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优化器构建CNN,但我收到以下错误.

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

[[Node: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op u'Adadelta/update_Variable_7/ApplyAdadelta'引起,

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

我尝试在adagrad语句之后重新初始化会话变量,如本文所述,但这也没有帮助.

我怎样才能避免这个错误？谢谢.

Tensorflow:使用Adam优化器

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

这里的问题是这tf.initialize_all_variables()是一个误导性的名称.它实际上意味着"返回一个初始化已经创建的所有变量的操作(在默认图形中)".调用时tf.train.AdadeltaOptimizer(...).minimize(),TensorFlow会创建其他变量,这些变量不在init您之前创建的op中.

移动线:

init = tf.initialize_all_variables()

...... 以后的建设tf.train.AdadeltaOptimizer应该让你的工作方案.

注意:除了变量之外,您的程序还会在每个训练步骤中重建整个网络.这可能是非常低效的,并且Adadelta算法将无法按预期进行调整,因为其状态在每个步骤上重新创建.我强烈建议将代码从定义移动batch_xs到optimizer两个嵌套for循环外部的创建.您应该tf.placeholder()为batch_xs和batch_ys输入定义操作,并使用feed_dict参数sess.run()来传递返回的值mnist.train.next_batch().