diff options
| -rw-r--r-- | README.md | 3 | ||||
| -rw-r--r-- | doc/nerv_layer.md | 136 | ||||
| -rw-r--r-- | doc/nerv_nn.md | 32 | ||||
| -rw-r--r-- | matrix/init.lua | 2 |
4 files changed, 167 insertions, 6 deletions
@@ -36,7 +36,8 @@ The IO package is used to read and write parameters to file. The parameter package is used to store, read model parameters from file. * __[The Nerv Layer Package](doc/nerv_layer.md)__ The layer package is used to define propagation and backpropagation of different type of layers. - +* __[The Nerv NN Package](doc/nerv_nn.md)__ +The nn package is for organizing a neural network, it contains __nerv.LayerRepo__, __nerv.ParamRepo__, and __nerv.DAGLayer__. [luaT]:https://github.com/torch/torch7/tree/master/lib/luaT [Torch]:https://github.com/torch [sync-help]:https://help.github.com/articles/syncing-a-fork/ diff --git a/doc/nerv_layer.md b/doc/nerv_layer.md index dd991df..0425d5f 100644 --- a/doc/nerv_layer.md +++ b/doc/nerv_layer.md @@ -9,15 +9,17 @@ __nerv.Layer__ is the base class and most of its methods are abstract. * `table dim_out` It specifies the dimensions of the outputs. * `string id` ID of this layer. * `table gconf` Stores the `global_conf`. -* __nerv.AffineLayer__ inherits __nerv.Layer__, both `#dim_in` and `#dim_out` are 1. +* __nerv.AffineLayer__ inherits __nerv.Layer__, both `#dim_in` and `#dim_out` are 1. * `MatrixParam ltp` The liner transform parameter. * `BiasParam bp` The bias parameter. * __nerv.BiasLayer__ inherits __nerv.Layer__, both `#dim_in` nad `#dim_out` are 1. * `BiasParam bias` The bias parameter. * __nerv.SigmoidLayer__ inherits __nerv.Layer__, both `#dim_in` and `#dim_out` are 1. -* __nerv.SoftmaxCELayer__ inherits __nerv.Layer__, `#dim_in` is 2 and `#dim_out` is 1. - * `float total_ce` - * `int total_frams` Records how many frames have passed. +* __nerv.SoftmaxCELayer__ inherits __nerv.Layer__, `#dim_in` is 2 and `#dim_out` is 0. `input[1]` is the input to the softmax layer, `input[2]` is the reference distribution. + * `float total_ce` Records the accumlated cross entropy value. + * `int total_frams` Records how many frames have passed. + * `bool compressed` The reference distribution can be a one-hot format. This feature is enabled by `layer_conf.compressed`. + ##Methods## * __void Layer.\_\_init(Layer self, string id, table global_conf, table layer_conf)__ Abstract method. @@ -41,3 +43,129 @@ Check whether `#self.dim_in == len_in` and `#self.dim_out == len_out`, if violat Abstract method. The layer should return a list containing its parameters. +##Examples## +* a basic example using __Nerv__ layers to a linear classification. + +``` +require 'math' + +require 'layer.affine' +require 'layer.softmax_ce' + +--[[Example using layers, a simple two-classification problem]]-- + +function calculate_accurate(networkO, labelM) + sum = 0 + for i = 0, networkO:nrow() - 1, 1 do + if (labelM[i][0] == 1 and networkO[i][0] >= 0.5) then + sum = sum + 1 + end + if (labelM[i][1] == 1 and networkO[i][1] >= 0.5) then + sum = sum + 1 + end + end + return sum +end + +--[[begin global setting and data generation]]-- +global_conf = {lrate = 10, + wcost = 1e-6, + momentum = 0.9, + cumat_type = nerv.CuMatrixFloat} + +input_dim = 5 +data_num = 100 +ansV = nerv.CuMatrixFloat(input_dim, 1) +for i = 0, input_dim - 1, 1 do + ansV[i][0] = math.random() - 0.5 +end +ansB = math.random() - 0.5 +print('displaying ansV') +print(ansV) +print('displaying ansB(bias)') +print(ansB) + +dataM = nerv.CuMatrixFloat(data_num, input_dim) +for i = 0, data_num - 1, 1 do + for j = 0, input_dim - 1, 1 do + dataM[i][j] = math.random() * 2 - 1 + end +end +refM = nerv.CuMatrixFloat(data_num, 1) +refM:fill(ansB) +refM:mul(dataM, ansV, 1, 1) --refM = dataM * ansV + ansB + +labelM = nerv.CuMatrixFloat(data_num, 2) +for i = 0, data_num - 1, 1 do + if (refM[i][0] > 0) then + labelM[i][0] = 1 + labelM[i][1] = 0 + else + labelM[i][0] = 0 + labelM[i][1] = 1 + end +end +--[[global setting and data generation