caffe-reduction layer

Reduction

usage:

layer {name: "reductionx"bottom: "rnn1"top: "reductionx"type: "Reduction"loss_weight: 1reduction_param {axis: 0}}

this layer is used in rnn-unrolled network.

layer {  name: "rnn_o_concat"  type: "Concat"  bottom: "o_1"  bottom: "o_2"  bottom: "o_3"  top: "o"  concat_param {    axis: 0  }}layer {  name: "o_pseudoloss"  type: "Reduction"  bottom: "o"  top: "o_pseudoloss"  loss_weight: 1}