15 手写数字识别-小数据集

Posted 2020-12-10 zengyf

作业补交：

https://www.cnblogs.com/zengyf/p/13054699.html

https://www.cnblogs.com/zengyf/p/13054744.html

https://www.cnblogs.com/zengyf/p/13055110.html

https://www.cnblogs.com/zengyf/p/13055257.html

https://www.cnblogs.com/zengyf/p/13055261.html

https://www.cnblogs.com/zengyf/p/13055266.html

https://www.cnblogs.com/zengyf/p/13055551.html

https://www.cnblogs.com/zengyf/p/13055600.html

原因：电脑未带回家。

1.手写数字数据集

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

 

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

 

# 将属性缩放到一个指定的最大和最小值（通常是1-0之间）
scaler = MinMaxScaler()
X_data = scaler.fit_transform(X_data)
print("MinMaxScaler_trans_X_data：")
print(X_data)

Y = OneHotEncoder().fit_transform(Y_data).todense()# 进行one-hot编码
print("one-hot_Y：")
print(Y)
# 转换为图片的格式
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)

　　运行图：

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。
• 

• model = Sequential()
  ks = (3, 3)  # 卷积核的大小
  input_shape = X_train.shape[1:]
  model.add(Conv2D(filters=16, kernel_size=ks, padding=‘same‘, input_shape=input_shape, activation=‘relu‘))# 一层卷积，padding=‘same‘,tensorflow会对输入自动补0
  model.add(MaxPool2D(pool_size=(2, 2)))# 池化层1
  model.add(Dropout(0.25))# 防止过拟合，随机丢掉连接
  model.add(Conv2D(filters=32, kernel_size=ks, padding=‘same‘, activation=‘relu‘))# 二层卷积
  model.add(MaxPool2D(pool_size=(2, 2)))# 池化层2
  model.add(Dropout(0.25))
  model.add(Conv2D(filters=64, kernel_size=ks, padding=‘same‘, activation=‘relu‘))# 三层卷积
  model.add(Conv2D(filters=128, kernel_size=ks, padding=‘same‘, activation=‘relu‘))# 四层卷积
  model.add(MaxPool2D(pool_size=(2, 2)))# 池化层3
  model.add(Dropout(0.25))
  model.add(Flatten())# 平坦层
  model.add(Dense(128, activation=‘relu‘))# 全连接层
  model.add(Dropout(0.25))
  model.add(Dense(10, activation=‘softmax‘))# 激活函数softmax
  model.summary()
  

  运行图：

• 

   

   

   

   

4.模型训练

• model.compile(loss=‘categorical_crossentropy‘, optimizer=‘adam‘, metrics=[‘accuracy‘])
• train_histor：y = model.fit(x=X_train,y=y_train,validation_split=0.2, batch_size=300,epochs=10,verbose=2)

• # 训练
  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)
  score = model.evaluate(X_test,y_test)
  score

运行图：

 

 

5.模型评价

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

• # 模型评价
  score = model.evaluate(X_test, y_test)
  print(‘score：‘, score)
  # 预测值
  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]
  # 交叉表查看预测数据与原数据对比
  pd.crosstab(y_true, y_pred, rownames=[‘true‘], colnames=[‘predict‘])

  # 交叉矩阵
  y_test1 = y_test1.tolist()[0]
  a = pd.crosstab(np.array(y_test1), y_pred)
  df = pd.DataFrame(a)
  sns.heatmap(df, annot=True, cmap="YlGnBu", linewidths=0.2, linecolor=‘G‘)
  plt.show()

  运行图：