Overlapping community detection has become a very hot research topic in recent decades,and a plethora of methods have been proposed.But,a common challenge in many existing overlapping community detection approaches is that the number of communities K must be predefined man-ually.We propose a flexible nonparametric Bayesian gener-ative model for count-value networks,which can allow K to increase as more and more data are encountered instead of to be fixed in advance.The Indian buffet process was used to model the community assignment matrix Z,and an uncol-lapsed Gibbs sampler has been derived.However,as the com-munity assignment matrix Z is a structured multi-variable pa-rameter,how to summarize the posterior inference results and estimate the inference quality about Z,is still a considerable challenge in the literature.In this paper,a graph convolutional neural network based graph classifier was utilized to help to summarize the results and to estimate the inference quality about Z.We conduct extensive experiments on synthetic data and real data,and find that empirically,the traditional poste-rior summarization strategy is reliable.