（三） Keras Mnist分类程序以及改用交叉熵对比
视频学习来源
https://www.bilibili.com/video/av40787141?from=search&seid=17003307842787199553
笔记
Mnist分类程序
import numpy as np from keras.datasets import mnist #将会从网络下载mnist数据集 from keras.utils import np_utils from keras.models import Sequential #序列模型 from keras.layers import Dense from keras.optimizers import SGD
C:\Program Files (x86)\Microsoft Visual Studio\Shared\Anaconda3_64\lib\site-packages\h5py\__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
Using TensorFlow backend.
第一次运行时，建议先下载数据集
1 打开cmd 输入python 回车
2 将上面的代码输入，导入相关文件包库
3 输入
(x_train,y_train),(x_test,y_test)=mnist.load_data()
回车
启动下载。加载完成便可在jupyter notebook中运行
#载入数据 (x_train,y_train),(x_test,y_test)=mnist.load_data() #查看格式 #（60000,28,28） print('x_shape:',x_train.shape) #（60000） print('y_shape:',y_train.shape) #（60000,28,28）->(60000,784) #行数60000，列-1表示自动设置 #除以255是做数据归一化处理 x_train=x_train.reshape(x_train.shape[0],-1)/255.0 #转换数据格式 x_test=x_test.reshape(x_test.shape[0],-1)/255.0 #转换数据格式 #label标签转换成 one hot 形式 y_train=np_utils.to_categorical(y_train,num_classes=10) #分成10类 y_test=np_utils.to_categorical(y_test,num_classes=10) #分成10类 #创建模型，输入754个神经元，输出10个神经元 #偏执值初始值设为1（默认为0） model=Sequential([ Dense(units=10,input_dim=784,bias_initializer='one',activation='softmax') ]) #定义优化器 #学习速率为0.2 sgd=SGD(lr=0.2) #定义优化器，损失函数，训练效果中计算准确率 model.compile( optimizer=sgd, #sgd优化器 loss='mse', #损失用均方差 metrics=['accuracy'], #计算准确率 ) #训练（不同于之前，这是新的训练方式） #六万张，每次训练32张，训练10个周期（六万张全部训练完算一个周期） model.fit(x_train,y_train,batch_size=32,epochs=10) #评估模型 loss,accuracy=model.evaluate(x_test,y_test) print('\ntest loss',loss) print('accuracy',accuracy)
x_shape: (60000, 28, 28)
y_shape: (60000,)
Epoch 1/10
60000/60000 [==============================] - 4s 65us/step - loss: 0.0384 - acc: 0.7673
Epoch 2/10
60000/60000 [==============================] - 5s 88us/step - loss: 0.0204 - acc: 0.8808
Epoch 3/10
60000/60000 [==============================] - 3s 57us/step - loss: 0.0178 - acc: 0.8934
Epoch 4/10
60000/60000 [==============================] - 3s 48us/step - loss: 0.0165 - acc: 0.8995
Epoch 5/10
60000/60000 [==============================] - 3s 45us/step - loss: 0.0157 - acc: 0.9038
Epoch 6/10
60000/60000 [==============================] - 3s 46us/step - loss: 0.0151 - acc: 0.9064
Epoch 7/10
60000/60000 [==============================] - 3s 48us/step - loss: 0.0146 - acc: 0.9093
Epoch 8/10
60000/60000 [==============================] - 3s 49us/step - loss: 0.0143 - acc: 0.9110
Epoch 9/10
60000/60000 [==============================] - 3s 46us/step - loss: 0.0140 - acc: 0.9126
Epoch 10/10
60000/60000 [==============================] - 3s 52us/step - loss: 0.0138 - acc: 0.9137
10000/10000 [==============================] - 0s 28us/step
test loss 0.01308599321632646
accuracy 0.9169
改用交叉熵
#定义优化器，损失函数，训练效果中计算准确率
model.compile(
optimizer=sgd, #sgd优化器
loss='categorical_crossentropy', #损失用交叉熵，速度会更快
metrics=['accuracy'], #计算准确率
)
完整代码
import numpy as np from keras.datasets import mnist #将会从网络下载mnist数据集 from keras.utils import np_utils from keras.models import Sequential #序列模型 from keras.layers import Dense from keras.optimizers import SGD
C:\Program Files (x86)\Microsoft Visual Studio\Shared\Anaconda3_64\lib\site-packages\h5py\__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
Using TensorFlow backend.
#载入数据 (x_train,y_train),(x_test,y_test)=mnist.load_data() #查看格式 #（60000,28,28） print('x_shape:',x_train.shape) #（60000） print('y_shape:',y_train.shape) #（60000,28,28）->(60000,784) #行数60000，列-1表示自动设置 #除以255是做数据归一化处理 x_train=x_train.reshape(x_train.shape[0],-1)/255.0 #转换数据格式 x_test=x_test.reshape(x_test.shape[0],-1)/255.0 #转换数据格式 #label标签转换成 one hot 形式 y_train=np_utils.to_categorical(y_train,num_classes=10) #分成10类 y_test=np_utils.to_categorical(y_test,num_classes=10) #分成10类 #创建模型，输入754个神经元，输出10个神经元 #偏执值初始值设为1（默认为0） model=Sequential([ Dense(units=10,input_dim=784,bias_initializer='one',activation='softmax') ]) #定义优化器 #学习速率为0.2 sgd=SGD(lr=0.2) #定义优化器，损失函数，训练效果中计算准确率 model.compile( optimizer=sgd, #sgd优化器 loss='categorical_crossentropy', #损失用交叉熵，速度会更快 metrics=['accuracy'], #计算准确率 ) #训练（不同于之前，这是新的训练方式） #六万张，每次训练32张，训练10个周期（六万张全部训练完算一个周期） model.fit(x_train,y_train,batch_size=32,epochs=10) #评估模型 loss,accuracy=model.evaluate(x_test,y_test) print('\ntest loss',loss) print('accuracy',accuracy)
x_shape: (60000, 28, 28)
y_shape: (60000,)
Epoch 1/10
60000/60000 [==============================] - 5s 82us/step - loss: 0.3782 - acc: 0.8926
Epoch 2/10
60000/60000 [==============================] - 4s 60us/step - loss: 0.3031 - acc: 0.9145
Epoch 3/10
60000/60000 [==============================] - 3s 54us/step - loss: 0.2894 - acc: 0.9186
Epoch 4/10
60000/60000 [==============================] - 3s 55us/step - loss: 0.2826 - acc: 0.9204
Epoch 5/10
60000/60000 [==============================] - 3s 54us/step - loss: 0.2773 - acc: 0.9227
Epoch 6/10
60000/60000 [==============================] - 3s 57us/step - loss: 0.2748 - acc: 0.9226
Epoch 7/10
60000/60000 [==============================] - 4s 59us/step - loss: 0.2715 - acc: 0.9239
Epoch 8/10
60000/60000 [==============================] - 4s 61us/step - loss: 0.2694 - acc: 0.9252
Epoch 9/10
60000/60000 [==============================] - 3s 55us/step - loss: 0.2664 - acc: 0.9254
Epoch 10/10
60000/60000 [==============================] - 4s 67us/step - loss: 0.2654 - acc: 0.9267
10000/10000 [==============================] - 0s 29us/step
test loss 0.28354966330975295
accuracy 0.9229
改用后精度在提高，速度也在变快
