ProductQuant.py 文件源码

def PQTrain(data, lenSubVec,numSubCenter):
    (dataSize, dataDim)=data.shape
    if 0!=dataDim%lenSubVec:
        print "Cannot partition the feature space with the given segment number"
        return
    numSubVec=dataDim/lenSubVec
    centers=npy.zeros((numSubVec*numSubCenter,lenSubVec),dtype=npy.float32)
    distOfCenters=npy.zeros((numSubCenter,numSubCenter,numSubVec),dtype=npy.float32)
    objKmeans=KMeans(numSubCenter,'k-means++',3,100,0.001)
    for ii in range(numSubVec):
        print("PQ training. Processing "+str(ii)+"-th sub-vector")
        objKmeans.fit(data[:,ii*lenSubVec:(ii+1)*lenSubVec]) 
        centers[ii*numSubCenter:(ii+1)*numSubCenter,:]= objKmeans.cluster_centers_
        distOfCenters[:,:,ii]=squareform(pdist(objKmeans.cluster_centers_,metric="euclidean"))
    model={"centers":centers,"distOfCenters":distOfCenters}   
    return model