import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data


mnist = input_data.read_data_sets('F:/PY/MNIST_data/', one_hot=True)

batch_size = 100
n_batch = mnist.train.num_examples // batch_size


#引數概要
def variable_summaries(var):
    with tf.name_scope('summaries'):
        mean = tf.reduce_mean(var)
        tf.summary.scalar('mean', mean)#平均值
        with tf.name_scope('stddev'):
            stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
        tf.summary.scalar('stddev', stddev)#標準差
        tf.summary.scalar('max', tf.reduce_max(var))#最大值
        tf.summary.scalar('min', tf.reduce_min(var))#最小值
        tf.summary.histogram('histogram', var)#直方圖


def weight_variable(shape, name):
    initial = tf.truncated_normal(shape, stddev = 0.1)
    return tf.Variable(initial, name=name)


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

#卷積層

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')

#名稱空間
with tf.name_scope('input'):
    x = tf.placeholder(tf.float32, [None, 784], name= 'x-input')
    y = tf.placeholder(tf.float32, [None, 10],name ='y-input')
    with tf.name_scope('x_image'):
        x_image = tf.reshape(x, [-1, 28, 28, 1], name='x_iamge')

with tf.name_scope('Conv1'):
    #第一層
    with tf.name_scope('W_conv1'):
        W_conv1 = weight_variable([5, 5, 1, 32],name='W_conv1')
    with tf.name_scope('b_conv1'):
        b_conv1 = bias_variable([32], name='b_conv1') #每一個卷積核一個偏置值

        # 把x_image和權值向量進行卷積，再加上偏置值，然後應用於relu啟用函式
    with tf.name_scope('conv2d_1'):
        conv2d_1 = conv2d(x_image, W_conv1) + b_conv1
    with tf.name_scope('relu'):
        h_conv1 = tf.nn.relu(conv2d_1)
    with tf.name_scope('h_pool1'):
        h_pool1 = max_pool_2x2((h_conv1)) #進行max-pooling
kernel_transposed = tf.transpose (W_conv1, [3, 0, 1, 2])
with tf.name_scope('Conv2'):
    #第二層
    # 初始化第二個卷積層的權值和偏置
    with tf.name_scope('W_conv2'):
        W_conv2 = weight_variable([5, 5, 32, 64], name= 'W_conv2')
    with tf.name_scope('b_conv2'):
        b_conv2 = bias_variable([64], name='b_conv2')
    # 把h_pool1和權值向量進行卷積，再加上偏置值，然後應用於relu啟用函式
    with tf.name_scope('conv2d_2'):
        conv2d_2 = conv2d(h_pool1,W_conv2)+ b_conv2
    with tf.name_scope('relu'):
        h_conv2 = tf.nn.relu(conv2d_2)
    with tf.name_scope('h_pool2'):
        h_pool2 = max_pool_2x2(h_conv2) #進行max-pooling


#28*28的圖片第一次卷積後還是28*28，第一次池化後變為14*14
#第二次卷積後為14*14，第二次池化後變為了7*7
#進過上面操作後得到64張7*7的平面
with tf.name_scope('fc1'):
    # 初始化第一個全連線層的權值
    with tf.name_scope('W_fc1'):
        W_fc1 = weight_variable([7*7*64,1024],name='W_fc1')
    with tf.name_scope('b_fc1'):
        b_fc1 = bias_variable([1024], name='b_fc1') #1024個節點

    with tf.name_scope('h_pool2_flat'):
        #把池化層2的輸出扁平化為1維
        h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64], name='h_pool2_flat')
    # 求第一個全連線層的輸出
    with tf.name_scope('wx_plus_b1'):
        wx_plus_b1 = tf.matmul(h_pool2_flat, W_fc1) +b_fc1
    with tf.name_scope('relu'):
        h_fc1 = tf.nn.relu(wx_plus_b1)

    # keep_prob用來表示神經元的輸出概率
    with tf.name_scope('keep_prob'):
        keep_prob = tf.placeholder(tf.float32, name='keep_prob')
    with tf.name_scope('h_fc1_drop'):
        h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob, name='h_fc1_drop')

with tf.name_scope('fc2'):
    # 初始化第二個全連線層
    with tf.name_scope('W_fc2'):
        w_fc2 = weight_variable([1024, 10], name='W_fc2')
    with tf.name_scope('b_fc2'):
        b_fc2 = bias_variable([10], name='b_fc2')
    with tf.name_scope('wx_plus_b2'):
        wx_plus_b2 = tf.matmul(h_fc1_drop, w_fc2) + b_fc2
    with tf.name_scope('softmax'):
        # 計算輸出
        prediction = tf.nn.softmax(wx_plus_b2)

#交叉熵代價函式
with tf.name_scope('cross_entropy'):
    cross_entropy  = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels= y,logits =prediction), name ='cross_entopy')
    tf.summary.scalar('cross_entropy', cross_entropy)
#使用AdamOptimizer進行優化
with tf.name_scope('train'):
    train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

#求準確率
with tf.name_scope('accuracy'):
    with tf.name_scope('correct_prediction'):
        #結果存放在一個布林列表中
        correct_prediction = tf.equal(tf.argmax(prediction,1),tf.argmax(y,1))#argmax返回一維張量中最大的值所在的位置
    with tf.name_scope('accuracy'):
        # 求準確率
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
        tf.summary.scalar('accuracy',accuracy)

# 合併所有的summary
merged = tf.summary.merge_all()

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())

    train_writer = tf.summary.FileWriter('logs/train', sess.graph)
    test_writer = tf.summary.FileWriter('logs/test',sess.graph)
    # img0 = tf.summary.image('conv1/filters', kernel_transposed, max_outputs=6)
    # layer1_image1 = h_conv1[0:1, :, :, 0:14]
    # layer1_image1 = tf.transpose(layer1_image1, perm=[3, 1, 2, 0])
    # img1 = tf.summary.image("filtered_images_layer1", layer1_image1, max_outputs=16)
    # train_writer.add_summary(sess.run(img0))
    # train_writer.add_summary(sess.run(img1))

    for i in range(5001):
        # 訓練模型
        batch_xs1, batch_ys1 = mnist.train.next_batch(batch_size)
        sess.run(train_step, feed_dict={x:batch_xs1, y: batch_ys1, keep_prob: 0.7})
        # 記錄訓練集計算的引數
        summary = sess.run(merged, feed_dict ={x:batch_xs1, y:batch_ys1, keep_prob:1.0})
        train_writer.add_summary(summary,i)
        batch_xs, batch_ys = mnist.test.next_batch(batch_size)
        summary1 = sess.run(merged, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.0})
        test_writer.add_summary(summary1, i)



        if i%100 ==0:
            test_acc = sess.run(accuracy, feed_dict={x:mnist.test.images, y:mnist.test.labels, keep_prob:1.0})
            train_acc = sess.run(accuracy, feed_dict={x:mnist.train.images[:10000],y:mnist.train.labels[:10000],keep_prob:0.7})
            print("Iter"+str(i)+".Testing Accuracy="+str(test_acc)+",Traning Accuracy="+str(train_acc))


 

Iter4500.Testing Accuracy=0.9871,Traning Accuracy=0.9895
Iter4600.Testing Accuracy=0.9867,Traning Accuracy=0.9885
Iter4700.Testing Accuracy=0.986,Traning Accuracy=0.9881
Iter4800.Testing Accuracy=0.9873,Traning Accuracy=0.9881
Iter4900.Testing Accuracy=0.9875,Traning Accuracy=0.9894
Iter5000.Testing Accuracy=0.9873,Traning Accuracy=0.9889