diff options
| author | Determinant <[email protected]> | 2016-03-13 17:02:58 +0800 |
|---|---|---|
| committer | Determinant <[email protected]> | 2016-03-13 17:02:58 +0800 |
| commit | 5d8f596e8fc5be4538f033405079584e4be00f38 (patch) | |
| tree | 3ea1080087dbb4c2d0b3c2f84504539e405ca793 /tutorial/howto_pretrain_from_tnet.rst | |
| parent | 93eb84aca23526959b76401fd6509f151a589e9a (diff) | |
correct a typoalpha-2
Diffstat (limited to 'tutorial/howto_pretrain_from_tnet.rst')
| -rw-r--r-- | tutorial/howto_pretrain_from_tnet.rst | 23 |
1 files changed, 12 insertions, 11 deletions
diff --git a/tutorial/howto_pretrain_from_tnet.rst b/tutorial/howto_pretrain_from_tnet.rst index 7636478..b37a1a7 100644 --- a/tutorial/howto_pretrain_from_tnet.rst +++ b/tutorial/howto_pretrain_from_tnet.rst @@ -17,6 +17,7 @@ How to Use a Pre-trained Model from TNet - To convert a TNet DNN model file: :: + # compile the tool written in C++: g++ -o tnet_to_nerv <nerv_home>/speech/htk_io/tools/tnet_to_nerv.cpp # conver the model (the third argument indicates the initial number used in naming the parameters) @@ -31,18 +32,18 @@ How to Use a Pre-trained Model from TNet - Create a copy of ``<nerv_home>/speech/htk_io/tools/nerv_to_tnet.lua``. - - Modify the list named ``lnames`` to list the name of layers you want to - put into the output TNet parameter file in order. You may ask why the - NERV-to-TNet converstion is so cumbersome. This is because TNet nnet is a - special case of more general NERV toolkit -- it only allows stacked DNNs - and therefore TNet-to-NERV conversion is lossless but the other direction - is not. Your future NERV network may have multiple branches and that's - why you need to specify how to select and "stack" your layers in the TNet - parameter output. + - Modify the list named ``lnames`` to list the name of layers you want to + put into the output TNet parameter file in order. You may ask why the + NERV-to-TNet converstion is so cumbersome. This is because TNet nnet is a + special case of more general NERV toolkit -- it only allows stacked DNNs + and therefore TNet-to-NERV conversion is lossless but the other direction + is not. Your future NERV network may have multiple branches and that's + why you need to specify how to select and "stack" your layers in the TNet + parameter output. - - Do the conversion by: + - Do the conversion by: - :: + :: - <nerv_home>/install/bin/nerv --use-cpu nerv_to_tnet.lua <your_network_config>.lua <your_trained_params>.nerv <path_to_converted>.nnet + <nerv_home>/install/bin/nerv --use-cpu nerv_to_tnet.lua <your_network_config>.lua <your_trained_params>.nerv <path_to_converted>.nnet |