CNN 的 Tensorflow 中的占位符缺失错误

Question

我正在使用张量流运行 MNIST 数据库上的卷积神经网络。但是我收到以下错误。

tensorflow.python.framework.errors.InvalidArgumentError: You must feed a value for placeholder tensor 'x' with dtype float [[Node: x = Placeholderdtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/cpu:0"]]

x = tf.placeholder(tf.float32, [None, 784], name='x') # mnist data image of shape 28*28=784

我以为我使用 feed_dict 正确地更新了 x 的值，但它说我没有更新占位符 x 的值。

此外，我的代码中还有其他逻辑缺陷吗？

如有任何帮助，我们将不胜感激。谢谢

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 = 10
batch_size = 100
display_step = 1

# tf Graph Input
#x = tf.placeholder(tf.float32, [50, 784], name='x') # mnist data image of shape 28*28=784
#y = tf.placeholder(tf.float32, [50, 10], name='y') # 0-9 digits recognition => 10 classes

# 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)


    # Training cycle
    for i in range(1000):
        print i
        batch_xs, batch_ys = mnist.train.next_batch(50)

        x_image = tf.reshape(x, [-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(y * tf.log(y_conv), reduction_indices=[1]))
        sess.run(
          [cross_entropy, y_conv],
          feed_dict={x: batch_xs, y: batch_ys})

        correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y,1))
        print correct_prediction.eval()
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

Answer 1

您为什么要尝试创建占位符变量？您应该能够直接使用 mnist.train.next_batch(50) 生成的输出，前提是您将 correct_prediction 的计算和精度移动到模型本身内部。

batch_xs, batch_ys = mnist.train.next_batch(50)
x_image = tf.reshape(batch_xs, [-1,28,28,1])
...
cross_entropy = tf.reduce_mean(-tf.reduce_sum(batch_ys * tf.log(y_conv), reduction_indices=[1]))
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(batch_ys,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
predictions_correct, acc = sess.run([cross_entropy, y_conv, correct_prediction, accuracy])
print predictions_correct, acc

Answer 2

您收到该错误是因为您试图运行 eval() correct_prediction。该张量需要批量输入（x 和 y）才能进行评估。您可以通过将其更改为来更正错误：

print correct_prediction.eval(feed_dict={x: batch_xs, y: batch_ys})

但正如 Benoit Steiner 所提到的，您可以轻松地将其拉入模型中。

更笼统地说，您没有在此处进行任何类型的优化，但也许您还没有着手去做。就目前而言，它只会在一段时间内打印出错误的预测。 :)

Answer 3

首先，你的 x 和 y 被注释掉了，如果你的实际代码中存在这两个问题，那很可能是问题所在。

correct_prediction.eval() 等同于 tf.session.run(correct_prediction) （或者在你的情况下 sess.run() ）因此需要相同的语法*。因此它需要 correct_prediction.eval(feed_dict={x: batch_xs, y: batch_ys}) 才能运行，但是请注意，这通常是 RAM 密集型的，可能会导致您的系统挂起。由于 ram 的使用，将精度函数拉入模型可能是个好主意。

我没有看到利用交叉熵的优化函数，但我从未尝试过不使用它，所以如果它有效，请不要修复它。但如果最终抛出错误，您可能想尝试：

optimizer = optimizer = tf.train.AdamOptimizer().minimize(cross_entropy)

并替换

中的“cross_entropy”

sess.run([cross_entropy, y_conv],feed_dict={x: batch_xs, y: batch_ys})

与“optimizer”

https://pythonprogramming.net/tensorflow-neural-network-session-machine-learning-tutorial/

检查脚本的准确性评估部分。

CNN 的 Tensorflow 中的占位符缺失错误

Placeholder missing error in Tensor flow for CNN

python

mnist

deep-learning

torch

tensorflow