DBN（深度信念网络）

DBN运用CD算法逐层进行训练，得到每一层的参数Wi和ci用于初始化DBN，之后再用监督学习算法对参数进行微调。本例中采用softmax分类器(下一篇随笔中)作为监督学习算法。

RBM与上一篇随笔中一致，通过多层RBM将softmax parameter从 (10L, 784L)降低到(10L, 50L)。单独用softmax分类器也可以得到相近（或者略好）的正确率，所需的时间略长一点。

 from rbm2 import RBM
 from softmax import SoftMax
 import os
 import numpy as np
 import cPickle
 
 class DBN:
     def __init__(self,nlayers,ntype,vlen,hlen):
         self.rbm_layers = []
         self.nlayers = nlayers
         self.ntype = ntype
         self.vlen=vlen
         self.hlen=hlen
 
     def calcRBMForward(self,x):
         for rbm in self.rbm_layers:
             x = rbm.forward(x.T)
         return x
 
     def load_param(self,dbnpath,softmaxpath):
         weights = cPickle.load(open(dbnpath,'rb'))
         self.nlayers = len(weights)
         for i in range(self.nlayers):
             weight = weights[i]
             v,h= np.shape(weight)
             rbm = RBM(v,h)
             rbm.w = weight
             self.rbm_layers.append(rbm)
             print "RBM layer%d shape:%s" %(i,str(rbm.w.shape))
         self.softmax = SoftMax()
         self.softmax.load_theta(softmaxpath)
         print "softmax parameter: "+str(self.softmax.theta.shape)
 
     def pretrainRBM(self,trainset):
         weights = []
         for i in range(self.nlayers):
             rbm = RBM(self.vlen,self.hlen)
             if i == 0:
                 traindata = trainset
             else:
                 traindata = np.array(outdata.T)
             rbm.rbmBB(traindata)
             outdata = np.mat(rbm.forward(traindata))
             self.rbm_layers.append(rbm)
             weights.append(rbm.w)
             self.vlen = self.hlen
             self.hlen = self.hlen/2
         f= open("data/dbn.pkl",'wb')
         cPickle.dump(weights,f)
         f.close()
 
     def fineTune(self,trainset,labelset):
         rbm_output = self.calcRBMForward(trainset)
         MAXT,step,landa = 100,1,0.01
         self.softmax = SoftMax(MAXT,step,landa)
         self.softmax.process_train(rbm_output,labelset,self.ntype)
 
     def predict(self,x):
         rbm_output = self.calcRBMForward(x)
         return self.softmax.predict(rbm_output)
 
     def validate(self,testset,labelset):
         testnum = len(testset)
         correctnum = 0
         for i in range(testnum):
             x = testset[i]
             testtype = self.predict(x)
             orgtype = labelset[i]
             if testtype == orgtype:
                 correctnum += 1
         rate = float(correctnum)/testnum
         print "correctnum = %d, sumnum = %d" %(correctnum,testnum)
         print "Accuracy:%.2f" %(rate)
         return rate
 
 dbn = DBN(3,10,784,200)
 f = open('mnist.pkl', 'rb')
 training_data, validation_data, test_data = cPickle.load(f)
 training_inputs = [np.reshape(x, 784) for x in training_data[0]]
 data = np.array(training_inputs[:5000]).T
 training_inputs = [np.reshape(x, 784) for x in validation_data[0]]
 vdata = np.array(training_inputs[:5000])
 if not os.path.exists('data/softmax.pkl'):  # Run twice
     dbn.pretrainRBM(data)
     dbn.fineTune(data.T,training_data[1][:5000])
 else:
     dbn.load_param("data/dbn.pkl","data/softmax.pkl")
     dbn.validate(vdata,validation_data[1][:5000])
 
 #RBM layer0 shape:(784L, 200L)
 #RBM layer1 shape:(200L, 100L)
 #RBM layer2 shape:(100L, 50L)
 #softmax parameter: (10L, 50L)
 #correctnum = 4357, sumnum = 5000
 #Accuracy:0.87