major change: clearer param binding semantics; permit rebinding; enable

resuming from previous training

1 files changed, 12 insertions, 8 deletions

diff --git a/nerv/layer/lstm.lua b/nerv/layer/lstm.lua
index 500bd87..d4c9212 100644
--- a/nerv/layer/lstm.lua
+++ b/nerv/layer/lstm.lua
@@ -4,15 +4,11 @@ function LSTMLayer:__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
-
+    nerv.Layer.__init(self, id, global_conf, layer_conf)
     -- prepare a DAGLayer to hold the lstm structure
     local pr = layer_conf.pr
     if pr == nil then
-        pr = nerv.ParamRepo()
+        pr = nerv.ParamRepo(nil, self.loc_type)
     end
     
     local function ap(str)
@@ -66,7 +62,7 @@ function LSTMLayer:__init(id, global_conf, layer_conf)
         },
     }
     
-    local layerRepo = nerv.LayerRepo(layers, pr, global_conf)
+    self.lrepo = nerv.LayerRepo(layers, pr, global_conf)
 
     local connections = {
         ["<input>[1]"] = ap("inputXDup[1]"),
@@ -109,12 +105,20 @@ function LSTMLayer:__init(id, global_conf, layer_conf)
     self.dag = nerv.DAGLayer(self.id, global_conf,
                                 {dim_in = self.dim_in,
                                  dim_out = self.dim_out,
-                                 sub_layers = layerRepo,
+                                 sub_layers = self.lrepo,
                                  connections = connections})
     
     self:check_dim_len(3, 2) -- x, h, c and h, c
 end
 
+function LSTMLayer:bind_params()
+    local pr = layer_conf.pr
+    if pr == nil then
+        pr = nerv.ParamRepo(nil, self.loc_type)
+    end
+    self.lrepo:rebind(pr)
+end
+
 function LSTMLayer:init(batch_size, chunk_size)
     self.dag:init(batch_size, chunk_size)
 end