major change: use luarocks to manage project

8 files changed, 436 insertions, 0 deletions

diff --git a/nerv/layer/affine.lua b/nerv/layer/affine.lua
new file mode 100644
index 0000000..00cbcfb
--- /dev/null
+++ b/nerv/layer/affine.lua
@@ -0,0 +1,91 @@
+local MatrixParam = nerv.class('nerv.MatrixParam', 'nerv.Param')
+local LinearTransParam = nerv.class('nerv.LinearTransParam', 'nerv.MatrixParam')
+local BiasParam = nerv.class('nerv.BiasParam', 'nerv.MatrixParam')
+local AffineLayer = nerv.class('nerv.AffineLayer', 'nerv.Layer')
+
+function MatrixParam:read(handle)
+    self.trans = self.gconf.cumat_type.new_from_host(
+                    nerv.MMatrixFloat.load(handle))
+end
+
+function MatrixParam:write(handle)
+    self.trans:new_to_host():save(handle)
+end
+
+function MatrixParam:train_init()
+    self.correction = self.trans:create()
+    self.correction:fill(0)
+end
+
+function MatrixParam:update(gradient)
+    local gconf = self.gconf
+    self.correction:add(self.correction, gradient, gconf.momentum, 1.0)
+    -- momentum gain
+    local mmt_gain = 1.0 / (1.0 - gconf.momentum);
+    local n = self.gconf.batch_size * mmt_gain
+    -- perform update
+    self.trans:add(self.trans, self.correction, 1.0, -gconf.lrate / n)
+end
+
+function LinearTransParam:update(gradient)
+    MatrixParam.update(self, gradient)
+    local gconf = self.gconf
+    -- weight decay
+    self.trans:add(self.trans, self.trans, 1.0, -gconf.lrate * gconf.wcost)
+end
+
+function AffineLayer:__init(id, global_conf, layer_conf)
+    self.id = id
+    self.ltp = layer_conf.ltp
+    self.bp = layer_conf.bp
+    self.dim_in = layer_conf.dim_in
+    self.dim_out = layer_conf.dim_out
+    self.gconf = global_conf
+    self:check_dim_len(1, 1) -- exactly one input and one output
+    self.direct_update = layer_conf.direct_update
+end
+
+function AffineLayer: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 AffineLayer:update(bp_err, input, output)
+    if self.direct_update then
+        self.ltp.correction:mul(input[1], bp_err[1], 1.0, gconf.momentum, 'T', 'N')
+        -- momentum gain
+        local mmt_gain = 1.0 / (1.0 - gconf.momentum);
+        local n = self.gconf.batch_size * mmt_gain
+        -- perform update
+        self.ltp.trans:add(self.ltp.trans, self.ltp.correction, 1.0, -gconf.lrate / n)
+    else
+        self.ltp_grad:mul(input[1], bp_err[1], 1.0, 0.0, 'T', 'N')
+        self.ltp:update(self.ltp_grad)
+    end
+    self.bp:update(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
diff --git a/nerv/layer/bias.lua b/nerv/layer/bias.lua
new file mode 100644
index 0000000..c99274d
--- /dev/null
+++ b/nerv/layer/bias.lua
@@ -0,0 +1,28 @@
+local BiasLayer = nerv.class("nerv.BiasLayer", "nerv.Layer")
+
+function BiasLayer:__init(id, global_conf, layer_conf)
+    self.id = id
+    self.gconf = global_conf
+    self.bias = layer_conf.bias
+    self.dim_in = layer_conf.dim_in
+    self.dim_out = layer_conf.dim_out
+    self:check_dim_len(1, 1)
+end
+
+function BiasLayer:init()
+    if self.dim_in[1] ~= self.bias.trans:ncol() then
+        nerv.error("mismatching dimensions of input and bias parameter")
+    end
+    if self.dim_out[1] ~= self.bias.trans:ncol() then
+        nerv.error("mismatching dimensions of output and bias parameter")
+    end
+end
+
+function BiasLayer:propagate(input, output)
+    output[1]:copy_fromd(input[1])
