1 files changed, 125 insertions, 0 deletions
diff --git a/nerv/tnn/layersT/lstm_t.lua b/nerv/tnn/layersT/lstm_t.lua
new file mode 100644
index 0000000..ded6058
--- /dev/null
+++ b/nerv/tnn/layersT/lstm_t.lua
@@ -0,0 +1,125 @@
+local LSTMLayerT = nerv.class('nerv.LSTMLayerT', 'nerv.LayerT')
+
+function LSTMLayerT:__init(id, global_conf, layer_conf)
+    --input1:x input2:h input3:c
+    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 pr = layer_conf.pr
+    if pr == nil then
+        pr = nerv.ParamRepo()
+    end
+    
+    local function ap(str)
+        return self.id .. '.' .. str
+    end
+
+    local layers = {
+        ["nerv.CombinerLayer"] = {
+            [ap("inputXDup")] = {{}, {["dim_in"] = {self.dim_in[1]}, 
+                ["dim_out"] = {self.dim_in[1], self.dim_in[1], self.dim_in[1], self.dim_in[1]}, ["lambda"] = {1}}},
+            [ap("inputHDup")] = {{}, {["dim_in"] = {self.dim_in[2]}, 
+                ["dim_out"] = {self.dim_in[2], self.dim_in[2], self.dim_in[2], self.dim_in[2]}, ["lambda"] = {1}}},
+            [ap("inputCDup")] = {{}, {["dim_in"] = {self.dim_in[3]}, 
+                ["dim_out"] = {self.dim_in[3], self.dim_in[3], self.dim_in[3], self.dim_in[3]}, ["lambda"] = {1}}},
+            [ap("mainCDup")] = {{}, {["dim_in"] = {self.dim_in[3], self.dim_in[3]}, ["dim_out"] = {self.dim_in[3], self.dim_in[3], self.dim_in[3]},
+                ["lambda"] = {1, 1}}},
+        },
+        ["nerv.AffineLayer"] = {
+            [ap("mainAffineL")] = {{}, {["dim_in"] = {self.dim_in[1], self.dim_in[2], self.dim_in[3]}, 
+                ["dim_out"] = {self.dim_out[1]}, ["pr"] = pr}},
+        },
+        ["nerv.TanhLayer"] = {
+            [ap("mainTanhL")] = {{}, {["dim_in"] = {self.dim_out[1]}, ["dim_out"] = {self.dim_out[1]}}},
+            [ap("outputTanhL")] = {{}, {["dim_in"] = {self.dim_out[1]}, ["dim_out"] = {self.dim_out[1]}}},
+        },
+        ["nerv.GateFFFLayer"] = {
+            [ap("forgetGateL")] = {{}, {["dim_in"] = {self.dim_in[1], self.dim_in[2], self.dim_in[3]}, 
+                ["dim_out"] = {self.dim_in[3]}, ["pr"] = pr}},
+            [ap("inputGateL")] = {{}, {["dim_in"] = {self.dim_in[1], self.dim_in[2], self.dim_in[3]}, 
+                ["dim_out"] = {self.dim_in[3]}, ["pr"] = pr}},
+            [ap("outputGateL")] = {{}, {["dim_in"] = {self.dim_in[1], self.dim_in[2], self.dim_in[3]}, 
+                ["dim_out"] = {self.dim_in[3]}, ["pr"] = pr}},
+
+        },
+        ["nerv.ElemMulLayer"] = {
+            [ap("inputGMulL")] = {{}, {["dim_in"] = {self.dim_in[3], self.dim_in[3]}, ["dim_out"] = {self.dim_in[3]}}},
+            [ap("forgetGMulL")] = {{}, {["dim_in"] = {self.dim_in[3], self.dim_in[3]}, ["dim_out"] = {self.dim_in[3]}}},
+            [ap("outputGMulL")] = {{}, {["dim_in"] = {self.dim_in[3], self.dim_in[3]}, ["dim_out"] = {self.dim_in[3]}}},
+        },
+    }
+    
+    local layerRepo = nerv.LayerRepo(layers, pr, global_conf)
+
+    local connections_t = {
+        ["<input>[1]"] = ap("inputXDup[1]"), 
+        ["<input>[2]"] = ap("inputHDup[1]"),
+        ["<input>[3]"] = ap("inputCDup[1]"),
+
+        [ap("inputXDup[1]")] = ap("mainAffineL[1]"),
+        [ap("inputHDup[1]")] = ap("mainAffineL[2]"),
+        [ap("inputCDup[1]")] = ap("mainAffineL[3]"),
+        [ap("mainAffineL[1]")] = ap("mainTanhL[1]"),
+
+        [ap("inputXDup[2]")] = ap("inputGateL[1]"),
+        [ap("inputHDup[2]")] = ap("inputGateL[2]"),
+        [ap("inputCDup[2]")] = ap("inputGateL[3]"),
+        
+        [ap("inputXDup[3]")] = ap("forgetGateL[1]"),
+        [ap("inputHDup[3]")] = ap("forgetGateL[2]"),
+        [ap("inputCDup[3]")] = ap("forgetGateL[3]"),
+
+        [ap("mainTanhL[1]")] = ap("inputGMulL[1]"),
+        [ap("inputGateL[1]")] = ap("inputGMulL[2]"),
+        
+        [ap("inputCDup[4]")] = ap("forgetGMulL[1]"),
+        [ap("forgetGateL[1]")] = ap("forgetGMulL[2]"),
+
+        [ap("inputGMulL[1]")] = ap("mainCDup[1]"),
+        [ap("forgetGMulL[1]")] = ap("mainCDup[2]"),
+
+        [ap("inputXDup[4]")] = ap("outputGateL[1]"),
+        [ap("inputHDup[4]")] = ap("outputGateL[2]"),
+        [ap("mainCDup[3]")] = ap("outputGateL[3]"),
+
+        [ap("mainCDup[2]")] = "<output>[2]",
+        [ap("mainCDup[1]")] = ap("outputTanhL[1]"),
+        
+        [ap("outputTanhL[1]")] = ap("outputGMulL[1]"),
+        [ap("outputGateL[1]")] = ap("outputGMulL[2]"),
+
+        [ap("outputGMulL[1]")] = "<output>[1]",
+    }
+    self.dagL = nerv.DAGLayerT(self.id, global_conf, 
+            {["dim_in"] = self.dim_in, ["dim_out"] = self.dim_out, ["sub_layers"] = layerRepo, 
+            ["connections"] = connections_t})
+    
+    self:check_dim_len(3, 2) -- x, h, c and h, c
+end
+
+function LSTMLayerT:init(batch_size, chunk_size)
+    self.dagL:init(batch_size, chunk_size)
+end
+
+function LSTMLayerT:batch_resize(batch_size, chunk_size)
+    self.dagL:batch_resize(batch_size, chunk_size)
+end
+
+function LSTMLayerT:update(bp_err, input, output, t)
+    self.dagL:update(bp_err, input, output, t)
+end
+
+function LSTMLayerT:propagate(input, output, t)
+    self.dagL:propagate(input, output, t)
+end
+
+function LSTMLayerT:back_propagate(bp_err, next_bp_err, input, output, t)
+    self.dagL:back_propagate(bp_err, next_bp_err, input, output, t)
+end
+
+function LSTMLayerT:get_params()
+    return self.dagL:get_params()
+end