Function std::tensor_conv2d_ex

&FloatTensor tensor_conv2d_ex(
    const &FloatTensor x,
    const &FloatTensor weight,
    const &FloatTensor bias,
    unsigned long inC,
    unsigned long inH,
    unsigned long inW,
    const &Conv2dSpec spec,
)

x is [batch, inCinHinW] (a 1D tensor is one image). Each returns [batch, outCoutHoutW] and records its backward edge to x, weight and bias, like tensor_add does. outC is bias's size.