keras和tensorflow搭建MNIST手写数字识别

MNIST手写数字集

　　MNIST是一个由美国由美国邮政系统开发的手写数字识别数据集。手写内容是0~9，一共有60000个图片样本，我们可以到MNIST官网免费下载，总共4个.gz后缀的压缩文件，该文件是二进制内容。

train-images-idx3-ubyte.gz:  training set images   　  图片样本，用来训练模型

train-labels-idx1-ubyte.gz:  training set labels 　    图片样本对应的数字标签

t10k-images-idx3-ubyte.gz:   test set images   　　　　测试样本

t10k-labels-idx1-ubyte.gz:   test set labels 　　　　 测试样本对应的数字标签

训练数据集包含 60,000 个样本, 测试数据集包含 10,000 样本。在 MNIST 数据集中的每张图片由 28 x 28 个像素点构成, 每个像素点用一个灰度值表示。

我们通过以下代码来窥探一下MNIST数据集的内部数据集的划分，以及手写数字的长相．

import matplotlib.pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets('./mnist', one_hot=True)

# 将数组张换成图片形式
print(mnist.train.images.shape)         # 训练数据图片(55000, 784)
print(mnist.train.labels.shape)         # 训练数据标签(55000, 10)
print(mnist.test.images.shape)          # 测试数据图片(10000, 784)
print(mnist.test.labels.shape)          # 测试数据图片(10000, 10)
print(mnist.validation.images.shape)    # 验证数据图片(5000, 784)
print(mnist.validation.labels.shape)    # 验证数据图片(5000, 784)

print(mnist.train.labels[1])        # [0. 0. 0. 0. 0. 0. 0. 1. 0. 0.]
image = mnist.train.images[1].reshape(28, 28)
fig = plt.figure("图片展示")
plt.imshow(image,cmap='gray')
plt.axis('off')                     #不显示坐标尺寸
plt.show() 

 　　在画出数字的同时，同时取出标签．

from tensorflow.examples.tutorials.mnist import input_data
import math
import matplotlib.pyplot as plt
import numpy as np

mnist = input_data.read_data_sets('./mnist', one_hot=True)

# 画单张mnist数据集的数字
def drawdigit(position,image, title):
    plt.subplot(*position)                      # 星号元组传参
    plt.imshow(image, cmap='gray_r')
    plt.axis('off')
    plt.title(title)

# 取一个batch的数据，然后在一张画布上画batch_size个子图
def batchDraw(batch_size):
    images, labels = mnist.train.next_batch(batch_size)
    row_num = math.ceil(batch_size ** 0.5)      # 向上取整
    column_num = row_num
    plt.figure(figsize=(row_num, column_num))   # 行．列
    for i in range(row_num):
        for j in range(column_num):
            index = i * column_num + j
            if index < batch_size:
                position = (row_num, column_num, index+1)
                image = images[index].reshape(28, 28)
                # 取出列表中最大数的索引
                title = 'actual:%d' % (np.argmax(labels[index]))
                drawdigit(position, image, title)


if __name__ == '__main__':
    batchDraw(16)
    plt.show()

代码说明：

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

　　图像是由RGB三个数组组成的，而灰度图只是其中一个数组，而图像是由像素组成，每个像素的值在0~225之间，MNIST数据集中的每个数字都有28*28＝784个像素值．上面的代码如果reshape＝True(默认)，MNIST数据的shape=(?, 784)，如果reshape=False MNIST数据为(?, 28,28,1)．

Keras

DNN网络

from keras.models import Model
from keras.layers import Input, Dense, Dropout
from keras import regularizers
from keras.optimizers import Adam

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("mnist/", one_hot=True)
x_train = mnist.train.images         # 训练数据 (55000, 784)
y_train = mnist.train.labels         # 训练标签
x_test = mnist.test.images
y_test = mnist.test.images

# DNN网络结构
inputs = Input(shape=(784,))
h1 = Dense(64, activation='relu', kernel_regularizer=regularizers.l2(0.01))(inputs)     # 权重矩阵l2正则化
h1 = Dropout(0.2)(h1)
h2 = Dense(64, activation='relu', kernel_regularizer=regularizers.l2(0.01))(h1)         # 权重矩阵l2正则化
h2 = Dropout(0.2)(h2)
h3 = Dense(64, activation='relu', kernel_regularizer=regularizers.l2(0.01))(h2)         # 权重矩阵l2正则化
h3 = Dropout(0.2)(h3)
outputs = Dense(10, activation='softmax', kernel_regularizer=regularizers.l2(0.01))(h3) # 权重矩阵l2正则化
model = Model(input=inputs, output=outputs)

# 编译模型
opt = Adam(lr=0.01, beta_1=0.9, beta_2=0.999, epsilon=1e-08)        # epsilon模糊因子
model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])     # 交叉熵损失函数

