【Python】keras神经网络识别mnist

谁践踏了优雅 2021-12-16 10:11 367阅读 0赞

上次用Matlab写过一个识别Mnist的神经网络，地址在：[https://www.cnblogs.com/tiandsp/p/9042908.html][https_www.cnblogs.com_tiandsp_p_9042908.html]

这次又用Keras做了一个差不多的，毕竟，现在最流行的项目都是Python做的，我也跟一下潮流：)

数据是从本地解析好的图像和标签载入的。

神经网络有两个隐含层，都有512个节点。

import numpy as np
    from keras.preprocessing import image
    from keras.models import Sequential
    from keras.layers.core import Dense, Dropout, Activation
    
    
    # 从文件夹图像与标签文件载入数据
    def create_x(filenum, file_dir):
        train_x = []
        for i in range(filenum):
            img = image.load_img(file_dir + str(i) + ".bmp", target_size=(28, 28))
            img = img.convert('L')
            x = image.img_to_array(img)
            train_x.append(x)
        train_x = np.array(train_x)
        train_x = train_x.astype('float32')
        train_x /= 255
        return train_x
    
    
    def create_y(classes, filename):
        train_y = []
        file = open(filename, "r")
        for line in file.readlines():
            tmp = []
            for j in range(classes):
                if j == int(line):
                    tmp.append(1)
                else:
                    tmp.append(0)
            train_y.append(tmp)
        file.close()
        train_y = np.array(train_y).astype('float32')
        return train_y
    
    
    classes = 10
    X_train = create_x(55000, './train/')
    X_test = create_x(10000, './test/')
    
    X_train = X_train.reshape(X_train.shape[0], 784)
    X_test = X_test.reshape(X_test.shape[0], 784)
    
    Y_train = create_y(classes, 'train.txt')
    Y_test = create_y(classes, 'test.txt')
    
    # 从网络下载的数据集直接解析数据
    '''
    from tensorflow.examples.tutorials.mnist import input_data
    mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
    X_train, Y_train = mnist.train.images, mnist.train.labels
    X_test, Y_test = mnist.test.images, mnist.test.labels
    X_train = X_train.astype('float32')
    X_test = X_test.astype('float32')
    X_train = X_train.reshape(55000, 784)
    X_test = X_test.reshape(10000, 784)
    '''
    model = Sequential()
    
    model.add(Dense(512, input_shape=(784,)))
    model.add(Activation('relu'))
    model.add(Dropout(0.4))
    
    model.add(Dense(512))
    model.add(Activation('relu'))
    model.add(Dropout(0.4))
    
    model.add(Dense(10))
    model.add(Activation('softmax'))
    model.summary()
    
    model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
    history = model.fit(X_train, Y_train, batch_size=500, epochs=20, verbose=1, validation_data=(X_test, Y_test))
    score = model.evaluate(X_test, Y_test, verbose=0)
    
    test_result = model.predict(X_test)
    result = np.argmax(test_result, axis = 1)
    
    print(result)
    print('Test score:', score[0])
    print('Test accuracy:', score[1])

最终在测试集上识别率在98%左右。

![340413-20180912161730171-1618572923.png][]

相关测试数据可以在这里[下载][Link 1]到。

转载于:https://www.cnblogs.com/tiandsp/p/9635155.html

[https_www.cnblogs.com_tiandsp_p_9042908.html]: https://www.cnblogs.com/tiandsp/p/9042908.html
[340413-20180912161730171-1618572923.png]: /images/20211214/ee7d8244617b4cfe801f2ff16fcc8abe.png
[Link 1]: https://pan.baidu.com/s/1lrOfLyYbz94C9IoFv0hmGQ