diff options
Diffstat (limited to 'nerv/examples/swb_baseline2.lua')
| -rw-r--r-- | nerv/examples/swb_baseline2.lua | 87 |
1 files changed, 44 insertions, 43 deletions
diff --git a/nerv/examples/swb_baseline2.lua b/nerv/examples/swb_baseline2.lua index 8b5ebb1..38cfb9a 100644 --- a/nerv/examples/swb_baseline2.lua +++ b/nerv/examples/swb_baseline2.lua @@ -1,13 +1,13 @@ require 'htk_io' -gconf = {lrate = 0.8, wcost = 1e-6, momentum = 0.9, +gconf = {lrate = 0.8, wcost = 1e-6, momentum = 0.9, frm_ext = 5, rearrange = true, -- just to make the context order consistent with old results, deprecated - frm_ext = 5, frm_trim = 5, -- trim the first and last 5 frames, TNet just does this, deprecated tr_scp = "/speechlab/users/mfy43/swb50/train_bp.scp", cv_scp = "/speechlab/users/mfy43/swb50/train_cv.scp", htk_conf = "/speechlab/users/mfy43/swb50/plp_0_d_a.conf", initialized_param = {"/speechlab/users/mfy43/swb50/swb_init.nerv", - "/speechlab/users/mfy43/swb50/swb_global_transf.nerv"}} + "/speechlab/users/mfy43/swb50/swb_global_transf.nerv"}, + chunk_size = 1} function make_layer_repo(param_repo) local layer_repo = nerv.LayerRepo( @@ -15,13 +15,13 @@ function make_layer_repo(param_repo) -- global transf ["nerv.BiasLayer"] = { - blayer1 = {dim_in = {429}, dim_out = {429}, params = {bias = "bias1"}}, - blayer2 = {dim_in = {429}, dim_out = {429}, params = {bias = "bias2"}} + blayer1 = {dim_in = {429}, dim_out = {429}, params = {bias = "bias0"}}, + blayer2 = {dim_in = {429}, dim_out = {429}, params = {bias = "bias1"}} }, ["nerv.WindowLayer"] = { - wlayer1 = {dim_in = {429}, dim_out = {429}, params = {window = "window1"}}, - wlayer2 = {dim_in = {429}, dim_out = {429}, params = {window = "window2"}} + wlayer1 = {dim_in = {429}, dim_out = {429}, params = {window = "window0"}}, + wlayer2 = {dim_in = {429}, dim_out = {429}, params = {window = "window1"}} }, -- biased linearity ["nerv.AffineLayer"] = @@ -65,39 +65,39 @@ function make_layer_repo(param_repo) layer_repo:add_layers( { - ["nerv.DAGLayer"] = + ["nerv.GraphLayer"] = { global_transf = { dim_in = {429}, dim_out = {429}, - sub_layers = layer_repo, + layer_repo = layer_repo, connections = { - ["<input>[1]"] = "blayer1[1]", - ["blayer1[1]"] = "wlayer1[1]", - ["wlayer1[1]"] = "blayer2[1]", - ["blayer2[1]"] = "wlayer2[1]", - ["wlayer2[1]"] = "<output>[1]" + {"<input>[1]", "blayer1[1]", 0}, + {"blayer1[1]", "wlayer1[1]", 0}, + {"wlayer1[1]", "blayer2[1]", 0}, + {"blayer2[1]", "wlayer2[1]", 0}, + {"wlayer2[1]", "<output>[1]", 0} } }, main = { dim_in = {429}, dim_out = {3001}, - sub_layers = layer_repo, + layer_repo = layer_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]"] = "<output>[1]" + {"<input>[1]", "affine0[1]", 0}, + {"affine0[1]", "sigmoid0[1]", 0}, + {"sigmoid0[1]", "affine1[1]", 0}, + {"affine1[1]", "sigmoid1[1]", 0}, + {"sigmoid1[1]", "affine2[1]", 0}, + {"affine2[1]", "sigmoid2[1]", 0}, + {"sigmoid2[1]", "affine3[1]", 0}, + {"affine3[1]", "sigmoid3[1]", 0}, + {"sigmoid3[1]", "affine4[1]", 0}, + {"affine4[1]", "sigmoid4[1]", 0}, + {"sigmoid4[1]", "affine5[1]", 0}, + {"affine5[1]", "sigmoid5[1]", 0}, + {"sigmoid5[1]", "affine6[1]", 0}, + {"affine6[1]", "sigmoid6[1]", 0}, + {"sigmoid6[1]", "affine7[1]", 0}, + {"affine7[1]", "<output>[1]", 0} } } } @@ -105,25 +105,25 @@ function make_layer_repo(param_repo) layer_repo:add_layers( { - ["nerv.DAGLayer"] = + ["nerv.GraphLayer"] = { ce_output = { dim_in = {429, 1}, dim_out = {1}, - sub_layers = layer_repo, + layer_repo = layer_repo, connections = { - ["<input>[1]"] = "main[1]", - ["main[1]"] = "ce_crit[1]", - ["<input>[2]"] = "ce_crit[2]", - ["ce_crit[1]"] = "<output>[1]" + {"<input>[1]", "main[1]", 0}, + {"main[1]", "ce_crit[1]", 0}, + {"<input>[2]", "ce_crit[2]", 0}, + {"ce_crit[1]", "<output>[1]", 0} } }, softmax_output = { dim_in = {429}, dim_out = {3001}, - sub_layers = layer_repo, + layer_repo = layer_repo, connections = { - ["<input>[1]"] = "main[1]", - ["main[1]"] = "softmax[1]", - ["softmax[1]"] = "<output>[1]" + {"<input>[1]", "main[1]", 0}, + {"main[1]", "softmax[1]", 0}, + {"softmax[1]", "<output>[1]", 0} } } } @@ -146,7 +146,7 @@ end function make_readers(scp_file, layer_repo) return { - {reader = nerv.TNetReader(gconf, + {reader = nerv.HTKReader(gconf, { id = "main_scp", scp_file = scp_file, @@ -167,10 +167,11 @@ function make_readers(scp_file, layer_repo) end function make_buffer(readers) - return nerv.SGDBuffer(gconf, + return nerv.FrmBuffer(gconf, { buffer_size = gconf.buffer_size, batch_size = gconf.batch_size, + chunk_size = gconf.chunk_size, randomize = gconf.randomize, readers = readers, use_gpu = true |