diff options
Diffstat (limited to 'doc/nerv_layer.md')
| -rw-r--r-- | doc/nerv_layer.md | 23 |
1 files changed, 16 insertions, 7 deletions
diff --git a/doc/nerv_layer.md b/doc/nerv_layer.md index 0425d5f..de2fb12 100644 --- a/doc/nerv_layer.md +++ b/doc/nerv_layer.md @@ -15,7 +15,7 @@ __nerv.Layer__ is the base class and most of its methods are abstract. * __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 0. `input[1]` is the input to the softmax layer, `input[2]` is the reference distribution. +* __nerv.SoftmaxCELayer__ inherits __nerv.Layer__, `#dim_in` is 2 and `#dim_out` is -1(optional). `input[1]` is the input to the softmax layer, `input[2]` is the reference distribution. In its `propagate(input, output)` method, if `output[1] ~= nil`, cross\_entropy value will outputed. * `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`. @@ -43,6 +43,15 @@ 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. +####nerv.Layer.get\_dim(self)#### +* Returns: + `dim_in`: __table__. + `dim_out`: __table__. +* Parameters: + `self`: __nerv.Layer__. +* Description: + Returns `self.dim_in, self.dim_out`. + ##Examples## * a basic example using __Nerv__ layers to a linear classification. @@ -141,7 +150,8 @@ 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)} +softmaxO = {} +output = nerv.CuMatrixFloat(data_num, 2) affineE = {nerv.CuMatrixFloat(data_num, 2)} --[[space allocation end]]-- @@ -152,9 +162,9 @@ ce_last = 0 for l = 0, 10, 1 do affineL:propagate(affineI, affineO) softmaxL:propagate(softmaxI, softmaxO) - softmaxO[1]:softmax(softmaxI[1]) + output:softmax(softmaxI[1]) - softmaxL:back_propagate(affineE, nil, softmaxI, softmaxO) + softmaxL:back_propagate(affineE, {}, softmaxI, softmaxO) affineL:update(affineE, affineI, affineO) @@ -162,10 +172,9 @@ for l = 0, 10, 1 do 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("accurate labels: %d\n", calculate_accurate(output, labelM)) nerv.utils.printf("total frames processed: %.8f\n", softmaxL.total_frames) end end --[[end training]]-- - -```
\ No newline at end of file +``` |