+    output[1]:add_row(self.bias.trans, 1.0)
+end
+
+function BiasLayer:get_params()
+    return nerv.ParamRepo({self.bias})
+end
diff --git a/nerv/layer/combiner.lua b/nerv/layer/combiner.lua
new file mode 100644
index 0000000..7bd7617
--- /dev/null
+++ b/nerv/layer/combiner.lua
@@ -0,0 +1,59 @@
+local CombinerLayer = nerv.class('nerv.CombinerLayer', 'nerv.Layer')
+
+function CombinerLayer:__init(id, global_conf, layer_conf)
+    self.id = id
+    self.lambda = layer_conf.lambda
+    self.dim_in = layer_conf.dim_in
+    self.dim_out = layer_conf.dim_out
+    self.gconf = global_conf
+    self:check_dim_len(#self.lambda, -1)
+    if #self.dim_in < 1 then
+        nerv.error("no input specified")
+    end
+    if #self.dim_out < 1 then
+        nerv.error("no output specified")
+    end
+end
+
+function CombinerLayer:init(batch_size)
+    local dim = self.dim_in[1]
+    for i = 2, #self.dim_in do
+        if self.dim_in[i] ~= dim then
+            nerv.error("mismatching dimensions of inputs")
+        end
+    end
+    for i = 1, #self.dim_out do
+        if self.dim_out[i] ~= dim then
+            nerv.error("mismatching dimensions of inputs/outputs")
+        end
+    end
+    self.sum = self.gconf.cumat_type(batch_size, dim)
+end
+
+function CombinerLayer:update(bp_err, input, output)
+end
+
+function CombinerLayer:propagate(input, output)
+    output[1]:fill(0)
+    for i = 1, #self.dim_in do
+        output[1]:add(output[1], input[i], 1.0, self.lambda[i])
+    end
+    for i = 2, #self.dim_out do
+        output[i]:copy_fromd(output[1])
+    end
+end
+
+function CombinerLayer:back_propagate(bp_err, next_bp_err, input, output)
+    local sum = self.sum
+    sum:copy_fromd(bp_err[1])
+    for i = 2, #self.dim_out do
+        sum:add(sum, bp_err[i], 1.0, 1.0)
+    end
+    for i = 1, #self.dim_in do
+        next_bp_err[i]:add(next_bp_err[i], sum, 0.0, self.lambda[i])
+    end
+end
+
+function CombinerLayer:get_params()
+    return nerv.ParamRepo({})
+end
diff --git a/nerv/layer/init.lua b/nerv/layer/init.lua
new file mode 100644
index 0000000..3c55a94
--- /dev/null
+++ b/nerv/layer/init.lua
@@ -0,0 +1,79 @@
+-- The following methods must be implemented to let a layer work properly
+
+local Param = nerv.class('nerv.Param')
+
+function Param:__init(id, global_conf)
+    self.id = id
+    self.gconf = global_conf
+end
+
+function Param:get_info()
+    return self.info
+end
+
+function Param:set_info(info)
+    self.info = info
+end
+
+function Param:read(handle)
+    nerv.error_method_not_implemented()
+end
+
+function Param:write(handle)
+    nerv.error_method_not_implemented()
+end
+
+function Param:update(gradient)
+    nerv.error_method_not_implemented()
+end
+
+local Layer = nerv.class('nerv.Layer')
+
+function Layer:__init(id, global_conf, layer_conf)
+    nerv.error_method_not_implemented()
+end
+
+function Layer:init(batch_size)
+    nerv.error_method_not_implemented()
+end
+
+function Layer:update(bp_err, input, output)
+    nerv.error_method_not_implemented()
+end
+
+function Layer:propagate(input, output)
+    nerv.error_method_not_implemented()
+end
+
+function Layer:back_propagate(bp_err, next_bp_err, input, output)
+    nerv.error_method_not_implemented()
+end
+
+function Layer:check_dim_len(len_in, len_out)
+    local expected_in = #self.dim_in
+    local expected_out = #self.dim_out
