mnist api 構建

0.文件結構如圖，data文件夾用來存放訓練後的權重，MNIST_data存放訓練數據和測試數據

1.搭建線性迴歸和cnn兩種模型，models.py

import tensorflow as tf

# y = wx+b

def regression(x):
    W = tf.Variable(tf.zeros([784,10]),name="W")
    b = tf.Variable(tf.zeros([10]),name="b")
    y = tf.nn.softmax(tf.matmul(x,W)+b)

    return y, [W,b]

def convolutional(x , keep_prob):   #輸入值，和drop_out 比例
    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")
    def weight_varible(shape):
        initial = tf.truncated_normal(shape,stddev=0.1)
        return tf.Variable(initial)
    def bias_varible(shape):
        initial = tf.constant(0.1,shape=shape)
        return tf.Variable(initial)

    x_image = tf.reshape(x,[-1,28,28,1])  #-1 樣本數任意，，28 28 爲矩陣大小，，1 爲圖像深度
    W_conv1 = weight_varible([5,5,1,32]) #卷積核爲5x5，單通道輸入（灰度圖像），三十二個特徵輸出
    b_conv1 = bias_varible([32])
    h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1)
    h_pool1 = max_pool_2x2(h_conv1)

    W_conv2 = weight_varible([5, 5, 32, 64]) #卷積核爲5x5，連接第一層輸出32通道輸入，64個輸出個特徵輸出
    b_conv2 = bias_varible([64])
    h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
    h_pool2 = max_pool_2x2(h_conv2)  #池化層


    #full connection   密集連接層
    W_fc1 = weight_varible([7*7*64,1024])
    b_fc1 = bias_varible([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)

    #dropout
    h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)
    W_fc2 = weight_varible([1024,10])
    b_fc2 = bias_varible([10])
    y = tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2) + b_fc2)  #網絡輸出

    return y , [W_conv1, b_conv1,W_conv2,b_conv2, W_fc1,b_fc1,W_fc2,b_fc2]  #返回網絡輸出，和此時的權重和偏置

2.regression.py  迴歸訓練

import os
import input_data
import models
import tensorflow as tf
data = input_data.read_data_sets('MNIST_data',one_hot=True) #通過特定方式，自動下載數據集
###被牆了，下載有問題

with tf.variable_scope("regression"):
    x = tf.placeholder(tf.float32,[None,784])
    y, variables = models.regression(x)

#train
y_ = tf.placeholder("float",[None,10])
cross_entropy = -tf.reduce_sum(y_*tf.log(y))   #計算交叉熵
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)  #訓練
correct_prediction = tf.equal(tf.arg_max(y,1),tf.argmax(y_,1))    #計算準確率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))  #計算準確率

saver = tf.train.Saver(variables)   #保存權重
with tf.Session() as sess:
    merged_summary_op = tf.summary.merge_all()
    summay_writer = tf.summary.FileWriter('/tmp/mnist_log/2', sess.graph)
    # summay_writer.add_graph(sess.graph)
    sess.run(tf.global_variables_initializer())  #初始化數據
    for _ in range(1000):
        batch_xs,batch_ys = data.train.next_batch(100)
        sess.run(train_step,feed_dict={x:batch_xs,y_:batch_ys})
    print((sess.run(accuracy,feed_dict={x:data.test.images,y_:data.test.labels})))
    path = saver.save(
        # sess,os.path.join(os.path.normpath(os.path.dirname(__file__)),'data','regression.ckpt'),write_meta_graph=False,write_state=False
        sess,os.path.join(os.path.dirname(__file__),'data','regression.ckpt'),write_meta_graph=False,write_state=False   ###os.path.dirname(__file__)爲當前路徑，不能含有漢字，否則會報錯：路徑不存在
    )
    print("Saved:",path)

