在Tensorflow中使用Adadelta优化器时未初始化的值错误

Question

我正在尝试使用Adagrad优化器来构建CNN，但出现以下错误。

tensorflow.python.framework.errors.FailedPreconditionError：试图使用未初始化值Variable_7/Adadelta

[[节点：Adadelta/update_Variable_7/ApplyAdadelta = ApplyAdadelta [T = DT_FLOAT，_class = [“LOC ：变量_7，变量_7/Adadelta，变量_7/Adadelta_1，Adadelta/lr，Adadelta/rho，_变量_7“]，use_locking = false，_device =”/ job：localhost/replica：0/task：0/cpu：0“ adadelta/epsilon，gradients/add_3_grad/tuple/control_dependency_1）]] 由op u'Adadelta/update_Variable_7/ApplyAdadelta引起，

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

我想在这篇文章中提到的adagrad语句后重新初始化会话变量，但没有帮助过。

我该如何避免这个错误？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() 

Answer 1

这里的问题是，tf.initialize_all_variables()是一个误导性的名称。它确实意味着“返回一个操作，该操作初始化所有已创建的变量（在默认图形中）”。当您致电tf.train.AdadeltaOptimizer(...).minimize()时，TensorFlow会创建其他变量，但您未在前面创建的init运算符中未包含该变量。

移动线：

init = tf.initialize_all_variables() 

... 的tf.train.AdadeltaOptimizer建成后应该让你的工作方案。

N.B.在每个培训步骤中，除了变量之外，您的程序还会重建整个网络。这可能效率很低，并且Adadelta算法不会按预期进行调整，因为其状态在每一步都会重新创建。我强烈建议将代码从batch_xs的定义移到在两个嵌套for循环外创建optimizer。您应该为batch_xs和batch_ys输入定义tf.placeholder() ops，并使用feed_dict参数指向sess.run()以传入mnist.train.next_batch()返回的值。