0

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：尝试使用未初始化的值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op u'Adadelta/update_Variable_7/ApplyAdadelta'引起，

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

如本文所述，我尝试在 adagrad 语句之后重新初始化会话变量，但这也无济于事。

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()
4

1 回答 1

7

这里的问题是这tf.initialize_all_variables()是一个误导性的名称。它的真正意思是“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 时tf.train.AdadeltaOptimizer(...).minimize()，TensorFlow 会创建其他变量，这些变量未包含在init您之前创建的操作中。

移动线路：

init = tf.initialize_all_variables()

...构建后应该tf.train.AdadeltaOptimizer使您的程序正常工作。

注意：您的程序会在每个训练步骤中重建整个网络，除了变量。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定义移动batch_xs到创建optimizer两个嵌套for循环的外部。您应该为和输入定义tf.placeholder()操作，并使用参数to 传入由.batch_xsbatch_ysfeed_dictsess.run()mnist.train.next_batch()

于 2016-04-26T02:56:23.350 回答