卷積神經網絡識別手寫數字實例：

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


# 定義一個初始化權重的函數
def weight_variables(shape):
    w = tf.Variable(tf.random_normal(shape=shape,mean=0.0,stddev=1.0))
    return w


# 定義一個初始化偏置的函數
def bias_variables(shape):
    b = tf.Variable(tf.constant(0.0,shape=shape))
    
 
return b


def model():
    ‘‘‘
    自定義的卷積模型
    :return:
    ‘‘‘

    # 1.準備數據的占位符  x [None,784]  y_ture [None,10]
    with tf.variable_scope(‘data‘):
        x = tf.placeholder(tf.float32,[None,784])

        y_true = tf.placeholder(tf.int32,[None,10])
    # 2. 一卷積層 卷積：5*5*1，,32個，strides=1 激活：tf.nn.relu 池化
 

    with tf.variable_scope(‘conv1‘):
        # 隨機初始化權重 偏置[32]
        w_conv1 = weight_variables([5,5,1,32])

        b_conv1 = bias_variables([32])

        # 對x進行形狀的改變[None,784]  [None,28,28,1]
        x_reshape = tf.reshape(x,[-1,28,28,1])

        # [None,28,28,1]---->[None,28,28,32]
        x_relu1 = tf.nn.relu(tf.nn.conv2d(x_reshape,w_conv1,strides=[1,1,1,1],padding=‘
 
SAME‘) + b_conv1)

        # 池化 2*2 ， strides2 [None,28,28,32]---->[None,14,14,32]
        x_pool1 = tf.nn.max_pool(x_relu1,ksize=[1,2,2,1],strides=[1,2,2,1],padding=‘SAME‘)

    # 3. 二卷積層 卷積：5*5*32 64個filter,strides=1 激活：tf.nn.relu 池化：
    with tf.variable_scope(‘conv2‘):
        # 隨機初始化權重   權重：[5,5,32,64]  偏置[64]
        w_conv2 = weight_variables([5,5,32,64])

        b_conv2 = bias_variables([64])

        # 卷積，激活，池化計算
        # [None,14,14,32]---->[None,14,14,64]
        x_relu2 = tf.nn.relu(tf.nn.conv2d(x_pool1,w_conv2,strides=[1,1,1,1],padding=‘SAME‘) + b_conv2)

        # 池化 2*2 strides 2,[None,14,14,64]--->[None,7,7,64]
        x_pool2 = tf.nn.max_pool(x_relu2,ksize=[1,2,2,1],strides=[1,2,2,1],padding=‘SAME‘)

    # 4. 全連接層 [None,7,7,64]--->[None,7*7*64]*[7*7*64,10] + [10] = [None,10]
    with tf.variable_scope(‘conv2‘):
        # 隨機初始化權重和偏置
        w_fc = weight_variables([7*7*64,10])

        b_fc = bias_variables([10])

        # 修改形狀 [None,7,7,64] --->[None,7*7*64]
        x_fc_reshape = tf.reshape(x_pool2,[-1,7*7*64])

        # 進行矩陣運算得出每個樣本的10個結果
        y_predict = tf.matmul(x_fc_reshape,w_fc) + b_fc

    return x,y_true,y_predict


def conv_fc():
    # 1. 獲取真實數據
    mnist = input_data.read_data_sets(‘./data/mnist/‘,one_hot=True)

    # 2. 定義模型，得出輸出
    x,y_true,y_predict = model()

    # 進行交叉熵損失計算
    # 3. 求出所有樣本的損失，然後求平均值
    with tf.variable_scope(‘soft_cross‘):
        # 求平均交叉熵損失
        loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_true,logits=y_predict))

    # 4. 梯度下降求出損失
    with tf.variable_scope(‘optimizer‘):
        train_op = tf.train.GradientDescentOptimizer(0.0001).minimize((loss))

    # 5. 計算準確率
    with tf.variable_scope(‘acc‘):
        equal_list = tf.equal(tf.argmax(y_true,1),tf.argmax(y_predict,1))

        # equal_list  None個樣本 [1,0,1,0,0,0,1,1,...]
        accracy = tf.reduce_mean(tf.cast(equal_list,tf.float32))

    # 定義一個初始化變量的op
    init_op = tf.global_variables_initializer()

    # 開啟會話運行
    with tf.Session() as sess:
        sess.run(init_op)

        # 循環去訓練
        for i in range(1000):
            # 取出真實存在的特征值和目標值
            mnist_x,mnist_y = mnist.train.next_batch(50)

            # 運行train_op訓練
            sess.run(train_op,feed_dict={x:mnist_x,y_true:mnist_y})

            print(‘訓練第%d步，準確率為:%f‘ % (i,sess.run(accracy,feed_dict={x:mnist_x,y_true:mnist_y})))


    return None


if __name__ == ‘__main__‘:
    conv_fc()

卷積神經網絡識別手寫數字實例