#!/usr/bin/env python

 # -*- coding: utf-8 -*-

 # @Author  : mario

 # @File    : mnist_faltung.py

 # @Project : base

 # @Time    : 2018-12-19 14:11:38

 # @Desc    : File is ...

 import tensorflow as tf

 from tensorflow.examples.tutorials.mnist import input_data

 mnist = input_data.read_data_sets("data/", one_hot=True)

 def init_weight_variable(shape):

     initial = tf.truncated_normal(shape, stddev=0.1)

     return tf.Variable(initial)

 def init_bias_variable(shape):

     initial = tf.constant(0.1, shape=shape)

     return tf.Variable(initial)

 def conv2d(x, W):

     return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding="SAME")

 def max_pool_2x2(x):

     return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME")

 x = tf.placeholder(tf.float32, [None, 784])

 y_ = tf.placeholder(tf.float32, [None, 10])

 W_conv_1 = init_weight_variable([5, 5, 1, 32])

 b_conv_1 = init_bias_variable([32])

 x_image = tf.reshape(x, [-1, 28, 28, 1])

 h_conv_1 = tf.nn.relu(conv2d(x_image, W_conv_1) + b_conv_1)

 h_pool_1 = max_pool_2x2(h_conv_1)

 W_conv_2 = init_weight_variable([5, 5, 32, 64])

 b_conv_2 = init_bias_variable([64])

 h_conv_2 = tf.nn.relu(conv2d(h_pool_1, W_conv_2) + b_conv_2)

 h_pool_2 = max_pool_2x2(h_conv_2)

 W_fc_1 = init_weight_variable([7 * 7 * 64, 1024])

 b_fc_1 = init_bias_variable([1024])

 h_pool_flat = tf.reshape(h_pool_2, [-1, 7 * 7 * 64])

 h_fc_1 = tf.nn.relu(tf.matmul(h_pool_flat, W_fc_1) + b_fc_1)

 keep_prob = tf.placeholder(tf.float32)

 h_fc1_drop = tf.nn.dropout(h_fc_1, keep_prob)

 W_fc_2 = init_weight_variable([1024, 10])

 b_fc_2 = init_bias_variable([10])

 y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc_2) + b_fc_2)

 cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))

 train_step = tf.train.AdagradOptimizer(1e-4).minimize(cross_entropy)

 sess = tf.InteractiveSession()

 init = tf.global_variables_initializer()

 sess.run(init)

 for _ in range(20000):

     batch = mnist.train.next_batch(50)

     train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

 correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))

 accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

 print(accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))