keras实战-入门之手写数字识别CNN

手写数字识别

cnn的大致原理可以看我的文章，应该比较直观了，可以看到效果比全连接的好，因为他除了提取了像素信息，还提取了像素之间的空间位置信息。

import numpy as np
from keras.utils import np_utils
from keras.datasets import mnist

np.random.seed(11)

(x_train_image,y_train_label),(x_test_image,y_test_label)=mnist.load_data()

print('train data=',len(x_train_image))
print('test data=',len(x_test_image))

train data= 60000
test data= 10000

print('y_train_label',x_train_image.shape)
print('y_train_label',y_train_label.shape)

y_train_label (60000, 28, 28)
y_train_label (60000,)

print('x_test_image:',x_test_image.shape)
print('y_test_label:',y_test_label.shape)

x_test_image: (10000, 28, 28)
y_test_label: (10000,)

#这里跟DNN不一样，因为图像，有宽 高 通道 
x_train4D=x_train_image.reshape(x_train_image.shape[0],28,28,1).astype('float32')
x_test4D=x_test_image.reshape(x_test_image.shape[0],28,28,1).astype('float32')
print(x_train4D.shape)
print(x_test4D.shape)

(60000, 28, 28, 1)
(10000, 28, 28, 1)

x_train_normalize=x_train4D/255
x_test_normalize=x_test4D/255

y_train_oneHot=np_utils.to_categorical(y_train_label)
y_test_oneHot=np_utils.to_categorical(y_test_label)

from keras import Sequential
from keras.layers import Dense,Dropout,Flatten,Conv2D,MaxPool2D

model=Sequential()

#卷积层 
model.add(Conv2D(filters=16,kernel_size=(5,5),padding='same',input_shape=(28,28,1),activation='relu'))

#池化层
model.add(MaxPool2D(pool_size=(2,2)))

model.add(Conv2D(filters=36,kernel_size=(5,5),padding='same',activation='relu'))

model.add(MaxPool2D(pool_size=(2,2)))

#随机忽略掉部分节点
model.add(Dropout(0.25))

model.add(Flatten())

model.add(Dense(units=128,activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10,activation='softmax'))

print(model.summary())

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_5 (Conv2D)            (None, 28, 28, 16)        416       
_________________________________________________________________
max_pooling2d_6 (MaxPooling2 (None, 14, 14, 16)        0         
_________________________________________________________________
conv2d_6 (Conv2D)            (None, 14, 14, 36)        14436     
_________________________________________________________________
max_pooling2d_7 (MaxPooling2 (None, 7, 7, 36)          0         
_________________________________________________________________
dropout_7 (Dropout)          (None, 7, 7, 36)          0         
_________________________________________________________________
flatten_3 (Flatten)          (None, 1764)              0         
_________________________________________________________________
dense_5 (Dense)              (None, 128)               225920    
_________________________________________________________________
dropout_8 (Dropout)          (None, 128)               0         
_________________________________________________________________
dense_6 (Dense)              (None, 10)                1290      
=================================================================
Total params: 242,062
Trainable params: 242,062
Non-trainable params: 0
_________________________________________________________________
None

model.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])

train_history=model.fit(x_train4D,y_train_oneHot,validation_split=0.2,epochs=10,batch_size=300,verbose=2)

Train on 48000 samples, validate on 12000 samples
Epoch 1/10
 - 3s - loss: 0.0543 - acc: 0.9835 - val_loss: 0.0393 - val_acc: 0.9893
Epoch 2/10
 - 3s - loss: 0.0515 - acc: 0.9842 - val_loss: 0.0413 - val_acc: 0.9888
Epoch 3/10
 - 3s - loss: 0.0450 - acc: 0.9859 - val_loss: 0.0433 - val_acc: 0.9886
Epoch 4/10
 - 3s - loss: 0.0458 - acc: 0.9855 - val_loss: 0.0466 - val_acc: 0.9882
Epoch 5/10
 - 3s - loss: 0.0419 - acc: 0.9869 - val_loss: 0.0453 - val_acc: 0.9882
Epoch 6/10
 - 3s - loss: 0.0430 - acc: 0.9866 - val_loss: 0.0480 - val_acc: 0.9878
Epoch 7/10
 - 3s - loss: 0.0435 - acc: 0.9860 - val_loss: 0.0475 - val_acc: 0.9874
Epoch 8/10
 - 3s - loss: 0.0365 - acc: 0.9875 - val_loss: 0.0480 - val_acc: 0.9888
Epoch 9/10
 - 3s - loss: 0.0387 - acc: 0.9884 - val_loss: 0.0416 - val_acc: 0.9898
Epoch 10/10
 - 3s - loss: 0.0378 - acc: 0.9883 - val_loss: 0.0435 - val_acc: 0.9898

def show_train_history(train_history,train,validation):
    plt.plot(train_history.history[train])
    plt.plot(train_history.history[validation])
    plt.title('Train histiry')
    plt.ylabel(train)
    plt.xlabel('epoch')
    plt.legend(['train,','validation'],loc='upper left')
    plt.show()

import matplotlib.pyplot as plt
show_train_history(train_history,'acc','val_acc')

show_train_history(train_history,'loss','val_loss')

scores=model.evaluate(x_test4D,y_test_oneHot)
print('accuracy=',scores[1])

10000/10000 [==============================] - 1s 103us/step
accuracy= 0.9906

prediction=model.predict_classes(x_test4D)

prediction

array([7, 2, 1, ..., 4, 5, 6], dtype=int64)

def plot_images_labels_prediction(images,labels,prediction,idx,num=10):
    flig=plt.figure(figsize=(12,14))
    if num>25:
        num=25
    for i in range(0,num):
        ax=plt.subplot(5,5,1+i)
        ax.imshow(images[idx],cmap='binary')
        title='labels='+str(labels[idx])
        if len(prediction)>0:
            title+=',predict='+str(prediction[idx])
        ax.set_title(title,fontsize=10)
        ax.set_xticks([])
        ax.set_yticks([])
        idx+=1
    plt.show()
plot_images_labels_prediction(x_test_image,y_test_label,prediction,idx=0)

#混淆矩阵
import pandas as pd
pd.crosstab(y_test_label,prediction,rownames=['label'],colnames=['predict'])

predict	0	1	2	3	4	5	6	7	8	9
label
0	973	1	0	0	1	0	3	1	1	0
1	0	1134	1	0	0	0	0	0	0	0
2	3	1	1022	0	1	0	0	4	1	0
3	0	0	0	1000	0	3	0	2	3	2
4	0	0	0	0	978	0	1	0	0	3
5	1	0	1	2	0	883	3	0	1	1
6	4	1	0	0	1	2	948	0	2	0
7	0	2	6	2	2	0	0	1010	1	5
8	2	0	0	1	1	1	0	3	963	3
9	1	4	1	0	4	1	1	1	1	995

df=pd.DataFrame({'label':y_test_label,'predict':prediction})

print(df[(df.label==1) & (df.predict==2)])

      label  predict
3073      1        2

plot_images_labels_prediction(x_test_image,y_test_label,prediction,idx=3073,num=1)

好了，今天就到这里了，希望对学习理解有帮助，大神看见勿喷，仅为自己的学习理解，能力有限，请多包涵，侵删。