35 model.add(Convolution2D(32, 5, 5, border_mode='valid', input_shape=(1, 28, 28), activation='relu')) 36 model.add(MaxPooling2D(pool_size=(2, 2))) 37 model.add(Dropout(0.2)) 38 model.add(Flatten())
39 model.add(Dense(128, activation='relu'))
40 model.add(Dense(num_classes, activation='softmax')) 41 # Compile model
42 model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) 43 return model 44
45 # build the model 46 model = baseline_model() 47
48 # Fit the model
49 model.fit(X_train, y_train, validation_data=(X_test, y_test), nb_epoch=10, batch_size=128, verbose=2) 50
51 # Final evaluation of the model
52 scores = model.evaluate(X_test, y_test, verbose=0) 53 print(\复制代码 结果： 复制代码
1 ____________________________________________________________________________________________________ 2 Layer (type) Output Shape Param # Connected to
3 ==================================================================================================== 4 convolution2d_1 (Convolution2D) (None, 32, 24, 24) 832 convolution2d_input_1[0][0]
5 ____________________________________________________________________________________________________ 6 maxpooling2d_1 (MaxPooling2D) (None, 32, 12, 12) 0 convolution2d_1[0][0]
7 ____________________________________________________________________________________________________ 8 dropout_1 (Dropout) (None, 32, 12, 12) 0 maxpooling2d_1[0][0]
9 ____________________________________________________________________________________________________ 10 flatten_1 (Flatten) (None, 4608) 0 dropout_1[0][0]
11 ____________________________________________________________________________________________________ 12 dense_1 (Dense) (None, 128) 589952 flatten_1[0][0]
13 ____________________________________________________________________________________________________ 14 dense_2 (Dense) (None, 10) 1290 dense_1[0][0]
15 ==================================================================================================== 16 Total params: 592074
17 ____________________________________________________________________________________________________ 18 Train on 60000 samples, validate on 10000 samples 19 Epoch 1/10
20 32s - loss: 0.2412 - acc: 0.9318 - val_loss: 0.0754 - val_acc: 0.9766 21 Epoch 2/10
22 32s - loss: 0.0726 - acc: 0.9781 - val_loss: 0.0534 - val_acc: 0.9829
23 Epoch 3/10
24 32s - loss: 0.0497 - acc: 0.9852 - val_loss: 0.0391 - val_acc: 0.9858 25 Epoch 4/10
26 32s - loss: 0.0413 - acc: 0.9870 - val_loss: 0.0432 - val_acc: 0.9854 27 Epoch 5/10
28 34s - loss: 0.0323 - acc: 0.9897 - val_loss: 0.0375 - val_acc: 0.9869 29 Epoch 6/10
30 36s - loss: 0.0281 - acc: 0.9909 - val_loss: 0.0424 - val_acc: 0.9864 31 Epoch 7/10
32 36s - loss: 0.0223 - acc: 0.9930 - val_loss: 0.0328 - val_acc: 0.9893 33 Epoch 8/10
34 36s - loss: 0.0198 - acc: 0.9939 - val_loss: 0.0381 - val_acc: 0.9880 35 Epoch 9/10
36 36s - loss: 0.0156 - acc: 0.9954 - val_loss: 0.0347 - val_acc: 0.9884 37 Epoch 10/10
38 36s - loss: 0.0141 - acc: 0.9955 - val_loss: 0.0318 - val_acc: 0.9893 39 CNN Error: 1.07% 复制代码
迭代的结果中，loss和acc为训练集的结果，val_loss和val_acc为验证机的结果。从结果上来看，效果不错，比100次迭代的MLP（1.46%）提升了0.39%，CNN的误差率为1.07%。这里的CNN的网络结构还是比较简单的，如果把CNN的结果再加几层，边复杂一代，结果是否还能提升？
3.Larger CNN
这一次我加了几层卷积层，代码： 复制代码 1 # Larger CNN 2 import numpy
3 from keras.datasets import mnist 4 from keras.models import Sequential 5 from keras.layers import Dense 6 from keras.layers import Dropout 7 from keras.layers import Flatten
8 from keras.layers.convolutional import Convolution2D 9 from keras.layers.convolutional import MaxPooling2D 10 from keras.utils import np_utils 11 12 seed = 7
13 numpy.random.seed(seed) 14 # load data
15 (X_train, y_train), (X_test, y_test) = mnist.load_data() 16 # reshape to be [samples][pixels][width][height]
17 X_train = X_train.reshape(X_train.shape[0], 1, 28, 28).astype('float32')
18 X_test = X_test.reshape(X_test.shape[0], 1, 28, 28).astype('float32') 19 # normalize inputs from 0-255 to 0-1 20 X_train = X_train / 255 21 X_test = X_test / 255 22 # one hot encode outputs
