caffe-innerproduct layer

caffe-innerproduct

usage:

layer {name: "inn"type: "InnerProduct"bottom: "data"top: "topinn"param {name: "w_hh"}inner_product_param {num_output: 10bias_term: falseweight_filler {type: "uniform"min: -0.8max: 0.8}axis: 2 #default 1   # The first axis to be lumped into a single inner product computation;                                     # all preceding axes are retained in the output.}}

e.g.

data : 5 * 3 * 4 * 4

output: 10  axis: 2

=>

param: 10 * 16

datainn: 5 * 3 * 10