神经网络入门及改进优化——CNN识别手写数字集（MNIST）（Python 3.8）

文章来自https://zhuanlan.zhihu.com/p/33669143

但是由于该文使用的tensorflow已经keras版本比较老，因此原来的版本在python3.8的情况下已经并不适用。

因此这里发表了适用于 TensorFlow 2.3 及 keras 2.4.3 的最新版本。如果想要深入了解原理的可点击上文链接查看。

1.BaseLine版本代码

import numpy
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
from keras.utils import np_utils
seed = 7
numpy.random.seed(seed)
#加载数据
(X_train, y_train), (X_test, y_test) = mnist.load_data()

num_pixels = X_train.shape[1] * X_train.shape[2]
X_train = X_train.reshape(X_train.shape[0], num_pixels).astype('float32')
X_test = X_test.reshape(X_test.shape[0], num_pixels).astype('float32')

X_train = X_train / 255
X_test = X_test / 255

# 对输出进行one hot编码
y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)
num_classes = y_test.shape[1]

# MLP模型
def baseline_model():
     model = Sequential()
     model.add(Dense(num_pixels, input_dim=num_pixels,  activation='relu'))
     model.add(Dense(num_classes,  activation='softmax'))
     model.summary()
     model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
     return model

# 建立模型
model = baseline_model()

# Fit
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=10, batch_size=200, verbose=2)

#Evaluation
scores = model.evaluate(X_test, y_test, verbose=0)
print("使用MLP并迭代十次的正确率为:" ,(scores[1]*100) , "%")

2.简单的CNN网络代码

import numpy
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
from keras.layers import Flatten
from keras.layers.convolutional import Convolution2D
from keras.layers.convolutional import MaxPooling2D
from keras.utils import np_utils
from keras import backend as K

seed = 7
numpy.random.seed(seed)

 #加载数据
(X_train, y_train), (X_test, y_test) = mnist.load_data()
# reshape to be [samples][channels][width][height]
X_train = X_train.reshape(X_train.shape[0],  28, 28, 1).astype('float32')
X_test = X_test.reshape(X_test.shape[0],  28, 28, 1).astype('float32')

 # normalize inputs from 0-255 to 0-1
X_train = X_train / 255
X_test = X_test / 255
 # one hot encode outputs
y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)
num_classes = y_test.shape[1]

# define a simple CNN model
def baseline_model():
    # create model
    model = Sequential()
    model.add(Convolution2D(32,( 5, 5), padding='valid', input_shape=( 28, 28, 1), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.2))
    model.add(Flatten())
    model.add(Dense(128, activation='relu'))
    model.add(Dense(num_classes, activation='softmax'))
    # Compile model
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    return model

# build the model
model = baseline_model()

# Fit the model
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=10, batch_size=128, verbose=2)

# Final evaluation of the model
scores = model.evaluate(X_test, y_test, verbose=0)
print("使用CNN网络的正确率为:" ,(scores[1]*100) , "%")

3.改进优化的CNN算法

# Larger CNN for the MNIST Dataset
import numpy
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
from keras.layers import Flatten
from keras.layers.convolutional import Convolution2D
from keras.layers.convolutional import MaxPooling2D
from keras.utils import np_utils
from keras.constraints import maxnorm
from keras.optimizers import SGD

# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)
# load data
(X_train, y_train), (X_test, y_test) = mnist.load_data()
# reshape to be [samples][pixels][width][height]
X_train = X_train.reshape(X_train.shape[0], 28, 28, 1).astype('float32')
X_test = X_test.reshape(X_test.shape[0], 28, 28, 1).astype('float32')
# normalize inputs from 0-255 to 0-1
X_train = X_train / 255
X_test = X_test / 255
# one hot encode outputs
y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)
num_classes = y_test.shape[1]
###raw
# define the larger model
def larger_model():
     # create model
     model = Sequential()
     model.add(Convolution2D(30, (5, 5), padding='valid', input_shape=(28, 28, 1), activation='relu'))
     model.add(MaxPooling2D(pool_size=(2, 2)))
     model.add(Dropout(0.4))
     model.add(Convolution2D(15, (3, 3), activation='relu'))
     model.add(MaxPooling2D(pool_size=(2, 2)))
     model.add(Dropout(0.4))
     model.add(Flatten())
     model.add(Dense(128, activation='relu'))
     model.add(Dropout(0.4))
     model.add(Dense(50, activation='relu'))
     model.add(Dropout(0.4))
     model.add(Dense(num_classes, activation='softmax'))
     # Compile model
     model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
     return model

# build the model
model = larger_model()
# Fit the model
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=200, batch_size=200, verbose=2)
# Final evaluation of the model
scores = model.evaluate(X_test, y_test, verbose=0)
print("使用优化后的CNN网络的正确率为:" ,(scores[1]*100) , "%")