用keras 和 tensorflow 构建手写字识别神经网路-优快云博客

本文介绍了使用Keras深度学习库进行MNIST手写数字识别的两种方法。首先，通过构建一个简单的全连接神经网络，实现了对MNIST数据集的训练和测试，达到较高的识别准确率。其次，展示了另一种网络结构的实现方式，包括多层全连接层和Dropout层，进一步提高了模型的泛化能力。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

#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])