diff options
Diffstat (limited to 'nerv/layer')
| -rw-r--r-- | nerv/layer/lstm.lua | 11 | ||||
| -rw-r--r-- | nerv/layer/lstm_gate.lua | 7 |
2 files changed, 14 insertions, 4 deletions
diff --git a/nerv/layer/lstm.lua b/nerv/layer/lstm.lua index 500bd87..b0cfe08 100644 --- a/nerv/layer/lstm.lua +++ b/nerv/layer/lstm.lua @@ -19,7 +19,7 @@ function LSTMLayer:__init(id, global_conf, layer_conf) return self.id .. '.' .. str end local din1, din2, din3 = self.dim_in[1], self.dim_in[2], self.dim_in[3] - local dout1, dout2, dout3 = self.dim_out[1], self.dim_out[2], self.dim_out[3] + local dout1, dout2 = self.dim_out[1], self.dim_out[2] local layers = { ["nerv.CombinerLayer"] = { [ap("inputXDup")] = {{}, {dim_in = {din1}, @@ -49,11 +49,14 @@ function LSTMLayer:__init(id, global_conf, layer_conf) }, ["nerv.LSTMGateLayer"] = { [ap("forgetGateL")] = {{}, {dim_in = {din1, din2, din3}, - dim_out = {din3}, pr = pr}}, + dim_out = {din3}, pr = pr}, + param_type = {'N', 'N', 'D'}}, [ap("inputGateL")] = {{}, {dim_in = {din1, din2, din3}, - dim_out = {din3}, pr = pr}}, + dim_out = {din3}, pr = pr}, + param_tpye = {'N', 'N', 'D'}}, [ap("outputGateL")] = {{}, {dim_in = {din1, din2, din3}, - dim_out = {din3}, pr = pr}}, + dim_out = {din3}, pr = pr}, + param_type = {'N', 'N', 'D'}}, }, ["nerv.ElemMulLayer"] = { diff --git a/nerv/layer/lstm_gate.lua b/nerv/layer/lstm_gate.lua index 1963eba..8785b4f 100644 --- a/nerv/layer/lstm_gate.lua +++ b/nerv/layer/lstm_gate.lua @@ -5,12 +5,16 @@ function LSTMGateLayer:__init(id, global_conf, layer_conf) self.id = id self.dim_in = layer_conf.dim_in self.dim_out = layer_conf.dim_out + self.param_type = layer_conf.param_type self.gconf = global_conf for i = 1, #self.dim_in do self["ltp" .. i] = self:find_param("ltp" .. i, layer_conf, global_conf, nerv.LinearTransParam, {self.dim_in[i], self.dim_out[1]}) + if self.param_type[i] == 'D' then + self["ltp" .. i].trans:diagonalize() + end end self.bp = self:find_param("bp", layer_conf, global_conf, nerv.BiasParam, {1, self.dim_out[1]}) @@ -64,6 +68,9 @@ function LSTMGateLayer:update(bp_err, input, output) self.err_bakm:sigmoid_grad(bp_err[1], output[1]) for i = 1, #self.dim_in do self["ltp" .. i]:update_by_err_input(self.err_bakm, input[i]) + if self.param_type[i] == 'D' then + self["ltp" .. i].trans:diagonalize() + end end self.bp:update_by_gradient(self.err_bakm:colsum()) end |