer,
                                    trainable=False)

_get_variable调用了tf.get_variable

def _get_variable(name,
                  shape,
                  initializer,
                  weight_decay=0.0,
                  dtype='float',
                  trainable=True):
    "A little wrapper around tf.get_variable to do weight decay and add to"
    "resnet collection"
    if weight_decay > 0:
        regularizer = tf.contrib.layers.l2_regularizer(weight_decay)
    else:
        regularizer = None
    collections = [tf.GraphKeys.VARIABLES, RESNET_VARIABLES]
    return tf.get_variable(name,
                           shape=shape,
                           initializer=initializer,
                           dtype=dtype,
                           regularizer=regularizer,
                           collections=collections,
                           trainable=trainable)