15 手写数字识别-小数据集

1.手写数字数据集

• from sklearn.datasets import load_digits
• digits = load_digits()

  from tensorflow.keras.models import Sequential
  from tensorflow.keras.layers import Dense,Dropout,Flatten,Conv2D,MaxPool2D
  import matplotlib.pyplot as plt
  import pandas as pd
  import tensorflow as tf
  from sklearn.metrics import accuracy_score
  digits = load_digits()
  X_data = digits.data.astype(np.float32)
  Y_data = digits.target.astype(np.float32).reshape(-1, 1)

  2.图片数据预处理

  • x：归一化MinMaxScaler()
  • y：独热编码OneHotEncoder()或to_categorical
  • 训练集测试集划分
  • 张量结构

    scaler = MinMaxScaler()
    X_data = scaler.fit_transform(X_data)
    print("MinMaxScaler_trans_X_data：")
    print(X_data)
    Y = OneHotEncoder().fit_transform(Y_data).todense()
    
    print("one-hot_Y：")
    
    print(Y)
    X = X_data.reshape(-1, 8, 8, 1)
    X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.2, random_state=0, stratify=Y)
    
    print('X_train.shape, X_test.shape, y_train.shape, y_test.shape：', X_train.shape, X_test.shape, y_train.shape, y_test.shape)

     

     

     

     

    3.设计卷积神经网络结构

    • 绘制模型结构图，并说明设计依据。　

    模型结构图如下：

        

     设计依据：

    （1）模型是层的堆叠，参考VGGnet模型，一条路走到黑，小卷积核，小池化核。

    （2）模型使用了四层卷积，三个池化层，所以加入Dropout层来防止过拟合。

    model = Sequential()
    ks = (3, 3)  
    input_shape = X_train.shape[1:]
    model.add(Conv2D(filters=16, kernel_size=ks, padding='same', input_shape=input_shape, activation='relu'))
    model.add(MaxPool2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))
    model.add(Conv2D(filters=32, kernel_size=ks, padding='same', activation='relu'))
    model.add(MaxPool2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))
    model.add(Conv2D(filters=64, kernel_size=ks, padding='same', activation='relu'))
    model.add(Conv2D(filters=128, kernel_size=ks, padding='same', activation='relu'))
    model.add(MaxPool2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))
    model.add(Flatten())
    model.add(Dense(128, activation='relu'))
    model.add(Dropout(0.25))
    model.add(Dense(10, activation='softmax'))
    print(model.summary())

    

     

     

  • 

     

     

    4.模型训练

    def show_train_history(train_history, train, validation):
        plt.plot(train_history.history[train])
        plt.plot(train_history.history[validation])
        plt.title('Train History')
        plt.ylabel('train')
        plt.xlabel('epoch')
        plt.legend(['train', 'validation'], loc='upper left')
        plt.show()
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    
    train_history = model.fit(x=X_train, y=y_train, validation_split=0.2, batch_size=300, epochs=10, verbose=2)
    
    show_train_history(train_history, 'accuracy', 'val_accuracy')
    
    show_train_history(train_history, 'loss', 'val_loss')

    

     

     

    5.模型评价

    • model.evaluate()
    • 交叉表与交叉矩阵
    • pandas.crosstab
    • seaborn.heatmap

      score = model.evaluate(X_test, y_test)
      print('score：', score)
      y_pred = model.predict_classes(X_test)
      print('y_pred：', y_pred[:10])
      # 交叉表与交叉矩阵
      y_test1 = np.argmax(y_test, axis=1).reshape(-1)
      y_true = np.array(y_test1)[0]
      pd.crosstab(y_true, y_pred, rownames=['true'], colnames=['predict'])
      # seaborn.heatmap
      y_test1 = y_test1.tolist()[0]
      a = pd.crosstab(np.array(y_test1), y_pred, rownames=['Lables'], colnames=['Predict'])
      df = pd.DataFrame(a)
      sns.heatmap(df, annot=True, cmap="Reds", linewidths=0.2, linecolor='G')
      plt.show()