import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data
# Loading data set MNIST = input_data.read_data_sets ( " MNIST_data " , one_hot = True) # batch size the batch_size = 64 # calculates a total period of a number of batches n_batch mnist.train.num_examples // = the batch_size # define two placeholder X = tf.placeholder (tf.float32, [None, 784 ]) Y = tf.placeholder (tf.float32, [None, 10 ]) # Create a simple neural network: 784-10 W is = tf.Variable ( tf.truncated_normal ([784,10], STDDEV = 0.1 )) B = tf.Variable (tf.zeros ([10]) + 0.1 ) Prediction = tf.nn.softmax (tf.matmul (X, W is) + B ) # Quadratic cost function Loss = tf.losses.mean_squared_error (Y, Prediction) # using a gradient descent method Train tf.train.GradientDescentOptimizer = (0.3 ) .minimize (Loss) # store the result in a Boolean list correct_prediction = tf.equal (tf.argmax (Y,. 1), tf.argmax (Prediction,. 1 )) # required accuracy accuracy = tf.reduce_mean (tf.cast (correct_prediction, tf.float32)) with tf.Session () AS Sess: # variable initialization sess.run (tf.global_variables_initializer ()) # cycles epoch: trained once all the data is a cycle for Epoch in the Range (21 ): for BATCH inRange (n_batch): # access to data and a tag batch batch_xs, batch_ys = mnist.train.next_batch (the batch_size) sess.run (Train, feed_dict = {X: batch_xs, Y: batch_ys}) # each training cycle do a test ACC = sess.run (Accuracy, feed_dict = {X: mnist.test.images, Y: mnist.test.labels}) Print ( " Iter " + STR (Epoch) + " , the Accuracy testing " + STR (ACC ))