graph layer complete

6 files changed, 203 insertions, 8 deletions

diff --git a/nerv/Makefile b/nerv/Makefile
index a2155b9..ba97579 100644
--- a/nerv/Makefile
+++ b/nerv/Makefile
@@ -34,6 +34,7 @@ LUA_LIBS := matrix/init.lua io/init.lua init.lua \
 			layer/init.lua layer/affine.lua layer/sigmoid.lua layer/tanh.lua layer/softmax_ce.lua layer/softmax.lua \
 			layer/window.lua layer/bias.lua layer/combiner.lua layer/mse.lua \
 			layer/elem_mul.lua layer/lstm.lua layer/lstm_gate.lua layer/dropout.lua layer/gru.lua \
+            layer/graph.lua layer/rnn.lua \
 			nn/init.lua nn/layer_repo.lua nn/param_repo.lua nn/layer_dag.lua \
 			io/sgd_buffer.lua \
 			tnn/init.lua tnn/sutil.lua tnn/tnn.lua
diff --git a/nerv/layer/graph.lua b/nerv/layer/graph.lua
new file mode 100644
index 0000000..83cf810
--- /dev/null
+++ b/nerv/layer/graph.lua
@@ -0,0 +1,118 @@
+local GraphLayer = nerv.class('nerv.GraphLayer', 'nerv.Layer')
+
+function GraphLayer:__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
+    self:graph_init(layer_conf.layer_repo, layer_conf.connections)
+end
+
+local function parse_id(str)
+    local id, port, _
+    _, _, id, port = string.find(str, "([a-zA-Z0-9_.]+)%[([0-9]+)%]")
+    if id == nil or port == nil then
+        _, _, id, port = string.find(str, "(.+)%[([0-9]+)%]")
+        if not (id == "<input>" or id == "<output>") then
+            nerv.error("wrong format of connection id")
+        end
+    end
+    port = tonumber(port)
+    return id, port
+end
+
+local function discover(id, layers, layer_repo)
+    if id == '<output>' then
+        id = '<input>'
+    end
+    local ref = layers[id]
+    if ref == nil then
+        local layer = layer_repo:get_layer(id)
+        local dim_in, dim_out = layer:get_dim()
+        ref = {
+            layer = layer,
+            inputs = {},
+            outputs = {},
+            dim_in = dim_in,
+            dim_out = dim_out,
+        }
+        layers[id] = ref
+    end
+    return ref
+end
+
+function GraphLayer:graph_init(layer_repo, connections)
+    self.connections = connections
+    self.sublayer = nerv.LayerRepo({}, nerv.ParamRepo(), self.gconf)
+
+    -- check data dimension between connected ports
+    local layers = {}
+    layers['<input>'] = {
+        inputs = {},
+        outputs = {},
+        dim_in = self.dim_out,
+        dim_out = self.dim_in,
+    }
+    for _, edge in pairs(self.connections) do
+        local from = edge[1]
+        local to = edge[2]
+        local id_from, port_from = parse_id(from)
+        local id_to, port_to = parse_id(to)
+        local ref_from = discover(id_from, layers, layer_repo)
+        local ref_to = discover(id_to, layers, layer_repo)
+        if ref_to.inputs[port_to] ~= nil then
+            nerv.error('%s has already been attached', to)
+        end
+        if ref_from.dim_out[port_from] ~= ref_to.dim_in[port_to] then
+            nerv.error('mismatching data dimension between %s and %s', from, to)
+        end
+        ref_from.outputs[port_from] = true
+        ref_to.inputs[port_to] = true
+    end
+
+    -- check dangling ports
+    for id, ref in pairs(layers) do
+        if id ~= '<input>' then
+            for i = 1, #ref.dim_in do
+                if ref.inputs[i] == nil then
+                    nerv.error('dangling input port %d of layer %s', i, id)
+                end
+            end
+            for i = 1, #ref.dim_out do
+                if ref.outputs[i] == nil then
+                   nerv.error('dangling output port %d os layer %s', i, id)
+                end
+            end
+            self.sublayer.layers[id] = ref.layer
+        end
+    end
+    for i = 1, #self.dim_in do
+        if layers['<input>'].outputs[i] == nil then
+            nerv.error('dangling port %d of layer <input>', i)
+        end
+    end
+    for i = 1, #self.dim_out do
+        if layers['<input>'].inputs[i] == nil then
+            nerv.error('dangling port %d of layer <output>', i)
+        end
+    end
+end
+
+function GraphLayer:set_attr(name, value)
+    self[name] = value
+    for id, layer in pairs(self.sublayer.layers) do
+        layer:set_attr(name, value)
+    end
+end
+
+function GraphLayer:get_sublayer(id)
+    return self.sublayer:get_layer(id)
+end
+
+function GraphLayer:get_params()
+    local param_repos = {}
+    for id, layer in pairs(self.sublayer.layers) do
+        table.insert(param_repos, layer:get_params())
+    end
+    return nerv.ParamRepo.merge(param_repos)
+end
diff --git a/nerv/layer/init.lua b/nerv/layer/init.lua
index 54f33ae..5e3395c 100644
--- a/nerv/layer/init.lua
+++ b/nerv/layer/init.lua
@@ -70,6 +70,14 @@ function Layer:get_dim()
     return self.dim_in, self.dim_out
 end
 
