上一篇部落格中，我們已經訓練好了模型

接下來我們要載入模型並識別真實場景下的一個手寫體數字

在此之前，我們先要準備好一張28*28畫素的影象（可用ps製作），然後通過處理將畫素的強度值變為0-1之間，之後即可輸入模型進行識別。

儲存已訓練的模型檔案如下：

程式碼如下：

import tensorflow as tf
import matplotlib.pyplot as plt
from PIL import Image


def imageprepare(imagepath):
    im = Image.open(imagepath) #讀取的圖片所在路徑，注意是28*28畫素
    plt.imshow(im)  #顯示需要識別的圖片
    plt.show()
    im = im.convert('L')
    tv = list(im.getdata())
    tva = [(255-x)*1.0/255.0 for x in tv]
    return tva


def weight_variable(shape, name):
    initial = tf.truncated_normal(shape, stddev=0.1)  # 生成一個截斷的正態分佈
    return tf.Variable(initial, name=name)


# 初始化偏置
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):
    # x input tensor of shape `[batch, in_height, in_width, in_channels]`
    # W filter / kernel tensor of shape [filter_height, filter_width, in_channels, out_channels]
    # `strides[0] = strides[3] = 1`. strides[1]代表x方向的步長，strides[2]代表y方向的步長
    # padding: A `string` from: `"SAME", "VALID"`
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')


# 池化層
def max_pool_2x2(x):
    # ksize [1,x,y,1]
    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'):
    # 定義兩個placeholder
    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'):
        # 改變x的格式轉為4D的向量[batch, in_height, in_width, in_channels]`
        x_image = tf.reshape(x, [-1, 28, 28, 1], name='x_image')

with tf.name_scope('Conv1'):
    # 初始化第一個卷積層的權值和偏置
    with tf.name_scope('W_conv1'):
        W_conv1 = weight_variable([5, 5, 1, 32], name='W_conv1')  # 5*5的取樣視窗，32個卷積核從1個平面抽取特徵
    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

with tf.name_scope('Conv2'):
    # 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')  # 5*5的取樣視窗，64個卷積核從32個平面抽取特徵
    with tf.name_scope('b_conv2'):
        b_conv2 = bias_variable([64], name='b_conv2')  # 每一個卷積核一個偏置值

    # 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')  # 上一場有7*7*64個神經元，全連線層有1024個神經元
    with tf.name_scope('b_fc1'):
        b_fc1 = bias_variable([1024], name='b_fc1')  # 1024個節點

    # 把池化層2的輸出扁平化為1維
    with tf.name_scope('h_pool2_flat'):
        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)
        res = tf.argmax(prediction, 1)


saver = tf.train.Saver()
image = imageprepare('6.png')


with tf.Session() as sess:
    saver.restore(sess, "cnn_Model/model.ckpt")
    result = sess.run(res,feed_dict={x: [image],keep_prob:1.0})
    print('識別結果為：%d' %result)
 

製作的影象和識別結果如下：