使用Keras构造简单的CNN网络实例

#生成一个model
model = Sequential()
 
#layer1-conv1
model.add(Convolution2D(16, 3, 3, border_mode='valid',input_shape=data.shape[-3:]))
model.add(Activation('tanh'))#tanh
 
# layer2-conv2
model.add(Convolution2D(32, 3, 3, border_mode='valid'))
model.add(Activation('tanh'))#tanh
 
# layer3-conv3
model.add(Convolution2D(32, 3, 3, border_mode='valid'))
model.add(Activation('tanh'))#tanh
 
# layer4
model.add(Flatten())
model.add(Dense(128, init='normal'))
model.add(Activation('tanh'))#tanh
 
# layer5-fully connect
model.add(Dense(numClass, init='normal')) 
model.add(Activation('softmax'))

# 
sgd = SGD(l2=0.1,lr=0.001, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd,class_mode="categorical")

from keras.preprocessing.image import ImageDataGenerator
from keras.models import Model
from keras.layers import MaxPooling2D,Input,Convolution2D
from keras.layers import Dropout, Flatten, Dense
from keras import backend as K

img_width, img_height = 28, 28 
train_data_dir = 'dataMnist/train' #train data directory
validation_data_dir = 'dataMnist/validation'# validation data directory
nb_train_samples = 60000 
nb_validation_samples = 10000
epochs = 50 
batch_size = 32

if K.image_dim_ordering() == 'th':
 input_shape = (3, img_width, img_height)
else:
 input_shape = (img_width, img_height, 3)

img_input=Input(shape=input_shape)
x=Convolution2D(32, 3, 3, activation='relu', border_mode='same')(img_input)
x=MaxPooling2D((2,2),strides=(2, 2),border_mode='same')(x)

x=Convolution2D(32,3,3,activation='relu',border_mode='same')(x)
x=MaxPooling2D((2,2),strides=(2, 2),border_mode='same')(x)

x=Convolution2D(64,3,3,activation='relu',border_mode='same')(x)
x=MaxPooling2D((2,2),strides=(2, 2),border_mode='same')(x)

x = Flatten(name='flatten')(x)
x = Dense(64, activation='relu')(x)
x= Dropout(0.5)(x)
x = Dense(10,activation='softmax')(x)
model=Model(img_input,x)


model.compile(loss='binary_crossentropy',
    optimizer='rmsprop',
    metrics=['accuracy'])
model.summary()

train_datagen = ImageDataGenerator(
 rescale=1. / 255,
 shear_range=0.2,
 zoom_range=0.2,
 horizontal_flip=True)

# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1. / 255)

train_generator = train_datagen.flow_from_directory(
 train_data_dir,
 target_size=(img_width, img_height),
 batch_size=batch_size,
 class_mode='categorical', #多分类问题设为'categorical'
 classes=['0','1','2','3','4','5','6','7','8','9'] #十种数字图片所在文件夹的名字
 )

validation_generator = test_datagen.flow_from_directory(
 validation_data_dir,
 target_size=(img_width, img_height),
 batch_size=batch_size,
 class_mode='categorical'
 )

model.fit_generator(
  train_generator,
  samples_per_epoch=nb_train_samples,
  nb_epoch=epochs,
  validation_data=validation_generator,
  nb_val_samples=nb_validation_samples
  )

model.save_weights('Mnist123weight.h5')
model.save('Mnist123model.h5')

from keras.models import load_model
from keras.preprocessing.image import img_to_array, load_img
import numpy as np
classes=['0','1','2','3','4','5','6','7','8','9']
model=load_model('Mnist123model.h5')
while True:
 img_addr=input('Please input your image address:')
 if img_addr=="exit":
  break
 else:
  img = load_img(img_addr, False, target_size=(28, 28))
  x = img_to_array(img) / 255.0
  x = np.expand_dims(x, axis=0)
  result = model.predict(x)
  ind=np.argmax(result,1)
  print('this is a ', classes[ind])