mnist_softmax_regression

from tensorflow.examples.tutorials.mnist import input_dataimport tensorflow as tfdata_dir="mnist"mnist = input_data.read_data_sets(data_dir, one_hot=True)#regression modelx = tf.placeholder(tf.float32, [None, 784])W = tf.Variable(tf.zeros([784, 10]))b = tf.Variable(tf.zeros([10]))y = tf.matmul(x, W) + b #prediction#loss functiony_ = tf.placeholder(tf.float32, [None, 10]) #realcross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=y, labels=y_))#optimizertrain_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)#trainsess = tf.InteractiveSession()tf.global_variables_initializer().run()for _ in range(1000):    batch_xs, batch_ys = mnist.train.next_batch(100)    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})#estimatecorrect_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))accuracy = tf.reduce_mean( tf.cast(correct_prediction, tf.float32) )print (sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))

0.9188