wsx66848

is the code still uncompleted? I'm a novice on deeplearning, I need an implementation of RN based on pytorch.Can somebody tell me whether the author is still following this code?...

mx.sym.full returns a new array of given shape and type, filled with the given value val so I think mx.sym.full((1,), represents [1000]

the reason why dim_mat is divied by 1 is that in the official version, div_mat = mx.sym.broadcast_div(lhs=position_mat, rhs=dim_mat),while in the autor's @heefe92 version, it is mul_mat = position_mat **\* dim_mat**

> @chensonglu > Have you successfully run the relation-networks-for-object-pytorch code? Why do I run code based on vgg16 network and get a much lower map value than the faster-rcnn code...