# 开始训练
model.fit(x=x_train, y=y_train, validation_split=0.1, batch_size=128, epochs=4)
model.save('k_DNN.h5')

View Code

CNN网络

from keras.models import Model
from keras.layers import Input, Conv2D, MaxPooling2D, Reshape, Dense
from keras import regularizers
from keras.optimizers import Adam
from tensorflow.examples.tutorials.mnist import input_data

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

x_train = mnist.train.images         # 训练数据　(55000, 28, 28, 1)
y_train = mnist.train.labels         # 训练标签
x_test = mnist.test.images
y_test = mnist.test.images

# 网络结构
input = Input(shape=(28, 28, 1))
h1 = Conv2D(filters=64, kernel_size=(3,3), strides=(1, 1), padding='same', activation='relu')(input)
h1 = MaxPooling2D(pool_size=2, strides=2, padding='valid')(h1)

h1 = Conv2D(filters=32, kernel_size=(3,3), strides=(1, 1), padding='same', activation='relu')(h1)
h1 = MaxPooling2D()(h1)

h1 = Conv2D(filters=16, kernel_size=(3,3), strides=(1, 1), padding='same', activation='relu')(h1)
h1 = Reshape((16 * 7 * 7,))(h1)     # h1.shape (?, 16*7*7)

output = Dense(10, activation="softmax", kernel_regularizer=regularizers.l2(0.01))(h1)
model = Model(input=input, output=output)
model.summary()

# 编译模型
opt = Adam(lr=0.01, beta_1=0.9, beta_2=0.999, epsilon=1e-08)
model.compile(optimizer=opt, loss="categorical_crossentropy", metrics=["accuracy"])

# 开始训练
model.fit(x=x_train, y=y_train, validation_split=0.1, epochs=5)

model.save('k_CNN.h5')

View Code

RNN网络

from keras.models import Model
from keras.layers import Input, LSTM, Dense
from keras import regularizers
from keras.optimizers import Adam

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("./mnist/", one_hot=True)
x_train = mnist.train.images            # (28, 28, 1)
x_train = x_train.reshape(-1, 28, 28)
y_train = mnist.train.labels

# RNN网络结构
inputs = Input(shape=(28, 28))
h1 = LSTM(64, activation='relu', return_sequences=True, dropout=0.2)(inputs)
h2 = LSTM(64, activation='relu', dropout=0.2)(h1)
outputs = Dense(10, activation='softmax', kernel_regularizer=regularizers.l2(0.01))(h2)
model = Model(input=inputs, output=outputs)

# 编译模型
opt = Adam(lr=0.003, beta_1=0.9, beta_2=0.999, epsilon=1e-08)
model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])
# 训练模型
model.fit(x=x_train, y=y_train, validation_split=0.1, batch_size=128, epochs=5)

model.save('k_RNN.h5')

View Code

 

Tensorflow

DNN网络

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

mnist = input_data.read_data_sets("./mnist", one_hot=True)
# train image shape: (55000, 784)
# trian label shape: (55000, 10)
# val image shape: (5000, 784)
# test image shape: (10000, 784)
epochs = 2
output_size = 10
input_size = 784
hidden1_size = 512
hidden2_size = 256
batch_size = 1000
learning_rate_base = 0.005
unit_list = [784, 512, 256, 10]
batch_num = mnist.train.labels.shape[0] // batch_size


# 全连接神经网络
def dense(x, w, b, keeppord):
    linear = tf.matmul(x, w) + b
    activation = tf.nn.relu(linear)
    y = tf.nn.dropout(activation,keeppord)
    return y


def DNNModel(image, w, b, keeppord):
    dense1 = dense(image, w[0], b[0],keeppord)
    dense2 = dense(dense1, w[1], b[1],keeppord)
    output = tf.matmul(dense2, w[2]) + b[2]
    return output


# 生成网络的权重
def gen_weights(unit_list):
    w = []
    b = []
    # 遍历层数
    for i in range(len(unit_list)-1):
        sub_w = tf.Variable(tf.random_normal(shape=[unit_list[i], unit_list[i+1]]))
        sub_b = tf.Variable(tf.random_normal(shape=[unit_list[i+1]]))
        w.append(sub_w)
        b.append(sub_b)
    return w, b

x = tf.placeholder(tf.float32, [None, 784])
y_true = tf.placeholder(tf.float32, [None, 10])
keepprob = tf.placeholder(tf.float32)
global_step = tf.Variable(0)

