CODEWITHSUNDEEP
pythontensorflow
arcoxia tom
arcoxia tom

Reputation: 1711

How to print the value at a particular index of a tensor

This tensorflow code is from this tutorial. I am wondering if there is a way to print the values at particular indexes of a tensor? For example in the session below can I print the value of row 1 column 1 of a the tensor y_ which should look something like [0,0,0,1,0,0,0,0,0]?

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}))

Upvotes: 0

Views: 282

Answers (1)

Ekaba Bisong
Ekaba Bisong

Reputation: 2982

When running a placeholder within a Session, you must pass in the data to the placeholder by using the feed_dict attribute of the method sess.run().

So by your question, to view the first row and column of the tensor y_, adjust your code to: sess.run(y_[0:][0], feed_dict = {y_: batch_ys}). The entire code block below should give you the results you expect:

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()

Output:

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.]

Upvotes: 0

Related Questions