【python keras实战】利用VGG卷积神经网络进行手写字体识别

# encoding: utf-8
import sys
reload(sys)
sys.setdefaultencoding('utf-8')

import numpy as np
from keras.datasets import mnist
import gc

from keras.models import Sequential, Model
from keras.layers import Input, Dense, Dropout, Flatten
from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.applications.vgg16 import VGG16
from keras.optimizers import SGD


import cv2
import h5py as h5py 
import numpy as np


##由于输入层需要10个节点，所以最好把目标数字0-9做成one Hot编码的形式。
def tran_y(y): 
    y_ohe = np.zeros(10) 
    y_ohe[y] = 1 
    return y_ohe


# 如果硬件配置较高，比如主机具备32GB以上内存，GPU具备8GB以上显存，可以适当增大这个值。VGG要求至少48像素
ishape=48
(X_train, y_train), (X_test, y_test) = mnist.load_data()
X_train = [cv2.cvtColor(cv2.resize(i, (ishape, ishape)), cv2.COLOR_GRAY2BGR) for i in X_train] 
X_train = np.concatenate([arr[np.newaxis] for arr in X_train]).astype('float32') 
X_train /= 255.0

X_test = [cv2.cvtColor(cv2.resize(i, (ishape, ishape)), cv2.COLOR_GRAY2BGR) for i in X_test] 
X_test = np.concatenate([arr[np.newaxis] for arr in X_test]).astype('float32')
X_test /= 255.0

y_train_ohe = np.array([tran_y(y_train[i]) for i in range(len(y_train))]) 
y_test_ohe = np.array([tran_y(y_test[i]) for i in range(len(y_test))])
y_train_ohe = y_train_ohe.astype('float32')
y_test_ohe = y_test_ohe.astype('float32')


print X_train.shape

# VGG16 全参重训迁移学习

# 很多时候需要多次回收垃圾才能彻底收回内存。如果不行，重新启动单独执行下面的模型
for i in range(10):
    gc.collect()



ishape=224
model_vgg = VGG16(include_top = False, weights = 'imagenet', input_shape = (ishape, ishape, 3)) 

for layer in model_vgg.layers:
        layer.trainable = False
model = Flatten()(model_vgg.output) 
model = Dense(4096, activation='relu', name='fc1')(model)
model = Dense(4096, activation='relu', name='fc2')(model)
model = Dropout(0.5)(model)
model = Dense(10, activation = 'softmax', name='prediction')(model) 
model_vgg_mnist_pretrain = Model(model_vgg.input, model, name = 'vgg16_pretrain')
print model_vgg_mnist_pretrain.summary()


##我们只需要训练25万个参数，比之前整数少了60倍。
sgd = SGD(lr = 0.05, decay = 1e-5) 
model_vgg_mnist_pretrain.compile(loss = 'categorical_crossentropy', optimizer = sgd, metrics = ['accuracy'])

model_vgg_mnist_pretrain.fit(X_train, y_train_ohe, validation_data = (X_test, y_test_ohe), epochs = 10, batch_size = 64)


#######在测试集上评价模型精确度
scores=model_vgg_mnist_pretrain.evaluate(X_test,y_test_ohe,verbose=0)

#####打印精确度
print scores


time2 = time.time()
print u'ok,结束!'
print u'总共耗时：' + str(time2 - time1) + 's'