Question

我尝试了很多谷歌搜索，但找不到。它是关于CNN人脸检测的一些论文的实现吗？

dlib卷积脸部检测器的理论部分是否有任何细节？

Answer 1

它使用自定义架构。您可以在source code

中进行检查

    ...    

    template <template <int,template<typename>class,int,typename> class block, int N, template<typename>class BN, typename SUBNET>
    using residual = add_prev1<block<N,BN,1,tag1<SUBNET>>>;

    template <template <int,template<typename>class,int,typename> class block, int N, template<typename>class BN, typename SUBNET>
    using residual_down = add_prev2<avg_pool<2,2,2,2,skip1<tag2<block<N,BN,2,tag1<SUBNET>>>>>>;

    template <int N, template <typename> class BN, int stride, typename SUBNET> 
    using block  = BN<con<N,3,3,1,1,relu<BN<con<N,3,3,stride,stride,SUBNET>>>>>;

    template <int N, typename SUBNET> using ares      = relu<residual<block,N,affine,SUBNET>>;
    template <int N, typename SUBNET> using ares_down = relu<residual_down<block,N,affine,SUBNET>>;

    template <typename SUBNET> using alevel0 = ares_down<256,SUBNET>;
    template <typename SUBNET> using alevel1 = ares<256,ares<256,ares_down<256,SUBNET>>>;
    template <typename SUBNET> using alevel2 = ares<128,ares<128,ares_down<128,SUBNET>>>;
    template <typename SUBNET> using alevel3 = ares<64,ares<64,ares<64,ares_down<64,SUBNET>>>>;
    template <typename SUBNET> using alevel4 = ares<32,ares<32,ares<32,SUBNET>>>;

    using anet_type = loss_metric<fc_no_bias<128,avg_pool_everything<
                                alevel0<
                                alevel1<
                                alevel2<
                                alevel3<
                                alevel4<
                                max_pool<3,3,2,2,relu<affine<con<32,7,7,2,2,
                                input_rgb_image_sized<150>
                                >>>>>>>>>>>>;
    anet_type net;

    ...

dlib的CNN面部检测器使用哪种架构？

1 个答案: