在 Tensorflow 中使用 Adadelta 优化器时出现未初始化值错误

Posted 2023-03-12

【中文标题】在 Tensorflow 中使用 Adadelta 优化器时出现未初始化值错误

【英文标题】：Uninitialized value error while using Adadelta optimizer in Tensorflow

【发布时间】：2016-08-19 15:36:11

【问题描述】：

我正在尝试使用 Adagrad 优化器构建 CNN，但出现以下错误。

tensorflow.python.framework.errors.FailedPreconditionError: Attempting to use uninitialized value Variable_7/Adadelta

[[节点：Adadelta/update_Variable_7/ApplyAdadelta = ApplyAdadelta[T=DT_FLOAT, _class=["loc:@Variable_7"], use_locking=false, _device="/job:localhost/replica:0/task :0/cpu:0"](Variable_7, Variable_7/Adadelta, Variable_7/Adadelta_1, Adadelta/lr, Adadelta/rho, Adadelta/epsilon, gradients/add_3_grad/tuple/control_dependency_1)]] 由操作 u'Adadelta/update_Variable_7/ApplyAdadelta' 引起，

优化器 = tf.train.AdadeltaOptimizer(learning_rate).minimize(cross_entropy)

我尝试在本文中提到的 adagrad 语句之后重新初始化会话变量，但这也没有帮助。

如何避免此错误？谢谢。

Tensorflow: Using Adam optimizer

import tensorflow as tf
import numpy
from tensorflow.examples.tutorials.mnist import input_data

def conv2d(x, W):
  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                        strides=[1, 2, 2, 1], padding='SAME')

def weight_variable(shape):
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)

def bias_variable(shape):
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)


mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)

# Parameters
learning_rate = 0.01
training_epochs = 100
batch_size = 1000
display_step = 1


# Set model weights
W = tf.Variable(tf.zeros([784, 10]), name="weights")
b = tf.Variable(tf.zeros([10]), name="bias")

W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])


W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])


W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

# Initializing the variables
init = tf.initialize_all_variables()

with tf.Session() as sess:
    sess.run(init)
    for epoch in range(training_epochs):
        total_batch = int(mnist.train.num_examples/batch_size)
        for i in range(total_batch):

            batch_xs, batch_ys = mnist.train.next_batch(batch_size)

            x_image = tf.reshape(batch_xs, [-1,28,28,1])

            h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
            h_pool1 = max_pool_2x2(h_conv1)

            h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
            h_pool2 = max_pool_2x2(h_conv2)

            h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
            h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)


            y_conv=tf.nn.softmax(tf.matmul(h_fc1, W_fc2) + b_fc2)

            cross_entropy = tf.reduce_mean(-tf.reduce_sum(batch_ys * tf.log(y_conv), reduction_indices=[1]))
            #optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cross_entropy)

            optimizer = tf.train.AdadeltaOptimizer(learning_rate).minimize(cross_entropy)
            sess.run(init)

            correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(batch_ys,1))
            accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
            sess.run([cross_entropy, y_conv,optimizer])
            print cross_entropy.eval()

【问题讨论】：

首先，我真的认为模型应该脱离循环。将h_*、cross_entropy、优化器、准确率等放在“b_fc2 = bias_variable([10])”行之后。

【参考方案1】：

这里的问题是tf.initialize_all_variables() 是一个误导性名称。它实际上意味着“返回一个初始化所有已经创建的变量的操作（在默认图中）”。当您调用 tf.train.AdadeltaOptimizer(...).minimize() 时，TensorFlow 会创建 其他 变量，这些变量未包含在您之前创建的 init 操作中。

移动线：

init = tf.initialize_all_variables()

...在tf.train.AdadeltaOptimizer 的构造之后应该使您的程序工作。

注意您的程序会在每个训练步骤中重建除变量之外的整个网络。这可能是非常低效的，并且 Adadelta 算法不会像预期的那样适应，因为它的状态在每一步都重新创建。我强烈建议将代码从batch_xs 的定义移动到在两个嵌套for 循环之外创建optimizer。您应该为batch_xs 和batch_ys 输入定义tf.placeholder() 操作，并使用sess.run() 的feed_dict 参数来传递mnist.train.next_batch() 返回的值。