Question

我正在使用TensorFlow训练DC Gan，我收到以下错误：

ValueError: Variable d_bn1/d_bn1_2/moments/Squeeze/ExponentialMovingAverage/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=tf.AUTO_REUSE in VarScope?

从以下文件中的第34行调用：在变量ema_apply_op之前。我已经尝试通过查看相关答案将Varible Reuse设置为True和其他东西，但我无法解决错误。

import math
import numpy as np 
import tensorflow as tf

from tensorflow.python.framework import ops


class batch_norm(object):
    """Code modification of http://stackoverflow.com/a/33950177"""
    def __init__(self, epsilon=1e-5, momentum = 0.9, name="batch_norm"):
        with tf.variable_scope(name):
            self.epsilon = epsilon
            self.momentum = momentum

            self.ema = tf.train.ExponentialMovingAverage(decay=self.momentum)
            self.name = name

    def __call__(self, x, train=True):
        shape = x.get_shape().as_list()

        if train:
            with tf.variable_scope(self.name) as scope:
                self.beta = tf.get_variable("beta", [shape[-1]],
                                    initializer=tf.constant_initializer(0.))
                self.gamma = tf.get_variable("gamma", [shape[-1]],
                                    initializer=tf.random_normal_initializer(1., 0.02))

                try:
                    batch_mean, batch_var = tf.nn.moments(x, [0, 1, 2], name='moments')
                except:
                    batch_mean, batch_var = tf.nn.moments(x, [0, 1], name='moments')

                ema_apply_op = self.ema.apply([batch_mean, batch_var])
                self.ema_mean, self.ema_var = self.ema.average(batch_mean), self.ema.average(batch_var)

                with tf.control_dependencies([ema_apply_op]):
                    mean, var = tf.identity(batch_mean), tf.identity(batch_var)
        else:
            mean, var = self.ema_mean, self.ema_var

        normed = tf.nn.batch_norm_with_global_normalization(
                x, mean, var, self.beta, self.gamma, self.epsilon, scale_after_normalization=True)

        return normed

def binary_cross_entropy(preds, targets, name=None):
    """Computes binary cross entropy given `preds`.

    For brevity, let `x = `, `z = targets`.  The logistic loss is

        loss(x, z) = - sum_i (x[i] * log(z[i]) + (1 - x[i]) * log(1 - z[i]))

    Args:
        preds: A `Tensor` of type `float32` or `float64`.
        targets: A `Tensor` of the same type and shape as `preds`.
    """
    eps = 1e-12
    with ops.op_scope([preds, targets], name, "bce_loss") as name:
        preds = ops.convert_to_tensor(preds, name="preds")
        targets = ops.convert_to_tensor(targets, name="targets")
        return tf.reduce_mean(-(targets * tf.log(preds + eps) +
                              (1. - targets) * tf.log(1. - preds + eps)))

在VarScope中重用Tensorflow变量True

0 个答案: