用keras框架较为方便
创新互联长期为超过千家客户提供的网站建设服务,团队从业经验10年,关注不同地域、不同群体,并针对不同对象提供差异化的产品和服务;打造开放共赢平台,与合作伙伴共同营造健康的互联网生态环境。为民勤企业提供专业的网站设计制作、网站设计,民勤网站改版等技术服务。拥有十年丰富建站经验和众多成功案例,为您定制开发。
首先安装anaconda,然后通过pip安装keras
以下转自wphh的博客。
#coding:utf-8
'''
GPU run command:
THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python cnn.py
CPU run command:
python cnn.py
2016.06.06更新:
这份代码是keras开发初期写的,当时keras还没有现在这么流行,文档也还没那么丰富,所以我当时写了一些简单的教程。
现在keras的API也发生了一些的变化,建议及推荐直接上keras.io看更加详细的教程。
'''
#导入各种用到的模块组件
from __future__ import absolute_import
from __future__ import print_function
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.advanced_activations import PReLU
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.optimizers import SGD, Adadelta, Adagrad
from keras.utils import np_utils, generic_utils
from six.moves import range
from data import load_data
import random
import numpy as np
np.random.seed(1024) # for reproducibility
#加载数据
data, label = load_data()
#打乱数据
index = [i for i in range(len(data))]
random.shuffle(index)
data = data[index]
label = label[index]
print(data.shape[0], ' samples')
#label为0~9共10个类别,keras要求格式为binary class matrices,转化一下,直接调用keras提供的这个函数
label = np_utils.to_categorical(label, 10)
###############
#开始建立CNN模型
###############
#生成一个model
model = Sequential()
#第一个卷积层,4个卷积核,每个卷积核大小5*5。1表示输入的图片的通道,灰度图为1通道。
#border_mode可以是valid或者full,具体看这里说明:
#激活函数用tanh
#你还可以在model.add(Activation('tanh'))后加上dropout的技巧: model.add(Dropout(0.5))
model.add(Convolution2D(4, 5, 5, border_mode='valid',input_shape=(1,28,28)))
model.add(Activation('tanh'))
#第二个卷积层,8个卷积核,每个卷积核大小3*3。4表示输入的特征图个数,等于上一层的卷积核个数
#激活函数用tanh
#采用maxpooling,poolsize为(2,2)
model.add(Convolution2D(8, 3, 3, border_mode='valid'))
model.add(Activation('tanh'))
model.add(MaxPooling2D(pool_size=(2, 2)))
#第三个卷积层,16个卷积核,每个卷积核大小3*3
#激活函数用tanh
#采用maxpooling,poolsize为(2,2)
model.add(Convolution2D(16, 3, 3, border_mode='valid'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
#全连接层,先将前一层输出的二维特征图flatten为一维的。
#Dense就是隐藏层。16就是上一层输出的特征图个数。4是根据每个卷积层计算出来的:(28-5+1)得到24,(24-3+1)/2得到11,(11-3+1)/2得到4
#全连接有128个神经元节点,初始化方式为normal
model.add(Flatten())
model.add(Dense(128, init='normal'))
model.add(Activation('tanh'))
#Softmax分类,输出是10类别
model.add(Dense(10, init='normal'))
model.add(Activation('softmax'))
#############
#开始训练模型
##############
#使用SGD + momentum
#model.compile里的参数loss就是损失函数(目标函数)
sgd = SGD(lr=0.05, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd,metrics=["accuracy"])
#调用fit方法,就是一个训练过程. 训练的epoch数设为10,batch_size为100.
#数据经过随机打乱shuffle=True。verbose=1,训练过程中输出的信息,0、1、2三种方式都可以,无关紧要。show_accuracy=True,训练时每一个epoch都输出accuracy。
#validation_split=0.2,将20%的数据作为验证集。
model.fit(data, label, batch_size=100, nb_epoch=10,shuffle=True,verbose=1,validation_split=0.2)
"""
#使用data augmentation的方法
#一些参数和调用的方法,请看文档
datagen = ImageDataGenerator(
featurewise_center=True, # set input mean to 0 over the dataset
samplewise_center=False, # set each sample mean to 0
featurewise_std_normalization=True, # divide inputs by std of the dataset
samplewise_std_normalization=False, # divide each input by its std
zca_whitening=False, # apply ZCA whitening
rotation_range=20, # randomly rotate images in the range (degrees, 0 to 180)
width_shift_range=0.2, # randomly shift images horizontally (fraction of total width)
height_shift_range=0.2, # randomly shift images vertically (fraction of total height)
horizontal_flip=True, # randomly flip images
vertical_flip=False) # randomly flip images
# compute quantities required for featurewise normalization
# (std, mean, and principal components if ZCA whitening is applied)
datagen.fit(data)
for e in range(nb_epoch):
print('-'*40)
print('Epoch', e)
print('-'*40)
print("Training...")
# batch train with realtime data augmentation
progbar = generic_utils.Progbar(data.shape[0])
for X_batch, Y_batch in datagen.flow(data, label):
loss,accuracy = model.train(X_batch, Y_batch,accuracy=True)
progbar.add(X_batch.shape[0], values=[("train loss", loss),("accuracy:", accuracy)] )
"""
如何用python实现图像的一维高斯滤波器
现在把卷积模板中的值换一下,不是全1了,换成一组符合高斯分布的数值放在模板里面,比如这时中间的数值最大,往两边走越来越小,构造一个小的高斯包。实现的函数为cv2.GaussianBlur()。对于高斯模板,我们需要制定的是高斯核的高和宽(奇数),沿x与y方向的标准差(如果只给x,y=x,如果都给0,那么函数会自己计算)。高斯核可以有效的出去图像的高斯噪声。当然也可以自己构造高斯核,相关函数:cv2.GaussianKernel().
import cv2
import numpy as np
import matplotlib.pyplot as plt
img = cv2.imread(‘flower.jpg‘,0) #直接读为灰度图像
for i in range(2000): #添加点噪声
temp_x = np.random.randint(0,img.shape[0])
temp_y = np.random.randint(0,img.shape[1])
img[temp_x][temp_y] = 255
blur = cv2.GaussianBlur(img,(5,5),0)
plt.subplot(1,2,1),plt.imshow(img,‘gray‘)#默认彩色,另一种彩色bgr
plt.subplot(1,2,2),plt.imshow(blur,‘gray‘)
上周末利用python简单实现了一个卷积神经网络,只包含一个卷积层和一个maxpooling层,pooling层后面的多层神经网络采用了softmax形式的输出。实验输入仍然采用MNIST图像使用10个feature map时,卷积和pooling的结果分别如下所示。
部分源码如下:
[python] view plain copy
#coding=utf-8
'''''
Created on 2014年11月30日
@author: Wangliaofan
'''
import numpy
import struct
import matplotlib.pyplot as plt
import math
import random
import copy
#test
from BasicMultilayerNeuralNetwork import BMNN2
def sigmoid(inX):
if 1.0+numpy.exp(-inX)== 0.0:
return 999999999.999999999
return 1.0/(1.0+numpy.exp(-inX))
def difsigmoid(inX):
return sigmoid(inX)*(1.0-sigmoid(inX))
def tangenth(inX):
return (1.0*math.exp(inX)-1.0*math.exp(-inX))/(1.0*math.exp(inX)+1.0*math.exp(-inX))
def cnn_conv(in_image, filter_map,B,type_func='sigmoid'):
#in_image[num,feature map,row,col]=in_image[Irow,Icol]
#features map[k filter,row,col]
#type_func['sigmoid','tangenth']
#out_feature[k filter,Irow-row+1,Icol-col+1]
shape_image=numpy.shape(in_image)#[row,col]
#print "shape_image",shape_image
shape_filter=numpy.shape(filter_map)#[k filter,row,col]
if shape_filter[1]shape_image[0] or shape_filter[2]shape_image[1]:
raise Exception
shape_out=(shape_filter[0],shape_image[0]-shape_filter[1]+1,shape_image[1]-shape_filter[2]+1)
out_feature=numpy.zeros(shape_out)
k,m,n=numpy.shape(out_feature)
for k_idx in range(0,k):
#rotate 180 to calculate conv
c_filter=numpy.rot90(filter_map[k_idx,:,:], 2)
for r_idx in range(0,m):
for c_idx in range(0,n):
#conv_temp=numpy.zeros((shape_filter[1],shape_filter[2]))
conv_temp=numpy.dot(in_image[r_idx:r_idx+shape_filter[1],c_idx:c_idx+shape_filter[2]],c_filter)
sum_temp=numpy.sum(conv_temp)
if type_func=='sigmoid':
out_feature[k_idx,r_idx,c_idx]=sigmoid(sum_temp+B[k_idx])
elif type_func=='tangenth':
out_feature[k_idx,r_idx,c_idx]=tangenth(sum_temp+B[k_idx])
else:
raise Exception
return out_feature
def cnn_maxpooling(out_feature,pooling_size=2,type_pooling="max"):
k,row,col=numpy.shape(out_feature)
max_index_Matirx=numpy.zeros((k,row,col))
out_row=int(numpy.floor(row/pooling_size))
out_col=int(numpy.floor(col/pooling_size))
out_pooling=numpy.zeros((k,out_row,out_col))
for k_idx in range(0,k):
for r_idx in range(0,out_row):
for c_idx in range(0,out_col):
temp_matrix=out_feature[k_idx,pooling_size*r_idx:pooling_size*r_idx+pooling_size,pooling_size*c_idx:pooling_size*c_idx+pooling_size]
out_pooling[k_idx,r_idx,c_idx]=numpy.amax(temp_matrix)
max_index=numpy.argmax(temp_matrix)
#print max_index
#print max_index/pooling_size,max_index%pooling_size
max_index_Matirx[k_idx,pooling_size*r_idx+max_index/pooling_size,pooling_size*c_idx+max_index%pooling_size]=1
return out_pooling,max_index_Matirx
def poolwithfunc(in_pooling,W,B,type_func='sigmoid'):
k,row,col=numpy.shape(in_pooling)
out_pooling=numpy.zeros((k,row,col))
for k_idx in range(0,k):
for r_idx in range(0,row):
for c_idx in range(0,col):
out_pooling[k_idx,r_idx,c_idx]=sigmoid(W[k_idx]*in_pooling[k_idx,r_idx,c_idx]+B[k_idx])
return out_pooling
#out_feature is the out put of conv
def backErrorfromPoolToConv(theta,max_index_Matirx,out_feature,pooling_size=2):
k1,row,col=numpy.shape(out_feature)
error_conv=numpy.zeros((k1,row,col))
k2,theta_row,theta_col=numpy.shape(theta)
if k1!=k2:
raise Exception
for idx_k in range(0,k1):
for idx_row in range( 0, row):
for idx_col in range( 0, col):
error_conv[idx_k,idx_row,idx_col]=\
max_index_Matirx[idx_k,idx_row,idx_col]*\
float(theta[idx_k,idx_row/pooling_size,idx_col/pooling_size])*\
difsigmoid(out_feature[idx_k,idx_row,idx_col])
return error_conv
def backErrorfromConvToInput(theta,inputImage):
k1,row,col=numpy.shape(theta)
#print "theta",k1,row,col
i_row,i_col=numpy.shape(inputImage)
if rowi_row or col i_col:
raise Exception
filter_row=i_row-row+1
filter_col=i_col-col+1
detaW=numpy.zeros((k1,filter_row,filter_col))
#the same with conv valid in matlab
for k_idx in range(0,k1):
for idx_row in range(0,filter_row):
for idx_col in range(0,filter_col):
subInputMatrix=inputImage[idx_row:idx_row+row,idx_col:idx_col+col]
#print "subInputMatrix",numpy.shape(subInputMatrix)
#rotate theta 180
#print numpy.shape(theta)
theta_rotate=numpy.rot90(theta[k_idx,:,:], 2)
#print "theta_rotate",theta_rotate
dotMatrix=numpy.dot(subInputMatrix,theta_rotate)
detaW[k_idx,idx_row,idx_col]=numpy.sum(dotMatrix)
detaB=numpy.zeros((k1,1))
for k_idx in range(0,k1):
detaB[k_idx]=numpy.sum(theta[k_idx,:,:])
