summaryrefslogblamecommitdiff
path: root/kaldi_io/example/swb_baseline_basic.lua
blob: e6c81450c55cc83fd3dd0acd67dc222dffb5af6c (plain) (tree) 
96a3241 ^





























































































































































1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157





























































































































































                                                                                                                                                                                                                                                                         
require 'kaldi_io'
gconf = {lrate = 0.8, wcost = 1e-6, momentum = 0.9,
        cumat_type = nerv.CuMatrixFloat,
        mmat_type = nerv.MMatrixFloat,
        frm_ext = 5,
        tr_rspecifier = "ark:/slfs6/users/ymz09/kaldi/src/featbin/copy-feats scp:/slfs6/users/ymz09/swb_ivec/train_bp.scp ark:- |",
        cv_rspecifier = "ark:/slfs6/users/ymz09/kaldi/src/featbin/copy-feats scp:/slfs6/users/ymz09/swb_ivec/train_cv.scp ark:- |",
        initialized_param = {"/slfs6/users/ymz09/swb_ivec/swb_init.nerv",
                "/slfs6/users/ymz09/swb_ivec/swb_global_transf.nerv"},
        debug = false}

function make_sublayer_repo(param_repo)
    return nerv.LayerRepo(
    {
        -- global transf
        ["nerv.BiasLayer"] =
        {
            blayer1 = {{bias = "bias1"}, {dim_in = {429}, dim_out = {429}}},
            blayer2 = {{bias = "bias2"}, {dim_in = {429}, dim_out = {429}}}
        },
        ["nerv.WindowLayer"] =
        {
            wlayer1 = {{window = "window1"}, {dim_in = {429}, dim_out = {429}}},
            wlayer2 = {{window = "window2"}, {dim_in = {429}, dim_out = {429}}}
        },
        -- biased linearity
        ["nerv.AffineLayer"] =
        {
            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"] =
        {
            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"] =
        {
            ce_crit = {{}, {dim_in = {3001, 1}, dim_out = {1}, compressed = true}}
        }
    }, param_repo, gconf)
end

function make_layer_repo(sublayer_repo, param_repo)
    return nerv.LayerRepo(
    {
        ["nerv.DAGLayer"] =
        {
            global_transf = {{}, {
                dim_in = {429}, dim_out = {429},
                sub_layers = sublayer_repo,
                connections = {
                    ["<input>[1]"] = "blayer1[1]",
                    ["blayer1[1]"] = "wlayer1[1]",
                    ["wlayer1[1]"] = "blayer2[1]",
                    ["blayer2[1]"] = "wlayer2[1]",
                    ["wlayer2[1]"] = "<output>[1]"
                }
            }},
            main = {{}, {
                dim_in = {429, 1}, dim_out = {1},
                sub_layers = sublayer_repo,
                connections = {
                    ["<input>[1]"] = "affine0[1]",
                    ["affine0[1]"] = "sigmoid0[1]",
                    ["sigmoid0[1]"] = "affine1[1]",
                    ["affine1[1]"] = "sigmoid1[1]",
                    ["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]"] = "ce_crit[1]",
                    ["<input>[2]"] = "ce_crit[2]",
                    ["ce_crit[1]"] = "<output>[1]"
                }
            }}
        }
    }, param_repo, gconf)
end

function get_network(layer_repo)
    return layer_repo:get_layer("main")
end

function make_readers(feature_rspecifier, layer_repo)
    return {
                {reader = nerv.KaldiReader(gconf,
                    {
                        id = "main_scp",
                        feature_rspecifier = feature_rspecifier,
                        frm_ext = gconf.frm_ext,
                        mlfs = {
                            phone_state = {
                                targets_rspecifier = "ark:/slfs6/users/ymz09/kaldi/src/bin/ali-to-pdf /slfs6/users/ymz09/swb_ivec/final.mdl \"ark:gunzip -c /slfs6/users/ymz09/swb_ivec/ali.*.gz |\" ark:- | /slfs6/users/ymz09/kaldi/src/bin/ali-to-post ark:- ark:- |",
                                format = "map"
                            }
                        },
                        global_transf = layer_repo:get_layer("global_transf")
                    }),
                data = {main_scp = 429, phone_state = 1}}
            }
end

function make_buffer(readers)
    return nerv.SGDBuffer(gconf,
        {
            buffer_size = gconf.buffer_size,
            randomize = gconf.randomize,
            readers = readers
        })
end

function get_input_order()
    return {"main_scp", "phone_state"}
end

function get_accuracy(sublayer_repo)
    local ce_crit = sublayer_repo:get_layer("ce_crit")
    return ce_crit.total_correct / ce_crit.total_frames * 100
end

function print_stat(sublayer_repo)
    local ce_crit = sublayer_repo:get_layer("ce_crit")
    nerv.info("*** training stat begin ***")
    nerv.printf("cross entropy:\t\t%.8f\n", ce_crit.total_ce)
    nerv.printf("correct:\t\t%d\n", ce_crit.total_correct)
    nerv.printf("frames:\t\t\t%d\n", ce_crit.total_frames)
    nerv.printf("err/frm:\t\t%.8f\n", ce_crit.total_ce / ce_crit.total_frames)
    nerv.printf("accuracy:\t\t%.3f%%\n", get_accuracy(sublayer_repo))
    nerv.info("*** training stat end ***")
end
Powered by cgit, Themed by Ted Yin.