from __future__ import print_function
import numpy as np
np.random.seed(1337) # for reproducibility
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.utils import np_utils
from keras import backend as K
Using TensorFlow backend.
from keras.utils.visualize_util import plot
batch_size = 128
nb_classes = 10
nb_epoch = 12
# 输入数据的维度
img_rows, img_cols = 28, 28
# 使用的卷积滤波器的数量
nb_filters = 32
# 用于 max pooling 的池化面积
pool_size = (2, 2)
# 卷积核的尺寸
kernel_size = (3, 3)
需要将数据还原成28*28大小的数组
注意:Theano和TensorFlow的维度表示含义是不一样的。
'th'模式,也即Theano模式会把100张RGB三通道的16×32(高为16宽为32)彩色图表示为下面这种形式(100,3,16,32),Caffe采取的也是这种方式。第0个维度是样本维,代表样本的数目,第1个维度是通道维,代表颜色通道数。后面两个就是高和宽了。而TensorFlow,即'tf'模式的表达形式是(100,16,32,3),即把通道维放在了最后。这两个表达方法本质上没有什么区别。
# the data, shuffled and split between train and test sets
(X_train, y_train), (X_test, y_test) = mnist.load_data()
if K.image_dim_ordering() == 'th':
X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)
X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 1)
X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255
print('X_train shape:', X_train.shape)
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')
X_train shape: (60000, 28, 28, 1) 60000 train samples 10000 test samples
# convert class vectors to binary class matrices
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)
model = Sequential()
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],
border_mode='valid',
input_shape=input_shape))
model.add(Activation('relu'))
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
model.summary()
____________________________________________________________________________________________________ Layer (type) Output Shape Param # Connected to ==================================================================================================== convolution2d_1 (Convolution2D) (None, 26, 26, 32) 320 convolution2d_input_1[0][0] ____________________________________________________________________________________________________ activation_1 (Activation) (None, 26, 26, 32) 0 convolution2d_1[0][0] ____________________________________________________________________________________________________ convolution2d_2 (Convolution2D) (None, 24, 24, 32) 9248 activation_1[0][0] ____________________________________________________________________________________________________ activation_2 (Activation) (None, 24, 24, 32) 0 convolution2d_2[0][0] ____________________________________________________________________________________________________ maxpooling2d_1 (MaxPooling2D) (None, 12, 12, 32) 0 activation_2[0][0] ____________________________________________________________________________________________________ dropout_1 (Dropout) (None, 12, 12, 32) 0 maxpooling2d_1[0][0] ____________________________________________________________________________________________________ flatten_1 (Flatten) (None, 4608) 0 dropout_1[0][0] ____________________________________________________________________________________________________ dense_1 (Dense) (None, 128) 589952 flatten_1[0][0] ____________________________________________________________________________________________________ activation_3 (Activation) (None, 128) 0 dense_1[0][0] ____________________________________________________________________________________________________ dropout_2 (Dropout) (None, 128) 0 activation_3[0][0] ____________________________________________________________________________________________________ dense_2 (Dense) (None, 10) 1290 dropout_2[0][0] ____________________________________________________________________________________________________ activation_4 (Activation) (None, 10) 0 dense_2[0][0] ==================================================================================================== Total params: 600810 ____________________________________________________________________________________________________
plot(model, to_file='model-cnn.png')
model.compile(loss='categorical_crossentropy',
optimizer='adadelta',
metrics=['accuracy'])
model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch,
verbose=1, validation_data=(X_test, Y_test))
Train on 60000 samples, validate on 10000 samples Epoch 1/12 60000/60000 [==============================] - 13s - loss: 0.3825 - acc: 0.8821 - val_loss: 0.0861 - val_acc: 0.9734 Epoch 2/12 60000/60000 [==============================] - 12s - loss: 0.1333 - acc: 0.9609 - val_loss: 0.0611 - val_acc: 0.9801 Epoch 3/12 60000/60000 [==============================] - 12s - loss: 0.1041 - acc: 0.9694 - val_loss: 0.0545 - val_acc: 0.9824 Epoch 4/12 60000/60000 [==============================] - 12s - loss: 0.0861 - acc: 0.9736 - val_loss: 0.0441 - val_acc: 0.9852 Epoch 5/12 60000/60000 [==============================] - 12s - loss: 0.0780 - acc: 0.9767 - val_loss: 0.0410 - val_acc: 0.9862 Epoch 6/12 60000/60000 [==============================] - 12s - loss: 0.0701 - acc: 0.9795 - val_loss: 0.0384 - val_acc: 0.9869 Epoch 7/12 60000/60000 [==============================] - 12s - loss: 0.0624 - acc: 0.9815 - val_loss: 0.0378 - val_acc: 0.9873 Epoch 8/12 60000/60000 [==============================] - 10s - loss: 0.0608 - acc: 0.9821 - val_loss: 0.0348 - val_acc: 0.9893 Epoch 9/12 60000/60000 [==============================] - 11s - loss: 0.0556 - acc: 0.9838 - val_loss: 0.0337 - val_acc: 0.9885 Epoch 10/12 60000/60000 [==============================] - 12s - loss: 0.0535 - acc: 0.9841 - val_loss: 0.0316 - val_acc: 0.9899 Epoch 11/12 60000/60000 [==============================] - 12s - loss: 0.0512 - acc: 0.9849 - val_loss: 0.0306 - val_acc: 0.9896 Epoch 12/12 60000/60000 [==============================] - 12s - loss: 0.0458 - acc: 0.9867 - val_loss: 0.0321 - val_acc: 0.9896
<keras.callbacks.History at 0x7f261c07e8d0>
score = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])
Test score: 0.0321088282784 Test accuracy: 0.9896