end]]-- + + +--[[begin network building]]-- +--parameters +affineL_ltp = nerv.LinearTransParam('AffineL_ltp', global_conf) +affineL_ltp.trans = nerv.CuMatrixFloat(input_dim, 2) +for i = 0, input_dim - 1, 1 do + for j = 0, 1, 1 do + affineL_ltp.trans[i][j] = math.random() - 0.5 + end +end +affineL_bp = nerv.BiasParam('AffineL_bp', global_conf) +affineL_bp.trans = nerv.CuMatrixFloat(1, 2) +for j = 0, 1, 1 do + affineL_bp.trans[j] = math.random() - 0.5 +end + +--layers +affineL = nerv.AffineLayer('AffineL', global_conf, {['ltp'] = affineL_ltp, + ['bp'] = affineL_bp, + dim_in = {input_dim}, + dim_out = {2}}) +softmaxL = nerv.SoftmaxCELayer('softmaxL', global_conf, {dim_in = {2, 2}, + dim_out = {}}) +print('layers initializing...') +affineL:init() +softmaxL:init() +--[[network building end]]-- + + +--[[begin space allocation]]-- +print('network input&output&error space allocation...') +affineI = {dataM} --input to the network is data +affineO = {nerv.CuMatrixFloat(data_num, 2)} +softmaxI = {affineO[1], labelM} +softmaxO = {nerv.CuMatrixFloat(data_num, 2)} + +affineE = {nerv.CuMatrixFloat(data_num, 2)} +--[[space allocation end]]-- + + +--[[begin training]]-- +ce_last = 0 +for l = 0, 10, 1 do + affineL:propagate(affineI, affineO) + softmaxL:propagate(softmaxI, softmaxO) + softmaxO[1]:softmax(softmaxI[1]) + + softmaxL:back_propagate(affineE, nil, softmaxI, softmaxO) + + affineL:update(affineE, affineI, affineO) + + if (l % 5 == 0) then + nerv.utils.printf("training iteration %d finished\n", l) + nerv.utils.printf("cross entropy: %.8f\n", softmaxL.total_ce - ce_last) + ce_last = softmaxL.total_ce + nerv.utils.printf("accurate labels: %d\n", calculate_accurate(softmaxO[1], labelM)) + nerv.utils.printf("total frames processed: %.8f\n", softmaxL.total_frames) + end +end +--[[end training]]-- + +```
\ No newline at end of file diff --git a/doc/nerv_nn.md b/doc/nerv_nn.md new file mode 100644 index 0000000..54c7165 --- /dev/null +++ b/doc/nerv_nn.md @@ -0,0 +1,32 @@ +#The Nerv NN Package# +Part of the [Nerv](../README.md) toolkit. + +##Description## +###Class hierarchy### +it contains __nerv.LayerRepo__, __nerv.ParamRepo__, and __nerv.DAGLayer__(inherits __nerv.Layer__). + +###Class hierarchy and their members### +* __nerv.ParamRepo__ Get parameter object by ID. + * `table param_table` Contains the mapping of parameter ID to parameter file(__nerv.ChunkFile__) +* __nerv.LayerRepo__ Get layer object by ID. + * `table layers` Contains the mapping of layer ID to layer object. +objects. +* __nerv.DAGLayer__ inherits __nerv.Layer__. + +##Methods## +###__nerv.ParamRepo__### +* __void ParamRepo:\_\_init(table param_files)__ +`param_files` is a list of file names that stores parameters, the newed __ParamRepo__ will read them from file and store the mapping for future fetching. +* __nerv.Param ParamRepo.get_param(ParamRepo self, string pid, table global_conf)__ +__ParamRepo__ will find the __nerv.ChunkFile__ `pf` that contains parameter of ID `pid` and return `pf:read_chunk(pid, global_conf)`. + +###__nerv.LayerRepo__### +* __void LayerRepo:\_\_init(table layer_spec, ParamRepo param_repo, table global_conf)__ +__LayerRepo__ will construct the layers specified in `layer_spec`. Every entry in the `layer_spec` table should follow the format below: +``` +layer_spec : {[layer_type1] = llist1, [layer_type2] = llist2, ...} +llist : {layer1, layer2, ...} +layer : layerid = {param_config, layer_config} +param_config : {param1 = paramID1, param2 = paramID2} +``` +__LayerRepo__ will merge `param_config` into `layer_config` and construct a layer by calling `layer_type(layerid, global_conf, layer_config)`.
\ No newline at end of file diff --git a/matrix/init.lua b/matrix/init.lua index 9637391..7bbc6a4 100644 --- a/matrix/init.lua +++ b/matrix/init.lua @@ -42,7 +42,7 @@ function nerv.CuMatrix:__sub__(b) end function nerv.CuMatrix:__mul__(b) - c = self:create() + c = nerv.get_type(self.__typename)(self:nrow(), b:ncol()) c:mul(self, b, 1.0, 0.0, 'N', 'N') return c end |