23 y_train = np_utils.to_categorical(y_train) 24 y_test = np_utils.to_categorical(y_test) 25 num_classes = y_test.shape[1] 26 # define the larger model 27 def larger_model(): 28 # create model 29 model = Sequential()
30 model.add(Convolution2D(30, 5, 5, border_mode='valid', input_shape=(1, 28, 28), activation='relu')) 31 model.add(MaxPooling2D(pool_size=(2, 2))) 32 model.add(Convolution2D(15, 3, 3, activation='relu')) 33 model.add(MaxPooling2D(pool_size=(2, 2))) 34 model.www.baiyuewang.netadd(Dropout(0.2)) 35 model.add(Flatten())
36 model.add(Dense(128, activation='relu')) 37 model.add(Dense(50, activation='relu'))
38 model.add(Dense(num_classes, activation='softmax')) 39 # Compile model 40 model.summary()
41 model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) 42 return model 43 # build the model 44 model = larger_model() 45 # Fit the model
46 model.fit(X_train, y_train, validation_data=(X_test, y_test), nb_epoch=69, batch_size=200, verbose=2) 47 # Final evaluation of the model
48 scores = model.evaluate(X_test, y_test, verbose=0) 49 print(\复制代码
结果： 复制代码
___________________________________________________________________________________________________ Layer (type) Output Shape Param # Connected to
==================================================================================================== convolution2d_1 (Convolution2D) (None, 30, 24, 24) 780 convolution2d_input_1[0][0]
____________________________________________________________________________________________________ maxpooling2d_1 (MaxPooling2D) (None, 30, 12, 12) 0 convolution2d_1[0][0]
____________________________________________________________________________________________________
convolution2d_2 (Convolution2D) (None, 15, 10, 10) 4065 maxpooling2d_1[0][0]
____________________________________________________________________________________________________ maxpooling2d_2 (MaxPooling2D) (None, 15, 5, 5) 0 convolution2d_2[0][0]
____________________________________________________________________________________________________ dropout_1 (Dropout) (None, 15, 5, 5) 0 maxpooling2d_2[0][0]
____________________________________________________________________________________________________ flatten_1 (Flatten) (None, 375) 0 dropout_1[0][0]
____________________________________________________________________________________________________ dense_1 (Dense) (None, 128) 48128 flatten_1[0][0]
____________________________________________________________________________________________________ dense_2 (Dense) (None, 50) 6450 dense_1[0][0]
____________________________________________________________________________________________________ dense_3 (Dense) (None, 10) 510 dense_2[0][0]
==================================================================================================== Total params: 59933
____________________________________________________________________________________________________ Train on 60000 samples, validate on 10000 samples Epoch 1/10
34s - loss: 0.3789 - acc: 0.8796 - val_loss: 0.0811 - val_acc: 0.9742 Epoch 2/10
34s - loss: 0.0929 - acc: 0.9710 - val_loss: 0.0462 - val_acc: 0.9854 Epoch 3/10
35s - loss: 0.0684 - acc: 0.9786 - val_loss: 0.0376 - val_acc: 0.9869 Epoch 4/10
35s - loss: 0.0546 - acc: 0.9826 - val_loss: 0.0332 - val_acc: 0.9890 Epoch 5/10
35s - loss: 0.0467 - acc: 0.9856 - val_loss: 0.0289 - val_acc: 0.9897 Epoch 6/10
35s - loss: 0.0402 - acc: 0.9873 - val_loss: 0.0291 - val_acc: 0.9902 Epoch 7/10
34s - loss: 0.0369 - acc: 0.9880 - val_loss: 0.0233 - val_acc: 0.9924 Epoch 8/10
36s - loss: 0.0336 - acc: 0.9894 - val_loss: 0.0258 - val_acc: 0.9913 Epoch 9/10
39s - loss: 0.0317 - acc: 0.9899 - val_loss: 0.0219 - val_acc: 0.9926 Epoch 10/10
40s - loss: 0.0268 - acc: 0.9916 - val_loss: 0.0220 - val_acc: 0.9919 Large CNN Error: 0.81% 复制代码
效果不错，现在的准确率是99.19%
4.最终版本