aboutsummaryrefslogtreecommitdiff
path: root/layer
diff options
context:
space:
mode:
authorDeterminant <[email protected]>2015-06-22 19:01:29 +0800
committerDeterminant <[email protected]>2015-06-22 19:01:29 +0800
commit2497fd9e7a0fae5ee4887890d7a312e0e08a93b8 (patch)
tree382f97575bd2df9ee6abb1662b11b279fc22d72b /layer
parent196e9b48a3541caccdffc5743001cced70667091 (diff)
major change: use luarocks to manage project
Diffstat (limited to 'layer')
-rw-r--r--layer/affine.lua91
-rw-r--r--layer/bias.lua28
-rw-r--r--layer/combiner.lua59
-rw-r--r--layer/init.lua79
-rw-r--r--layer/mse.lua52
-rw-r--r--layer/sigmoid.lua31
-rw-r--r--layer/softmax_ce.lua68
-rw-r--r--layer/window.lua28
8 files changed, 0 insertions, 436 deletions
diff --git a/layer/affine.lua b/layer/affine.lua
deleted file mode 100644
index 00cbcfb..0000000
--- a/layer/affine.lua
+++ /dev/null
@@ -1,91 +0,0 @@
-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/layer/bias.lua b/layer/bias.lua
deleted file mode 100644
index c99274d..0000000
--- a/layer/bias.lua
+++ /dev/null
@@ -1,28 +0,0 @@
-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/layer/combiner.lua b/layer/combiner.lua
deleted file mode 100644
index 7bd7617..0000000
--- a/layer/combiner.lua
+++ /dev/null
@@ -1,59 +0,0 @@
-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/layer/init.lua b/layer/init.lua
deleted file mode 100644
index e39af94..0000000
--- a/layer/init.lua
+++ /dev/null
@@ -1,79 +0,0 @@
--- 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
-
-require 'layer.affine'
-require 'layer.sigmoid'
-require 'layer.softmax_ce'
-require 'layer.bias'
-require 'layer.window'
-require 'layer.mse'
-require 'layer.combiner'
diff --git a/layer/mse.lua b/layer/mse.lua
deleted file mode 100644
index 9a97add..0000000
--- a/layer/mse.lua
+++ /dev/null
@@ -1,52 +0,0 @@
-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/layer/sigmoid.lua b/layer/sigmoid.lua
deleted file mode 100644
index dfd09eb..0000000
--- a/layer/sigmoid.lua
+++ /dev/null
@@ -1,31 +0,0 @@
-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/layer/softmax_ce.lua b/layer/softmax_ce.lua
deleted file mode 100644
index daf891e..0000000
--- a/layer/softmax_ce.lua
+++ /dev/null
@@ -1,68 +0,0 @@
-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/layer/window.lua b/layer/window.lua
deleted file mode 100644
index 4e9a3b1..0000000
--- a/layer/window.lua
+++ /dev/null
@@ -1,28 +0,0 @@
-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