From 08a52c03a77ce13ae4f6a4deb06ab0ae274d399a Mon Sep 17 00:00:00 2001
From: Determinant <ted.sybil@gmail.com>
Date: Tue, 2 Jun 2015 23:07:15 +0800
Subject: fix a bug: input[1] should be input[2] (since Lua arrays are 1-based)
---
examples/test_nn_lib.lua | 60 +++++++++++++++++++++++++++++++++++++-----------
layer/softmax_ce.lua | 4 +++-
nn/layer_dag.lua | 4 ++++
3 files changed, 54 insertions(+), 14 deletions(-)
diff --git a/examples/test_nn_lib.lua b/examples/test_nn_lib.lua
index fd7167a..ec338fe 100644
--- a/examples/test_nn_lib.lua
+++ b/examples/test_nn_lib.lua
@@ -1,25 +1,46 @@
-require 'layer.affine'
-require 'layer.sigmoid'
-require 'layer.softmax_ce'
+-- require 'layer.affine'
+-- require 'layer.sigmoid'
+-- require 'layer.softmax_ce'
gconf = {lrate = 0.8, wcost = 1e-6, momentum = 0.9,
mat_type = nerv.CuMatrixFloat,
batch_size = 10}
-param_repo = nerv.ParamRepo({"affine.param"})
+param_repo = nerv.ParamRepo({"converted.nerv"})
sublayer_repo = nerv.LayerRepo(
{
["nerv.AffineLayer"] =
{
- affine1 = {{ltp = "a", bp = "b"}, {dim_in = {429}, dim_out = {2048}}}
+ affine0 = {{ltp = "affine0_ltp", bp = "affine0_bp"},
+ {dim_in = {429}, dim_out = {2048}}},
+ affine1 = {{ltp = "affine1_ltp", bp = "affine1_bp"},
+ {dim_in = {2048}, dim_out = {2048}}},
+ affine2 = {{ltp = "affine2_ltp", bp = "affine2_bp"},
+ {dim_in = {2048}, dim_out = {2048}}},
+ affine3 = {{ltp = "affine3_ltp", bp = "affine3_bp"},
+ {dim_in = {2048}, dim_out = {2048}}},
+ affine4 = {{ltp = "affine4_ltp", bp = "affine4_bp"},
+ {dim_in = {2048}, dim_out = {2048}}},
+ affine5 = {{ltp = "affine5_ltp", bp = "affine5_bp"},
+ {dim_in = {2048}, dim_out = {2048}}},
+ affine6 = {{ltp = "affine6_ltp", bp = "affine6_bp"},
+ {dim_in = {2048}, dim_out = {2048}}},
+ affine7 = {{ltp = "affine7_ltp", bp = "affine7_bp"},
+ {dim_in = {2048}, dim_out = {3001}}}
},
["nerv.SigmoidLayer"] =
{
- sigmoid1 = {{}, {dim_in = {2048}, dim_out = {2048}}}
+ sigmoid0 = {{}, {dim_in = {2048}, dim_out = {2048}}},
+ sigmoid1 = {{}, {dim_in = {2048}, dim_out = {2048}}},
+ sigmoid2 = {{}, {dim_in = {2048}, dim_out = {2048}}},
+ sigmoid3 = {{}, {dim_in = {2048}, dim_out = {2048}}},
+ sigmoid4 = {{}, {dim_in = {2048}, dim_out = {2048}}},
+ sigmoid5 = {{}, {dim_in = {2048}, dim_out = {2048}}},
+ sigmoid6 = {{}, {dim_in = {2048}, dim_out = {2048}}}
},
["nerv.SoftmaxCELayer"] =
{
- softmax_ce1 = {{}, {dim_in = {2048, 2048}, dim_out = {}}}
+ softmax_ce0 = {{}, {dim_in = {3001, 3001}, dim_out = {}}}
}
}, param_repo, gconf)
@@ -28,20 +49,33 @@ layer_repo = nerv.LayerRepo(
