用keras 和 tensorflow 构建手写字识别神经网路

#导入数据
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
from keras.datasets import mnist

(train_images, train_labels), (test_images, test_labels) = mnist.load_data()
print(train_images.shape)
print(train_images.dtype)
print(train_labels.shape)

print(test_images.shape)
print(test_labels.shape)

#图像转换
train_images = train_images.reshape((60000, 28*28))
train_images = train_images.astype('float32')/255

test_images = test_images.reshape((10000, 28*28))
test_images = test_images.astype('float32')/ 255

#构建网络
from keras import models
from keras import layers

network = models.Sequential()
network.add(layers.Dense(512, activation = 'relu', input_shape = (28*28, )))
network.add(layers.Dense(10, activation = 'softmax'))

network.compile(optimizer = 'rmsprop', loss = 'categorical_crossentropy', metrics = ['accuracy'])

#准备标签
from keras.utils import to_categorical

train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)

#模型拟合
network.fit(train_images, train_labels, epochs=5, batch_size = 128)

#测试模型
test_loss, test_acc = network.evaluate(test_images, test_labels)
print('test_acc:', test_acc)

 

换一种写法（来自Bilibili李宏毅 机器学习课程）

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.layers import Conv2D, MaxPooling2D, Flatten
from keras.optimizers import SGD, Adam
from keras.utils import np_utils
from keras.datasets import mnist

def load_data():
    (x_train, y_train), (x_test, y_test) = mnist.load_data()
    number = 10000
    x_train = x_train[0:number]
    y_train = y_train[0:number]
    x_train = x_train.reshape(number, 28*28)
    x_test = x_test.reshape(x_test.shape[0], 28*28)
    x_train = x_train.astype('float32')
    x_test = x_test.astype('float32')
    #convert class vectors to binart vlass matrics
    y_train = np_utils.to_categorical(y_train, 10)
    y_test = np_utils.to_categorical(y_test, 10)
    x_train = x_train
    x_test = x_test
    #x_test = np.random.normal(x_test)
    x_train = x_train /255
    x_test = x_test / 255
    return (x_train, y_train), (x_test, y_test)

(x_train, y_train), (x_test, y_test) = load_data()
    
x_train.shape #(10000, 784)
y_train.shape #(10000, 10)
x_test.shape #(10000, 784)
y_test.shape #(10000, 10)

model = Sequential()
model.add(Dense(input_dim = 28*28, units = 800, activation = 'relu'))
#model.add(Dropout(0.7))
model.add(Dense(units=700, activation = 'relu'))
#model.add(Dropout(0.7))
model.add(Dense(units=700, activation = 'relu'))
#model.add(Dropout(0.7))
model.add(Dense(units=10, activation = 'softmax'))

model.compile(loss = 'categorical_crossentropy', optimizer = "adam", metrics = ['accuracy'])
model.fit(x_train, y_train, batch_size = 100, epochs = 20)

result = model.evaluate(x_test, y_test)
print("Test Acc:", result[1])