| 13 | mnist = input_data.read_data_sets('MNIST_data', one_hot=True) |
| 14 | |
| 15 | def compute_accuracy(v_xs, v_ys): |
| 16 | global prediction |
| 17 | y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1}) |
| 18 | correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1)) |
| 19 | accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) |
| 20 | result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys, keep_prob: 1}) |
| 21 | return result |
| 22 | |
| 23 | def weight_variable(shape): |
| 24 | initial = tf.truncated_normal(shape, stddev=0.1) |