1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
|
local LSTMLayerT = nerv.class('nerv.LSTMLayerT', 'nerv.LayerT')
function LSTMLayerT:__init(id, global_conf, layer_conf)
self.id = id
self.dim_in = layer_conf.dim_in
self.dim_out = layer_conf.dim_out
self.gconf = global_conf
--prepare a DAGLayerT to hold the lstm structure
local paramRepo = nerv.ParamRepo()
local layers = {
["nerv.IndRecurrentLayer"] = {
["recurrentL1"] = recurrentLconfig,
}}
self:check_dim_len(1, 1) -- exactly one input and one output
end
function LSTMLayerT:init(batch_size)
if self.ltp.trans:ncol() ~= self.bp.trans:ncol() then
nerv.error("mismatching dimensions of linear transform and bias paramter")
end
if self.dim_in[1] ~= self.ltp.trans:nrow() then
nerv.error("mismatching dimensions of linear transform parameter and input")
end
if self.dim_out[1] ~= self.ltp.trans:ncol() then
nerv.error("mismatching dimensions of linear transform parameter and output")
end
self.ltp_grad = self.ltp.trans:create()
self.ltp:train_init()
self.bp:train_init()
end
function LSTMLayerT:batch_resize(batch_size)
-- do nothing
end
function AffineLayer:update(bp_err, input, output)
self.ltp:update_by_err_input(bp_err[1], input[1])
self.bp:update_by_gradient(bp_err[1]:colsum())
end
function AffineLayer:propagate(input, output)
-- apply linear transform
output[1]:mul(input[1], self.ltp.trans, 1.0, 0.0, 'N', 'N')
-- add bias
output[1]:add_row(self.bp.trans, 1.0)
end
function AffineLayer:back_propagate(bp_err, next_bp_err, input, output)
next_bp_err[1]:mul(bp_err[1], self.ltp.trans, 1.0, 0.0, 'N', 'T')
end
function AffineLayer:get_params()
return nerv.ParamRepo({self.ltp, self.bp})
end
|