利用卷积神经网络识别手写数字

冷不防 2022-04-15 06:39 289阅读 0赞

#### 1.测试数据准备 ####

1.我们使用的测试数据，可以直接从keras.datasets.mnist导入

import numpy as np
    import seaborn as sns
    import matplotlib.pyplot as plt
    plt.rcParams['figure.figsize']=(7,7)
    
    from keras.datasets import mnist
    from keras.models import Sequential
    from keras.utils import np_utils
    import keras
    from keras.preprocessing.image import ImageDataGenerator
    from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D
    from keras.layers.normalization import BatchNormalization
    
    epochs = 20
    input_shape = (28, 28, 1)
    nb_classes = 10
    
    (X_train, y_train), (X_test, y_test) = mnist.load_data()
    print('X_train shape:', X_train.shape)
    print('X_test shape:', X_test.shape)

能看到一共有6W条训练数据和1W条测试数据  
![在这里插入图片描述][20181122170139340.png]  
由于被墙的原因，mnist可能无法下载，可以换成本地数据导入的方式。下载数据请点击[这里][Link 1]，数据导入方式换成

path='./mnist.npz'
    f = np.load(path)
    X_train, y_train = f['x_train'], f['y_train']
    X_test, y_test = f['x_test'], f['y_test']
    f.close()

2.查看数据

for i in range(9):
        plt.subplot(3, 3, i+1)
        plt.imshow(X_train[i], cmap='gray', interpolation='none')
        plt.title("Class {}".format(y_train[i]))

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x0MzI2MDMwNDM0_size_16_color_FFFFFF_t_70]  
3.将数据格式转换为keras接受的数据结构

X_train = X_train.reshape(X_train.shape[0], 28, 28, 1)
    X_test = X_test.reshape(X_test.shape[0], 28, 28, 1)
    print('X_train shape:', X_train.shape)
    print('X_test shape:', X_test.shape)

![在这里插入图片描述][20181122172807335.png]  
使用seaborn观察训练数据集的y值分布

sns.countplot(y_train)

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x0MzI2MDMwNDM0_size_16_color_FFFFFF_t_70 1]

Y_train = np_utils.to_categorical(y_train, nb_classes)
    Y_test = np_utils.to_categorical(y_test, nb_classes)
    print("Y_train:", Y_train.shape)

![在这里插入图片描述][20181122173232532.png]

#### 2.定义深度神经网络结构 ####

model = Sequential()
    model.add(Conv2D(32, kernel_size=(3,3), activation='relu', kernel_initializer='he_normal', input_shape=input_shape))
    model.add(Conv2D(32, kernel_size=(3,3), activation='relu', kernel_initializer='he_normal'))
    model.add(MaxPool2D(2,2))
    model.add(Dropout(0.2))
    model.add(Conv2D(64, kernel_size=(3,3), activation='relu', kernel_initializer='he_normal', padding='same'))
    model.add(Conv2D(64, kernel_size=(3,3), activation='relu', kernel_initializer='he_normal', padding='same'))
    model.add(MaxPool2D(2,2))
    model.add(Dropout(0.25))
    model.add(Conv2D(128, kernel_size=(3,3), activation='relu', kernel_initializer='he_normal', padding='same'))
    model.add(Dropout(0.25))
    model.add(Flatten())
    model.add(Dense(128, activation='relu'))
    model.add(BatchNormalization())
    model.add(Dropout(0.25))
    model.add(Dense(nb_classes, activation='softmax'))
    
    model.compile(loss=keras.losses.categorical_crossentropy,
                 optimizer=keras.optimizers.Adam(),
                 metrics=['accuracy'])
    model.summary()

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x0MzI2MDMwNDM0_size_16_color_FFFFFF_t_70 2]

#### 3.训练模型 ####

完成数据训练并保存训练好的模型

datagen = ImageDataGenerator(featurewise_center=True, featurewise_std_normalization=True)
    
    datagen.fit(X_train)
    
    filepath = 'model.hdf5'
    from keras.callbacks import ModelCheckpoint
    
    # monitor计算每一个模型validation_data的准确率
    # save_best_only 只保存最好的一个模型
    checkpointer = ModelCheckpoint(filepath, monitor='val_acc', save_best_only=True, mode='max')
    
    # steps_per_epoch指定循环次数
    h = model.fit_generator(datagen.flow(X_train, Y_train, batch_size=500),
                           steps_per_epoch=len(X_train)/1000, epochs=epochs,
                           validation_data=datagen.flow(X_test, Y_test, batch_size=len(X_test)),
                           validation_steps=1, callbacks=[checkpointer])

