1 import tensorflow as tf
2 import input_data
3
4 mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
5
6 x = tf.placeholder("float", [None, 784])
7 w = tf.Variable(tf.zeros([784, 10]))
8 b = tf.Variable(tf.zeros([10]))
9
10 y = tf.nn.softmax(tf.matmul(x, w) + b)
11 y_ = tf.placeholder("float", [None, 10])
12
13 cross_entropy = -tf.reduce_sum(y_ * tf.log(y))
14 train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
15
16 init = tf.global_variables_initializer()
17 with tf.Session() as sess:
18 sess.run(init)
19 for i in range(1000):
20 batch_xs, batch_ys = mnist.train.next_batch(100)
21 sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
22 correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
23 accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
24 print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))