+function Layer:set_attr(name, value)
+    self[name] = value
+end
+
+function Layer:get_sublayer(id)
+    nerv.error('primitive layer does not have sublayers.')
+end
+
 function Layer:find_param(pid_list, lconf, gconf, p_type, p_dim)
     if type(pid_list) == "string" then
         pid_list = {pid_list}
@@ -101,6 +109,7 @@ function Layer:find_param(pid_list, lconf, gconf, p_type, p_dim)
     return p
 end
 
+nerv.include('graph.lua')
 nerv.include('affine.lua')
 nerv.include('sigmoid.lua')
 nerv.include('tanh.lua')
@@ -115,6 +124,7 @@ nerv.include('lstm.lua')
 nerv.include('lstm_gate.lua')
 nerv.include('dropout.lua')
 nerv.include('gru.lua')
+nerv.include('rnn.lua')
 
 -- The following lines are for backward compatibility, and will be removed in
 -- the future. The use of these names are deprecated.
diff --git a/nerv/layer/rnn.lua b/nerv/layer/rnn.lua
new file mode 100644
index 0000000..a93530f
--- /dev/null
+++ b/nerv/layer/rnn.lua
@@ -0,0 +1,37 @@
+local RNNLayer = nerv.class('nerv.RNNLayer', 'nerv.GraphLayer')
+
+function RNNLayer:__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 = layer_conf.gconf
+    self:check_dim_len(1, 1)
+
+    local din = layer_conf.dim_in[1]
+    local dout = layer_conf.dim_out[1]
+
+    local pr = layer_conf.pr
+    if pr == nil then
+        pr = nerv.ParamRepo()
+    end
+
+    local layers = {
+        ['nerv.AffineLayer'] = {
+            main = {dim_in = {din, dout}, dim_out = {dout}, pr = pr},
+        },
+        ['nerv.SigmoidLayer'] = {
+            sigmoid = {dim_in = {dout}, dim_out = {dout}},
+        },
+    }
+
+    local layer_repo = nerv.LayerRepo(layers, pr, global_conf)
+
+    local connections = {
+        {'<input>[1]', 'main[1]', 0},
+        {'main[1]', 'sigmoid[1]', 0},
+        {'sigmoid[1]', 'main[2]', 0},
+        {'sigmoid[1]', '<output>[1]', 1},
+    }
+
+    self:graph_init(layer_repo, connections)
+end
diff --git a/nerv/main.lua b/nerv/main.lua
new file mode 100644
index 0000000..85e291c
--- /dev/null
+++ b/nerv/main.lua
@@ -0,0 +1,31 @@
+print 'Hello'
+
+local global_conf = {
+    cumat_type = nerv.CuMatrixFloat,
+    param_random = function() return 0 end,
+}
+
+local layer_repo = nerv.LayerRepo(
+    {
+        ['nerv.RNNLayer'] = {
+            rnn = {dim_in = {23}, dim_out = {26}},
+        },
+        ['nerv.AffineLayer'] = {
+            input = {dim_in = {20}, dim_out = {23}},
+            output = {dim_in = {26, 79}, dim_out = {79}},
+        },
+        ['nerv.SigmoidLayer'] = {
+            sigmoid = {dim_in = {23}, dim_out = {23}},
+        },
+    }, nerv.ParamRepo(), global_conf)
+
+local connections = {
+    {'<input>[1]', 'input[1]', 0},
+    {'input[1]', 'sigmoid[1]', 0},
+    {'sigmoid[1]', 'rnn[1]', 0},
+    {'rnn[1]', 'output[1]', 0},
+    {'output[1]', 'output[2]', 1},
+    {'output[1]', '<output>[1]', 0},
+}
+
+local network = nerv.GraphLayer('network', global_conf, {dim_in = {20}, dim_out = {79}, layer_repo = layer_repo, connections = connections})
diff --git a/nerv/nn/layer_repo.lua b/nerv/nn/layer_repo.lua
index 3d3a79f..a169b2b 100644
--- a/nerv/nn/layer_repo.lua
+++ b/nerv/nn/layer_repo.lua
@@ -12,20 +12,18 @@ function LayerRepo:add_layers(layer_spec, param_repo, global_conf)
         if layer_type == nil then
             nerv.error('layer type `%s` not found', ltype)
         end
-        for id, spec in pairs(llist) do
+        for id, layer_config in pairs(llist) do
             if layers[id] ~= nil then
                 nerv.error("a layer with id %s already exists", id)
             end
             nerv.info("create layer: %s", id)
-            if type(spec[2]) ~= "table" then
+            if type(layer_config) ~= "table" then
                 nerv.error("layer config table is need")
             end
-            layer_config = spec[2]
-            if type(spec[1]) ~= "table" then
-                nerv.error("parameter description table is needed")
-            end
-            for pname, pid in pairs(spec[1]) do
-                layer_config[pname] = param_repo:get_param(pid)
+            if type(layer_config.params) == "table" then
+                for pname, pid in pairs(layer_config.params) do
+                    layer_config[pname] = param_repo:get_param(pid)
+                end
             end
             if layer_config.pr == nil then
                 layer_config.pr = param_repo