训练完成后可以看到模型在测试数据上的准确率已经达到了99.39%  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x0MzI2MDMwNDM0_size_16_color_FFFFFF_t_70 3]  
我们可以用pyplot打印一下，随着epochs的执行，模型在训练数据和测试数据集的准确率的表现情况

history = h.history
    accuracy = history['acc']
    val_accuracy = history['val_acc']
    loss = history['loss']
    val_loss = history['val_loss']
    epochs = range(len(accuracy))
    plt.plot(epochs, accuracy, 'bo', label='Training Accuracy')
    plt.plot(epochs, val_accuracy, 'b', label='Validation Accuracy')
    plt.title('Training and validation accuracy')
    plt.legend()
    plt.show()

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x0MzI2MDMwNDM0_size_16_color_FFFFFF_t_70 4]

#### 4.模型评估 ####

from keras.models import load_model
    model = load_model('model.hdf5')
    score = model.evaluate(X_test, Y_test)
    print('Test score:', score[0])
    print('Test accuracy:', score[1])

可以看到一共有1W组数据，损失函数约为0.24，准确率达到了0.984，已经比较高了。  
![在这里插入图片描述][20181123170758664.png]

我们可以抽取一些预测数据，与真实值进行对比

predicted_classes = model.predict_classes(X_test)
    correct_indices = np.nonzero(predicted_classes == y_test)[0]
    incorrect_indices = np.nonzero(predicted_classes != y_test)[0]

选取9个预测正确的进行打印

plt.figure()
    for i, correct in enumerate(correct_indices[:9]):
        plt.subplot(3,3,i+1)
        plt.imshow(X_test[correct].reshape(28, 28), cmap='gray', interpolation='none')
        plt.title("Predicted {}, Class {}".format(predicted_classes[correct], y_test[correct]))

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x0MzI2MDMwNDM0_size_16_color_FFFFFF_t_70 5]  
当然我们也可以选择9个错误的进行打印

plt.figure()
    for i, incorrect in enumerate(incorrect_indices[:9]):
        plt.subplot(3,3,i+1)
        plt.imshow(X_test[incorrect].reshape(28, 28), cmap='gray', interpolation='none')
        plt.title("Predicted {}, Class {}".format(predicted_classes[incorrect], y_test[incorrect]))

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x0MzI2MDMwNDM0_size_16_color_FFFFFF_t_70 6]  
可以看到，有一些真实值为1的图片，被识别错误了，说明模型还有一些改进的空间。

所有源码、测试数据以及训练好的模型已上传至git，[点击这里][Link 2]可直接查看，有疑问的同学请在博客下方留言或提Issuees，谢谢！

[20181122170139340.png]: /images/20220415/5dd3e9a91c944c85a3a1f41e262e4bf6.png
[Link 1]: https://s3.amazonaws.com/img-datasets/mnist.npz
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x0MzI2MDMwNDM0_size_16_color_FFFFFF_t_70]: /images/20220415/35f24ffd162441e8ba30257a90ae22a8.png
[20181122172807335.png]: /images/20220415/481c70d0cdae43a4b5904a4f28fbd974.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x0MzI2MDMwNDM0_size_16_color_FFFFFF_t_70 1]: /images/20220415/e9981b1c245d4f0890f50b2435023417.png
[20181122173232532.png]: /images/20220415/50db162f1cd7427cac977b626248f9f6.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x0MzI2MDMwNDM0_size_16_color_FFFFFF_t_70 2]: /images/20220415/950a7cea00a54560940eb7a0c6b33b4d.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x0MzI2MDMwNDM0_size_16_color_FFFFFF_t_70 3]: /images/20220415/dbdf61c8b93a4501a8cd21faa182d7c7.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x0MzI2MDMwNDM0_size_16_color_FFFFFF_t_70 4]: /images/20220415/a3f944e0789b431aa23cb6d3668c00dd.png
[20181123170758664.png]: /images/20220415/dccaf8b28a4e4c24ab2e26714521cda4.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x0MzI2MDMwNDM0_size_16_color_FFFFFF_t_70 5]: /images/20220415/f4cdd98f4ee04f3bb9970c1b790cabb8.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2x0MzI2MDMwNDM0_size_16_color_FFFFFF_t_70 6]: /images/20220415/5acbfe20e9f448639774bfee70f6d687.png
[Link 2]: https://github.com/Maginaaa/mnist_recognition