keras深度学习框架通过卷积神经网络cnn实现手写数字识别

一时失言乱红尘 2024-03-24 22:45 73阅读 0赞

昨天通过[keras构建简单神经网络实现手写数字识别][keras]，结果在最后进行我们自己的手写数字识别的时候，准确率堪忧，只有60%。今天通过卷积神经网络来实现手写数字识别。

构建卷积神经网络和简单神经网络思路类似，只不过这里加入了卷积、池化等概念，网络结构复杂了一些，但是整体的思路没有变化，加载数据集，数据集修改，搭建网络模型，编译模型，训练模型，保存模型，利用模型预测。

这里还是给出两个例子，一个是构建网络，最后保存训练好的网络模型，一个是通过加载保存的网络模型预测我们自己的手写数字图片。

import keras
    import numpy as np
    import tensorflow as tf
    from keras.models import Sequential
    from keras.layers import Dense, Activation, Dropout, Conv2D, Flatten, MaxPool2D
    from tensorflow.keras import datasets, utils
    # 数据处理
    (x_train, y_train), (x_test, y_test) = datasets.mnist.load_data()
    x_train = x_train.reshape(x_train.shape[0], x_train.shape[1], x_train.shape[1], 1)
    x_train = x_train.astype('float32') / 255
    x_test = x_test.reshape(x_test.shape[0], x_test.shape[1], x_test.shape[1], 1)
    x_test = x_test.astype('float32') / 255
    y_train = utils.to_categorical(y_train, num_classes=10)
    y_test = utils.to_categorical(y_test, num_classes=10)
    # 构建模型
    model = Sequential()
    model.add(Conv2D(filters=16, kernel_size=(3, 3), padding='same', activation="relu", input_shape=(28, 28, 1)))
    model.add(MaxPool2D(pool_size=(2, 2)))
    model.add(Conv2D(filters=36, kernel_size=(3, 3), padding='same', activation="relu"))
    model.add(MaxPool2D(pool_size=(2, 2)))
    model.add(Dropout(0.2))
    model.add(Flatten())
    model.add(Dense(128, activation="relu"))
    model.add(Dropout(0.25))
    model.add(Dense(10, activation="softmax"))
    # 编译
    model.compile(loss="categorical_crossentropy", optimizer="adam", metrics=["accuracy"])
    model.summary()
    # 训练
    model.fit(x_train, y_train, epochs=5, batch_size=128, validation_data=(x_test, y_test))
    # 保存模型
    model.save("mnist.h5")

训练模型，打印信息如下：

Model: "sequential"
    _________________________________________________________________
     Layer (type)                Output Shape              Param #   
    =================================================================
     conv2d (Conv2D)             (None, 28, 28, 16)        160       
                                                                     
     max_pooling2d (MaxPooling2D  (None, 14, 14, 16)       0         
     )                                                               
                                                                     
     conv2d_1 (Conv2D)           (None, 14, 14, 36)        5220      
                                                                     
     max_pooling2d_1 (MaxPooling  (None, 7, 7, 36)         0         
     2D)                                                             
                                                                     
     dropout (Dropout)           (None, 7, 7, 36)          0         
                                                                     
     flatten (Flatten)           (None, 1764)              0         
                                                                     
     dense (Dense)               (None, 128)               225920    
                                                                     
     dropout_1 (Dropout)         (None, 128)               0         
                                                                     
     dense_1 (Dense)             (None, 10)                1290      
                                                                     
    =================================================================
    Total params: 232,590
    Trainable params: 232,590
    Non-trainable params: 0
    _________________________________________________________________
    Epoch 1/5
    2023-08-28 16:03:54.677314: I tensorflow/stream_executor/cuda/cuda_dnn.cc:368] Loaded cuDNN version 8800
    469/469 [==============================] - 10s 17ms/step - loss: 0.2842 - accuracy: 0.9123 - val_loss: 0.0628 - val_accuracy: 0.9798
    Epoch 2/5
    469/469 [==============================] - 7s 16ms/step - loss: 0.0836 - accuracy: 0.9743 - val_loss: 0.0473 - val_accuracy: 0.9841
    Epoch 3/5
    469/469 [==============================] - 7s 16ms/step - loss: 0.0627 - accuracy: 0.9801 - val_loss: 0.0325 - val_accuracy: 0.9886
    Epoch 4/5
    469/469 [==============================] - 7s 15ms/step - loss: 0.0497 - accuracy: 0.9844 - val_loss: 0.0346 - val_accuracy: 0.9882
    Epoch 5/5
    469/469 [==============================] - 7s 15ms/step - loss: 0.0422 - accuracy: 0.9867 - val_loss: 0.0298 - val_accuracy: 0.9898