+    if len_in > 0 and expected_in ~= len_in then
+        nerv.error("layer %s expects %d inputs, %d given",
+                    self.id, len_in, expected_in)
+    end
+    if len_out > 0 and expected_out ~= len_out then
+        nerv.error("layer %s expects %d outputs, %d given",
+                    self.id, len_out, expected_out)
+    end
+end
+
+function Layer:get_params()
+    nerv.error_method_not_implemented()
+end
+
+function Layer:get_dim()
+    return self.dim_in, self.dim_out
+end
+
+nerv.include('affine.lua')
+nerv.include('sigmoid.lua')
+nerv.include('softmax_ce.lua')
+nerv.include('bias.lua')
+nerv.include('window.lua')
+nerv.include('mse.lua')
+nerv.include('combiner.lua')
diff --git a/nerv/layer/mse.lua b/nerv/layer/mse.lua
new file mode 100644
index 0000000..9a97add
--- /dev/null
+++ b/nerv/layer/mse.lua
@@ -0,0 +1,52 @@
+local MSELayer = nerv.class("nerv.MSELayer", "nerv.Layer")
+
+function MSELayer:__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:check_dim_len(2, -1)
+end
+
+function MSELayer:init(batch_size)
+    if self.dim_in[1] ~= self.dim_in[2] then
+        nerv.error("mismatching dimensions of previous network output and labels")
+    end
+    self.scale = 1 / self.dim_in[1]
+    self.total_mse = 0.0
+    self.total_frames = 0
+    self.mse = self.gconf.cumat_type(batch_size, self.dim_in[1])
+    self.mse_sum = self.gconf.cumat_type(batch_size, 1)
+    self.diff = self.mse:create()
+end
+
+function MSELayer:update(bp_err, input, output)
+    -- no params, therefore do nothing
+end
+
+function MSELayer:propagate(input, output)
+    local mse = self.mse
+    local mse_sum = self.mse_sum
+    mse:add(input[1], input[2], 1.0, -1.0)
+    self.diff:copy_fromd(mse)
+    mse:mul_elem(mse, mse)
+    mse_sum:add(mse_sum, mse:rowsum(mse), 0.0, self.scale)
+    if output[1] ~= nil then
+        output[1]:copy_fromd(mse_sum)
+    end
+    self.total_mse = self.total_mse + mse_sum:colsum()[0]
+    self.total_frames = self.total_frames + mse_sum:nrow()
+end
+
+-- NOTE: must call propagate before back_propagate
+function MSELayer:back_propagate(bp_err, next_bp_err, input, output)
+    local nbe = next_bp_err[1]
+    nbe:add(nbe, self.diff, 0.0, 2 * self.scale)
+    if bp_err[1] ~= nil then
+        nbe:scale_rows_by_col(bp_err[1])
+    end
+end
+
+function MSELayer:get_params()
+    return nerv.ParamRepo({})
+end
diff --git a/nerv/layer/sigmoid.lua b/nerv/layer/sigmoid.lua
new file mode 100644
index 0000000..dfd09eb
--- /dev/null
+++ b/nerv/layer/sigmoid.lua
@@ -0,0 +1,31 @@
+local SigmoidLayer = nerv.class("nerv.SigmoidLayer", "nerv.Layer")
+
+function SigmoidLayer:__init(id, global_conf, layer_conf)
+    self.id = id
+    self.gconf = global_conf
+    self.dim_in = layer_conf.dim_in
+    self.dim_out = layer_conf.dim_out
+    self:check_dim_len(1, 1)
+end
+
+function SigmoidLayer:init()
+    if self.dim_in[1] ~= self.dim_out[1] then
+        nerv.error("mismatching dimensions of input and output")
+    end
+end
+
+function SigmoidLayer:update(bp_err, input, output)
+    -- no params, therefore do nothing
+end
+
+function SigmoidLayer:propagate(input, output)
+    output[1]:sigmoid(input[1])
+end
+
+function SigmoidLayer:back_propagate(bp_err, next_bp_err, input, output)
+    next_bp_err[1]:sigmoid_grad(bp_err[1], output[1])
+end
+
+function SigmoidLayer:get_params()
+    return nerv.ParamRepo({})
