Lenet5的网络结构图如下

第一个池化层(S2)和第二个卷积层(C3)之间的连接表如下：

大家看下Tiny-DNN的代码，如下所示，代码结构非常清晰得表达了连接表的逻辑，

static void construct_net(tiny_dnn::network<tiny_dnn::sequential> &nn,
                          tiny_dnn::core::backend_t backend_type) {
// connection table [Y.Lecun, 1998 Table.1]
#define O true
#define X false
  // clang-format off
static const bool tbl[] = {
    O, X, X, X, O, O, O, X, X, O, O, O, O, X, O, O,
    O, O, X, X, X, O, O, O, X, X, O, O, O, O, X, O,
    O, O, O, X, X, X, O, O, O, X, X, O, X, O, O, O,
    X, O, O, O, X, X, O, O, O, O, X, X, O, X, O, O,
    X, X, O, O, O, X, X, O, O, O, O, X, O, O, X, O,
    X, X, X, O, O, O, X, X, O, O, O, O, X, O, O, O
};
// clang-format on
#undef O
#undef X

  // construct nets
  //
  // C : convolution
  // S : sub-sampling
  // F : fully connected
  // clang-format off
  using fc = tiny_dnn::layers::fc;
  using conv = tiny_dnn::layers::conv;
  using ave_pool = tiny_dnn::layers::ave_pool;
  using tanh = tiny_dnn::activation::tanh;

  using tiny_dnn::core::connection_table;
  using padding = tiny_dnn::padding;

  nn << conv(32, 32, 5, 1, 6,   // C1, 1@32x32-in, 6@28x28-out
             padding::valid, true, 1, 1, 1, 1, backend_type)
     << tanh()
     << ave_pool(28, 28, 6, 2)   // S2, 6@28x28-in, 6@14x14-out
     << tanh()
     << conv(14, 14, 5, 6, 16,   // C3, 6@14x14-in, 16@10x10-out
             connection_table(tbl, 6, 16),
             padding::valid, true, 1, 1, 1, 1, backend_type)
     << tanh()
     << ave_pool(10, 10, 16, 2)  // S4, 16@10x10-in, 16@5x5-out
     << tanh()
     << conv(5, 5, 5, 16, 120,   // C5, 16@5x5-in, 120@1x1-out
             padding::valid, true, 1, 1, 1, 1, backend_type)
     << tanh()
     << fc(120, 10, true, backend_type)  // F6, 120-in, 10-out
     << tanh();
}

而在github或者其他网络上看到Python实现的代码，几乎都没有表达这个连接表的逻辑，所以挺困惑，

是因为S2到C3之间不需要按照连接表来进行吗？