caffe-innerproduct layer

caffe-innerproduct

usage:

layer {
	name: "inn"
	type: "InnerProduct"
	bottom: "data"
	top: "topinn"
	param {
		name: "w_hh"
	}
	inner_product_param {
		num_output: 10
		bias_term: false
		weight_filler {
			type: "uniform"
			min: -0.8
			max: 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