["nerv.DAGLayer"] =
{
main = {{}, {
- dim_in = {429, 2048}, dim_out = {},
+ dim_in = {429, 3001}, dim_out = {},
sub_layers = sublayer_repo,
connections = {
- ["<input>[1]"] = "affine1[1]",
+ ["<input>[1]"] = "affine0[1]",
+ ["affine0[1]"] = "sigmoid0[1]",
+ ["sigmoid0[1]"] = "affine1[1]",
["affine1[1]"] = "sigmoid1[1]",
- ["sigmoid1[1]"] = "softmax_ce1[1]",
- ["<input>[2]"] = "softmax_ce1[2]"
+ ["sigmoid1[1]"] = "affine2[1]",
+ ["affine2[1]"] = "sigmoid2[1]",
+ ["sigmoid2[1]"] = "affine3[1]",
+ ["affine3[1]"] = "sigmoid3[1]",
+ ["sigmoid3[1]"] = "affine4[1]",
+ ["affine4[1]"] = "sigmoid4[1]",
+ ["sigmoid4[1]"] = "affine5[1]",
+ ["affine5[1]"] = "sigmoid5[1]",
+ ["sigmoid5[1]"] = "affine6[1]",
+ ["affine6[1]"] = "sigmoid6[1]",
+ ["sigmoid6[1]"] = "affine7[1]",
+ ["affine7[1]"] = "softmax_ce0[1]",
+ ["<input>[2]"] = "softmax_ce0[2]"
}
}}
}
}, param_repo, gconf)
df = nerv.ChunkFile("input.param", "r")
-label = nerv.CuMatrixFloat(10, 2048)
+label = nerv.CuMatrixFloat(10, 3001)
label:fill(0)
for i = 0, 9 do
label[i][i] = 1.0
@@ -51,7 +85,7 @@ input = {df:read_chunk("input", gconf).trans, label}
output = {}
err_input = {}
err_output = {input[1]:create()}
-sm = sublayer_repo:get_layer("softmax_ce1")
+sm = sublayer_repo:get_layer("softmax_ce0")
main = layer_repo:get_layer("main")
main:init()
for i = 0, 3 do
diff --git a/layer/softmax_ce.lua b/layer/softmax_ce.lua
index 3dfebc5..09eb3a9 100644
--- a/layer/softmax_ce.lua
+++ b/layer/softmax_ce.lua
@@ -27,6 +27,8 @@ function SoftmaxCELayer:propagate(input, output)
local ce = soutput:create()
ce:log_elem(soutput)
ce:mul_elem(ce, input[2])
+-- print(input[1][0])
+-- print(soutput[1][0])
-- add total ce
self.total_ce = self.total_ce - ce:rowsum():colsum()[0]
self.total_frames = self.total_frames + soutput:nrow()
@@ -34,5 +36,5 @@ end
function SoftmaxCELayer:back_propagate(next_bp_err, bp_err, input, output)
-- softmax output - label
- next_bp_err[1]:add(self.soutput, input[1], 1.0, -1.0)
+ next_bp_err[1]:add(self.soutput, input[2], 1.0, -1.0)
end
diff --git a/nn/layer_dag.lua b/nn/layer_dag.lua
index 8ea28a0..1ab18fa 100644
--- a/nn/layer_dag.lua
+++ b/nn/layer_dag.lua
@@ -219,6 +219,10 @@ function nerv.DAGLayer:back_propagate(next_bp_err, bp_err, input, output)
self:set_outputs(output)
for i = #self.queue, 1, -1 do
local ref = self.queue[i]
+ -- print(ref.layer.id)
ref.layer:back_propagate(ref.err_outputs, ref.err_inputs, ref.inputs, ref.outputs)
+ -- if #ref.err_outputs > 0 then
+ -- print(ref.err_outputs[1])
+ -- end
end
end
--
cgit v1.2.3-70-g09d2