准确率最后，到达了98.5%以上。

用模型预测

import keras
    import numpy as np
    import cv2
    from keras.models import load_model
    
    model = load_model("mnist.h5")
    
    
    def predict(img_path):
        img = cv2.imread(img_path, 0)
        img = img.reshape(28, 28).astype("float32") / 255  # 0 1
        img = img.reshape(1, 28, 28, 1)  # 28 * 28 -> (1,28,28,1)
        label = model.predict(img)
        label = np.argmax(label, axis=1)
        print('{} -> {}'.format(img_path, label[0]))
    
    
    if __name__ == '__main__':
        for _ in range(10):
            predict("number_images/b_{}.png".format(_))

数字图片如下：

![7d02df88dd4b4726a4b28b310713df18.png][]![712ef02a74c5406099a7a236e8ab486d.png][]![f73a873e44784bf49796e63e6796eb8b.png][]![f3705a063d3a48d79805bcbde6f72881.png][]![8b499a6116c945d3abbe0f031eaea34f.png][]![40b0a5b3769543418c49ac2905af860d.png][]![e4a62174b71942b7af6055bccc48d8c6.png][]![a56de75a9cee47958078f6ae581f9b02.png][]![050a899f42de4b7facf71ab535c90bfb.png][]![6d58d2d4a218469a85bf030b976a6730.png][]

图片放在项目目录number\_images中。

预测结果打印：

![42d5fabcbf034af69f7d2acaaf892a50.png][]

感觉就是不一样，准确率从60%提升到了90%。虽然没有达到100%，但是已经很好了。

对比之前的代码，改动很小，主要是网络输入的时候，数据形状发生了改变，简单神经网络需要的是（784，\*）结构，卷积神经网络需要的是（1，28，28，1）的结构， 在数据处理上做了调整，另一个不一样的地方就是网络模型在添加的时候，之前就是简单的两层网络，卷积神经网络复杂了很多。

[keras]: https://blog.csdn.net/feinifi/article/details/132523461?spm=1001.2014.3001.5501
[7d02df88dd4b4726a4b28b310713df18.png]: https://img-blog.csdnimg.cn/7d02df88dd4b4726a4b28b310713df18.png
[712ef02a74c5406099a7a236e8ab486d.png]: https://img-blog.csdnimg.cn/712ef02a74c5406099a7a236e8ab486d.png
[f73a873e44784bf49796e63e6796eb8b.png]: https://img-blog.csdnimg.cn/f73a873e44784bf49796e63e6796eb8b.png
[f3705a063d3a48d79805bcbde6f72881.png]: https://img-blog.csdnimg.cn/f3705a063d3a48d79805bcbde6f72881.png
[8b499a6116c945d3abbe0f031eaea34f.png]: https://img-blog.csdnimg.cn/8b499a6116c945d3abbe0f031eaea34f.png
[40b0a5b3769543418c49ac2905af860d.png]: https://img-blog.csdnimg.cn/40b0a5b3769543418c49ac2905af860d.png
[e4a62174b71942b7af6055bccc48d8c6.png]: https://img-blog.csdnimg.cn/e4a62174b71942b7af6055bccc48d8c6.png
[a56de75a9cee47958078f6ae581f9b02.png]: https://img-blog.csdnimg.cn/a56de75a9cee47958078f6ae581f9b02.png
[050a899f42de4b7facf71ab535c90bfb.png]: https://img-blog.csdnimg.cn/050a899f42de4b7facf71ab535c90bfb.png
[6d58d2d4a218469a85bf030b976a6730.png]: https://image.dandelioncloud.cn/pgy_files/images/2024/03/13/7e27218609944c938880f92ad9a23e1b.png
[42d5fabcbf034af69f7d2acaaf892a50.png]: https://image.dandelioncloud.cn/pgy_files/images/2024/03/13/5abfe446eead4fabba138f42fc7062c5.png