w, b = gen_weights(unit_list)
y_pre = DNNModel(x, w, b, keepprob)
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=y_pre, labels=y_true))
tf.summary.scalar("loss", loss)                 # 收集标量
opt = tf.train.AdamOptimizer(0.001).minimize(loss, global_step=global_step)
predict = tf.equal(tf.argmax(y_pre, axis=1), tf.argmax(y_true, axis=1))       # 返回每行或者每列最大值的索引，判断是否相等
acc = tf.reduce_mean(tf.cast(predict, tf.float32))
tf.summary.scalar("acc", acc)                   # 收集标量
merged = tf.summary.merge_all()                 # 和并变量
saver = tf.train.Saver()                        # 保存和加载模型
init = tf.global_variables_initializer()        # 初始化全局变量
with tf.Session() as sess:
    sess.run(init)
    writer = tf.summary.FileWriter("./logs/tensorboard", tf.get_default_graph())      # tensorboard 事件文件
    for i in range(batch_num * epochs):
        x_train, y_train = mnist.train.next_batch(batch_size)
        summary, _ = sess.run([merged, opt], feed_dict={x:x_train, y_true:y_train, keepprob: 0.75})
        writer.add_summary(summary, i)              # 将每次迭代后的变量写入事件文件
        # 评估模型在验证集上的识别率
        if i % 50 == 0:
            feeddict = {x: mnist.validation.images, y_true: mnist.validation.labels, keepprob: 1.}      # 验证集
            valloss, accuracy = sess.run([loss, acc], feed_dict=feeddict)
            print(i, 'th batch val loss:', valloss, ', accuracy:', accuracy)

    saver.save(sess, './checkpoints/tfdnn.ckpt')        # 保存模型
    print('测试集准确度:', sess.run(acc, feed_dict={x:mnist.test.images, y_true:mnist.test.labels, keepprob:1.}))

writer.close()

View Code

CNN网络

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

epochs = 10
batch_size = 100
mnist = input_data.read_data_sets("mnist/", one_hot=True, reshape=False)
batch_nums = mnist.train.labels.shape[0] // batch_size

# 卷积结构
def conv2d(x, w, b):
    # x = (?, 28,28,1)
    # filter = [filter_height, filter_width, in_channels, out_channels]
    # data_format = [批次，高度，宽度，通道] # 第一个和第四个必须是1
    return tf.nn.conv2d(x, filter=w, strides=[1, 1, 1, 1], padding='SAME') + b
def pool(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
# 定义网络结构
def cnn_net(x, keepprob):
    # x = reshape=False (?, 28,28,1)
    w1 = tf.Variable(tf.random_normal([5, 5, 1, 64]))
    b1 = tf.Variable(tf.random_normal([64]))
    w2 = tf.Variable(tf.random_normal([5, 5, 64, 32]))
    b2 = tf.Variable(tf.random_normal([32]))
    w3 = tf.Variable(tf.random_normal([7 * 7 * 32, 10]))
    b3 = tf.Variable(tf.random_normal([10]))
    hidden1 = pool(conv2d(x, w1, b1))
    hidden1 = tf.nn.dropout(hidden1, keepprob)
    hidden2 = pool(conv2d(hidden1, w2, b2))
    hidden2 = tf.reshape(hidden2, [-1, 7 * 7 * 32])
    hidden2 = tf.nn.dropout(hidden2, keepprob)
    output = tf.matmul(hidden2, w3) + b3
    return output


# 定义所需占位符
x = tf.placeholder(tf.float32, [None, 28, 28, 1])
y_true = tf.placeholder(tf.float32, [None, 10])
keepprob = tf.placeholder(tf.float32)

# 在训练模型时，随着训练的逐步降低学习率。该函数返回衰减后的学习率。
global_step = tf.Variable(0)
learning_rate = tf.train.exponential_decay(0.01, global_step, 100, 0.96, staircase=True)

# 训练所需损失函数
logits = cnn_net(x, keepprob)
loss = tf.reduce_mean(tf.nn.tf.nn.softmax_cross_entropy_with_logits_v2(logits=logits, labels=y_true))
opt = tf.train.AdamOptimizer(learning_rate).minimize(loss, global_step=global_step)

# 定义评估模型
predict = tf.equal(tf.argmax(logits, 1), tf.argmax(y_true, 1))      # 预测值
accuracy = tf.reduce_mean(tf.cast(predict, tf.float32))             # 验证值

init = tf.global_variables_initializer()
# 开始训练
with tf.Session() as sess:
    sess.run(init)
    for k in range(epochs):
        for i in range(batch_nums):
            train_x, train_y = mnist.train.next_batch(batch_size)
            sess.run(opt, {x: train_x, y_true: train_y, keepprob: 0.75})
            # 评估模型在验证集上的识别率
            if i % 50 == 0:
                acc = sess.run(accuracy, {x: mnist.validation.images[:1000], y_true: mnist.validation.labels[:1000], keepprob: 1.})
                print(k, 'epochs, ', i, 'iters, ', ', acc :', acc)

