import sys,os
import numpy as np
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data 

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

sess = tf.InteractiveSession()
x = tf.placeholder('float',shape=[None, 784])
y_ = tf.placeholder('float', shape=[None, 10])


def weight_varialbe(shape):
    init_val = tf.truncated_normal( shape, stddev=0.1 )
    return tf.Variable(init_val)


def bias_variable(shape):
    init_val = tf.constant( 0.1, shape=shape )
    return tf.Variable(init_val)


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')


W_conv1 = weight_varialbe( [5,5,1,32] )
b_conv1 = bias_variable( [32] )

x_image = tf.reshape(x,[-1,28,28,1] )
h_conv1 = tf.nn.relu( conv2d(x_image, W_conv1) + b_conv1 )
h_pool1 = max_pool_2x2(h_conv1)


# layer2
W_conv2 = weight_varialbe( [5,5,32,64] )
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu( conv2d(h_pool1, W_conv2) + b_conv2 )
h_pool2 = max_pool_2x2(h_conv2)


W_fc1 = weight_varialbe( [7*7*64, 1024] )
b_fc1 = bias_variable([1024])


h_pool2_flat = tf.reshape( h_pool2, [-1, 7*7*64] )
h_fc1 = tf.nn.relu( tf.matmul( h_pool2_flat, W_fc1 ) + b_fc1 )


keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob )


W_fc2 = weight_varialbe([1024,10])
b_fc2 = bias_variable([10])
y_conv = tf.nn.softmax( tf.matmul(h_fc1_drop, W_fc2) + b_fc2 )



cross_entropy = -tf.reduce_sum( y_ * tf.log(y_conv) )
train_step = tf.train.AdamOptimizer(1e-4).minimize( cross_entropy )
correct_perd = tf.equal( tf.argmax(y_conv, 1), tf.argmax(y_,1) )
accuracy = tf.reduce_mean( tf.cast( correct_perd, "float" ) )


sess.run(tf.initialize_all_variables())



for i in range(2000):
    batch = mnist.train.next_batch(50)
    train_acc = accuracy.eval( feed_dict={x:batch[0], y_:batch[1], keep_prob:1.0} )
    print('setp %d accuracy=%g'%( i, train_acc ))
    train_step.run(feed_dict={ x:batch[0], y_:batch[1], keep_prob:0.5 } )


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


if __name__ == "__main__":
    #counter()
    #mul_sensor()
    #feed_sensor()


    pass
 

最終在測試集上驗證準確度為0.977。