3,convolution.py  cnn訓練

import os
import models
import tensorflow as tf
import input_data

data = input_data.read_data_sets('MNIST_data',one_hot=True)
#model
with tf.variable_scope("convolutional"):
    x = tf.placeholder(tf.float32,[None,784],name = 'x')
    keep_prob = tf.placeholder(tf.float32)
    y ,variables = models.convolutional(x,keep_prob)

#train
y_ = tf.placeholder(tf.float32,[None,10],name='y')
cross_entropy = -tf.reduce_sum(y_ * tf.log(y))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)#AdadeltaOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

saver = tf.train.Saver(variables)

with tf.Session() as sess:
    merged_summary_op = tf.summary.merge_all()
    summay_writer = tf.summary.FileWriter('/tmp/mnist_log/1',sess.graph)
    summay_writer.add_graph(sess.graph)
    # summay_writer.add_graph(sess.)
    sess.run(tf.global_variables_initializer())

    for i in range(20000):
        batch = data.train.next_batch(50)
        if i%100 == 0:
            train_accuracy = accuracy.eval(feed_dict={x:batch[0],y_:batch[1],keep_prob:1.0})
            print("srep %d, train accuracy %g" % (i,train_accuracy))

        sess.run(train_step,feed_dict={x:batch[0],y_:batch[1],keep_prob:0.5})
    print(sess.run(accuracy,feed_dict={x:data.test.images,y_:data.test.labels,keep_prob:1.0}))

    path = saver.save(sess,os.path.join(os.path.dirname(__file__),'data','convolutional.ckpt'),write_meta_graph=False,write_state=False)

    print("Saved:",path)

4.執行regression.py 和 convolution.py 後訓練模型會保存在指定的文件夾下，在下面的main.py中使用訓練好的數據集

import numpy as np
import tensorflow as tf
from mnist import models
from PIL import Image
from PIL import ImageDraw
from PIL import ImageFont

x = tf.placeholder("float",[None,784])
sess = tf.Session()

##迴歸
with tf.variable_scope("regression"):
    y1, variables = models.regression(x)
saver = tf.train.Saver(variables)
saver.restore(sess,"mnist/data/regression.ckpt")
##迴歸

##cnn
with tf.variable_scope("convolutional"):
    keep_prob = tf.placeholder("float")
    y2,variables = models.convolutional(x,keep_prob)

saver = tf.train.Saver(variables)
saver.restore(sess,"mnist/data/convolutional.ckpt")
##cnn

def regression(input):  #處理輸入圖片
    return sess.run(y1,feed_dict={x:input}).flatten().tolist()
def convolutional(input):#處理輸入圖片（卷積）
    return sess.run(y2,feed_dict={x:input,keep_prob:1.0}).flatten().tolist()


def input_image(img):  #對圖片進行處理
    img_l = img.convert("L").resize((28,28))
    return ((255 - np.array(img_l, dtype=np.uint8)) / 255.0).reshape([1,784])
if __name__ == '__main__':

    each = '1'
    blank = Image.new("RGB", [56, 56], "white")  # 創建背景[269,70]
    drawObject = ImageDraw.Draw(blank)  # 加載背景
    ttf = 'tyc-num-d325fc6b6b.ttf'  # 字體文件，在網上找的字體文件，生成字體，畫在圖片上，供網絡輸入
    Font4 = ImageFont.truetype(ttf, 24)  # 加載字體,字體大小
    drawObject.text([20, 20], each, font=Font4, fill='black')  # 以字體庫生成字體圖片，起始座標[5, 5]，字體黑色'123456890.' 026974381
    #blank.save(each.replace(".","point")+".jpg")
    blank.save(each +".jpg")
    photos = input_image(blank) #處理圖片
    out_put1 = regression(photos)
    out_put2 = convolutional(photos)
    print(out_put1.index(max(out_put1)))
    lis = []
    for each_p in out_put2:
        lis.append('{:.16f}'.format(each_p))  #cnn輸出的是指數形式的值，轉化爲浮點形式
    print(lis.index(max(lis)))
    print("###############")