+end
diff --git a/nerv/layer/softmax_ce.lua b/nerv/layer/softmax_ce.lua
new file mode 100644
index 0000000..daf891e
--- /dev/null
+++ b/nerv/layer/softmax_ce.lua
@@ -0,0 +1,68 @@
+local SoftmaxCELayer = nerv.class("nerv.SoftmaxCELayer", "nerv.Layer")
+
+function SoftmaxCELayer:__init(id, global_conf, layer_conf)
+    self.id = id
+    self.gconf = global_conf
+    self.dim_in = layer_conf.dim_in
+    self.dim_out = layer_conf.dim_out
+    self.compressed = layer_conf.compressed
+    if self.compressed == nil then
+        self.compressed = false
+    end
+    self:check_dim_len(2, -1) -- two inputs: nn output and label
+end
+
+function SoftmaxCELayer:init(batch_size)
+    if not self.compressed and (self.dim_in[1] ~= self.dim_in[2]) then
+        nerv.error("mismatching dimensions of previous network output and labels")
+    end
+    self.total_ce = 0.0
+    self.total_correct = 0
+    self.total_frames = 0
+    self.softmax = self.gconf.cumat_type(batch_size, self.dim_in[1])
+    self.ce = self.softmax:create()
+end
+
+function SoftmaxCELayer:update(bp_err, input, output)
+    -- no params, therefore do nothing
+end
+
+function SoftmaxCELayer:propagate(input, output)
+    local softmax = self.softmax
+    local ce = self.ce
+    local classified = softmax:softmax(input[1])
+    local label = input[2]
+    ce:log_elem(softmax)
+    if self.compressed then
+        label = label:decompress(input[1]:ncol())
+    end
+    ce:mul_elem(ce, label)
+    ce = ce:rowsum()
+    if output[1] ~= nil then
+        output[1]:copy_fromd(ce)
+    end
+    -- add total ce
+    self.total_ce = self.total_ce - ce:colsum()[0]
+    self.total_frames = self.total_frames + softmax:nrow()
+    -- TODO: add colsame for uncompressed label
+    if self.compressed then
+        self.total_correct = self.total_correct + classified:colsame(input[2])[0]
+    end
+end
+
+function SoftmaxCELayer:back_propagate(bp_err, next_bp_err, input, output)
+    -- softmax output - label
+    local label = input[2]
+    if self.compressed then
+        label = label:decompress(input[1]:ncol())
+    end
+    local nbe = next_bp_err[1]
+    nbe:add(self.softmax, label, 1.0, -1.0)
+    if bp_err[1] ~= nil then
+        nbe:scale_rows_by_col(bp_err[1])
+    end
+end
+
+function SoftmaxCELayer:get_params()
+    return nerv.ParamRepo({})
+end
diff --git a/nerv/layer/window.lua b/nerv/layer/window.lua
new file mode 100644
index 0000000..4e9a3b1
--- /dev/null
+++ b/nerv/layer/window.lua
@@ -0,0 +1,28 @@
+local WindowLayer = nerv.class("nerv.WindowLayer", "nerv.Layer")
+
+function WindowLayer:__init(id, global_conf, layer_conf)
+    self.id = id
+    self.gconf = global_conf
+    self.window = layer_conf.window
+    self.dim_in = layer_conf.dim_in
+    self.dim_out = layer_conf.dim_out
+    self:check_dim_len(1, 1)
+end
+
+function WindowLayer:init()
+    if self.dim_in[1] ~= self.window.trans:ncol() then
+        nerv.error("mismatching dimensions of input and window parameter")
+    end
+    if self.dim_out[1] ~= self.window.trans:ncol() then
+        nerv.error("mismatching dimensions of output and window parameter")
+    end
+end
+
+function WindowLayer:propagate(input, output)
+    output[1]:copy_fromd(input[1])
+    output[1]:scale_rows_by_row(self.window.trans)
+end
+
+function WindowLayer:get_params()
+    return nerv.ParamRepo({self.window})
+end