View Code

RNN网络

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

epochs = 10
batch_size = 1000
mnist = input_data.read_data_sets("mnist/", one_hot=True)
batch_nums = mnist.train.labels.shape[0] // batch_size

# 定义网络结构
def RNN_Model(x, batch_size, keepprob):
    # rnn_layers = [tf.nn.rnn_cell.LSTMCell(size) for size in [28, 28]]
    rnn_cell = tf.nn.rnn_cell.LSTMCell(28)
    rnn_drop = tf.nn.rnn_cell.DropoutWrapper(rnn_cell, output_keep_prob=keepprob)
    # 创建由多个RNNCell组成的RNN单元。
    multi_rnn_cell = tf.nn.rnn_cell.MultiRNNCell([rnn_drop] * 2)
    initial_state = multi_rnn_cell.zero_state(batch_size, tf.float32)
    # 创建由RNNCell指定的递归神经网络cell。执行完全动态展开inputs
    outputs, states = tf.nn.dynamic_rnn(cell=multi_rnn_cell, inputs=x, dtype=tf.float32, initial_state=initial_state )
    # outputs 的shape为[batch_size, max_time, 28]

    w = tf.Variable(tf.random_normal([28, 10]))
    b = tf.Variable(tf.random_normal([10]))
    output = tf.matmul(outputs[:, -1, :], w) + b
    return output, states


# 定义所需占位符
x = tf.placeholder(tf.float32, [None, 28, 28])
y_true = tf.placeholder(tf.float32, [None, 10])
keepprob = tf.placeholder(tf.float32)
global_step = tf.Variable(0)
# 在训练模型时，随着训练的逐步降低学习率。该函数返回衰减后的学习率。
learning_rate = tf.train.exponential_decay(0.01, global_step, 10, 0.96, staircase=True)

# 训练所需损失函数
y_pred, states = RNN_Model(x, batch_size, keepprob)
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=y_pred, labels=y_true))
opt = tf.train.AdamOptimizer(learning_rate).minimize(loss, global_step=global_step)        # 最小化损失函数
predict = tf.equal(tf.argmax(y_pred, 1), tf.argmax(y_true, 1))        # 预测值
acc = tf.reduce_mean(tf.cast(predict, tf.float32))                # 精度
init = tf.global_variables_initializer()
# 开始训练
with tf.Session() as sess:
    sess.run(init)
    for k in range(epochs):
        for i in range(batch_nums):
            train_x, train_y = mnist.train.next_batch(batch_size)
            sess.run(opt, {x: train_x.reshape((-1, 28, 28)), y_true: train_y, keepprob: 0.8})
            # 评估模型在验证集上的识别率
            if i % 50 == 0:
                val_losses = 0
                accuracy = 0
                val_x, val_y = mnist.validation.next_batch(batch_size)
                for i in range(val_x.shape[0]):
                    val_loss, accy = sess.run([loss, acc], {x: val_x.reshape((-1, 28, 28)), y_true: val_y, keepprob: 1.})
                    val_losses += val_loss
                    accuracy += accy
                print('val_loss is :', val_losses / val_x.shape[0], ', accuracy is :', accuracy / val_x.shape[0])

View Code

 

加载模型

　　深度学习的训练是需要很长时间的，我们不可能每次需要预测都花大量的时间去重新训练，因此我们想出一个方法，保存模型，也就是保存我们训练好的参数． 

import numpy as np
from keras.models import load_model
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets("./mnist/", one_hot=True, reshape=False)  # (?, 28,28,1)
x_test = mnist.test.images            # (10000, 28,28,1)
y_test = mnist.test.labels            # (10000, 10)
print(y_test[1])                    # [0. 0. 1. 0. 0. 0. 0. 0. 0. 0.]

model = load_model('k_CNN.h5')        # 读取模型

# 评估模型
evl = model.evaluate(x=x_test, y=y_test)
evl_name = model.metrics_names
for i in range(len(evl)):
    print(evl_name[i], ':\t', evl[i])
    # loss :     0.19366768299341203
    # acc :     0.9691

test = x_test[1].reshape(1, 28, 28, 1)
y_predict = model.predict(test)        # (1, 10)
print(y_predict)
# [[1.6e-06 6.0e-09 9.9e-01 5.8e-10 4.0e-07 2.5e-08 1.72e-06 1.2e-09 2.1e-07 8.5e-08]]
y_true = 'actual:%d' % (np.argmax(y_test[1]))        # actual:2
pre = 'actual:%d' % (np.argmax(y_predict))            # actual:2

View Code

 

参考文献：

 

MNIST数据集探究

Audior的CSDN博客深度学习项目实战计划——汇总