如何在張量的特定索引處打印值

Question

此tensorflow代碼來自本教程 。 我想知道是否有一種方法可以在張量的特定索引處打印值？ 例如，在下面的會話中，我可以打印張量y_的第1行第1列的值嗎？它應該看起來像[0,0,0,1,0,0,0,0,0,0]？

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

import tensorflow as tf

x = tf.placeholder(tf.float32, [None, 784])

W = tf.Variable(tf.zeros([784, 10]))

b = tf.Variable(tf.zeros([10]))

y = tf.nn.softmax(tf.matmul(x, W) + b)

y_ = tf.placeholder(tf.float32, [None, 10])

cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))

train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

sess = tf.InteractiveSession()

tf.global_variables_initializer().run()

for _ in range(10):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

    correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))

    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

    print(sess.run(y_))

    print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))

Answer 1

在Session運行placeholder ，必須使用sess.run()方法的feed_dict屬性將數據傳遞到占位符。

因此，根據您的問題，要查看張量y_的第一行和第一列，請將代碼調整為： sess.run(y_[0:][0], feed_dict = {y_: batch_ys}) 。 下面的整個代碼塊應為您提供預期的結果：

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

import tensorflow as tf

x = tf.placeholder(tf.float32, [None, 784])

W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))

y = tf.nn.softmax(tf.matmul(x, W) + b)
y_ = tf.placeholder(tf.float32, [None, 10])

cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), \
                                                reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

sess = tf.InteractiveSession()
tf.global_variables_initializer().run()

for _ in range(10):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

    print('Values of y\n{}'.format(sess.run(y_[0:][0], \
                                 feed_dict = {y_: batch_ys})))

print(sess.run(accuracy, feed_dict={x: mnist.test.images, \
                                       y_: mnist.test.labels}))

sess.close()

輸出：

Values of y
[0. 0. 0. 0. 1. 0. 0. 0. 0. 0.]
Values of y
[1. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
Values of y
[0. 0. 0. 0. 0. 1. 0. 0. 0. 0.]
Values of y
[0. 0. 0. 1. 0. 0. 0. 0. 0. 0.]
Values of y
[0. 0. 1. 0. 0. 0. 0. 0. 0. 0.]
Values of y
[0. 0. 0. 0. 0. 0. 0. 0. 0. 1.]
Values of y
[0. 0. 0. 1. 0. 0. 0. 0. 0. 0.]
Values of y
[0. 0. 0. 0. 1. 0. 0. 0. 0. 0.]
Values of y
[0. 0. 0. 0. 0. 0. 0. 0. 1. 0.]
Values of y
[0. 0. 0. 0. 0. 0. 0. 0. 0. 1.]