return detaW,detaB
def loadMNISTimage(absFilePathandName,datanum=60000):
images=open(absFilePathandName,'rb')
buf=images.read()
index=0
magic, numImages , numRows , numColumns = struct.unpack_from('IIII' , buf , index)
print magic, numImages , numRows , numColumns
index += struct.calcsize('IIII')
if magic != 2051:
raise Exception
datasize=int(784*datanum)
datablock=""+str(datasize)+"B"
#nextmatrix=struct.unpack_from('47040000B' ,buf, index)
nextmatrix=struct.unpack_from(datablock ,buf, index)
nextmatrix=numpy.array(nextmatrix)/255.0
#nextmatrix=nextmatrix.reshape(numImages,numRows,numColumns)
#nextmatrix=nextmatrix.reshape(datanum,1,numRows*numColumns)
nextmatrix=nextmatrix.reshape(datanum,1,numRows,numColumns)
return nextmatrix, numImages
def loadMNISTlabels(absFilePathandName,datanum=60000):
labels=open(absFilePathandName,'rb')
buf=labels.read()
index=0
magic, numLabels = struct.unpack_from('II' , buf , index)
print magic, numLabels
index += struct.calcsize('II')
if magic != 2049:
raise Exception
datablock=""+str(datanum)+"B"
#nextmatrix=struct.unpack_from('60000B' ,buf, index)
nextmatrix=struct.unpack_from(datablock ,buf, index)
nextmatrix=numpy.array(nextmatrix)
return nextmatrix, numLabels
def simpleCNN(numofFilter,filter_size,pooling_size=2,maxIter=1000,imageNum=500):
decayRate=0.01
MNISTimage,num1=loadMNISTimage("F:\Machine Learning\UFLDL\data\common\\train-images-idx3-ubyte",imageNum)
print num1
row,col=numpy.shape(MNISTimage[0,0,:,:])
out_Di=numofFilter*((row-filter_size+1)/pooling_size)*((col-filter_size+1)/pooling_size)
MLP=BMNN2.MuiltilayerANN(1,[128],out_Di,10,maxIter)
MLP.setTrainDataNum(imageNum)
MLP.loadtrainlabel("F:\Machine Learning\UFLDL\data\common\\train-labels-idx1-ubyte")
MLP.initialweights()
#MLP.printWeightMatrix()
rng = numpy.random.RandomState(23455)
W_shp = (numofFilter, filter_size, filter_size)
W_bound = numpy.sqrt(numofFilter * filter_size * filter_size)
W_k=rng.uniform(low=-1.0 / W_bound,high=1.0 / W_bound,size=W_shp)
B_shp = (numofFilter,)
B= numpy.asarray(rng.uniform(low=-.5, high=.5, size=B_shp))
cIter=0
while cItermaxIter:
cIter += 1
ImageNum=random.randint(0,imageNum-1)
conv_out_map=cnn_conv(MNISTimage[ImageNum,0,:,:], W_k, B,"sigmoid")
out_pooling,max_index_Matrix=cnn_maxpooling(conv_out_map,2,"max")
pool_shape = numpy.shape(out_pooling)
MLP_input=out_pooling.reshape(1,1,out_Di)
#print numpy.shape(MLP_input)
DetaW,DetaB,temperror=MLP.backwardPropogation(MLP_input,ImageNum)
if cIter%50 ==0 :
print cIter,"Temp error: ",temperror
#print numpy.shape(MLP.Theta[MLP.Nl-2])
#print numpy.shape(MLP.Ztemp[0])
#print numpy.shape(MLP.weightMatrix[0])
theta_pool=MLP.Theta[MLP.Nl-2]*MLP.weightMatrix[0].transpose()
#print numpy.shape(theta_pool)
#print "theta_pool",theta_pool
temp=numpy.zeros((1,1,out_Di))
temp[0,:,:]=theta_pool
back_theta_pool=temp.reshape(pool_shape)
#print "back_theta_pool",numpy.shape(back_theta_pool)
#print "back_theta_pool",back_theta_pool
error_conv=backErrorfromPoolToConv(back_theta_pool,max_index_Matrix,conv_out_map,2)
#print "error_conv",numpy.shape(error_conv)
#print error_conv
conv_DetaW,conv_DetaB=backErrorfromConvToInput(error_conv,MNISTimage[ImageNum,0,:,:])
#print "W_k",W_k
#print "conv_DetaW",conv_DetaW