Configuration class that controls neural net combination, where we combine a number of neural nets, trying to find for each layer the optimal weighted combination of the different neural-net parameters. More...
#include <combine-nnet-fast.h>
Public Member Functions | |
NnetCombineFastConfig () | |
void | Register (OptionsItf *opts) |
Configuration class that controls neural net combination, where we combine a number of neural nets, trying to find for each layer the optimal weighted combination of the different neural-net parameters.
Definition at line 50 of file combine-nnet-fast.h.
|
inline |
Definition at line 68 of file combine-nnet-fast.h.
|
inline |
Definition at line 73 of file combine-nnet-fast.h.
References kaldi::nnet2::CombineNnetsFast(), and OptionsItf::Register().
Referenced by main().
BaseFloat alpha |
Definition at line 59 of file combine-nnet-fast.h.
BaseFloat fisher_floor |
Definition at line 56 of file combine-nnet-fast.h.
int32 fisher_minibatch_size |
Definition at line 60 of file combine-nnet-fast.h.
BaseFloat initial_impr |
Definition at line 55 of file combine-nnet-fast.h.
int32 initial_model |
Definition at line 51 of file combine-nnet-fast.h.
int32 max_lbfgs_dim |
Definition at line 65 of file combine-nnet-fast.h.
int32 minibatch_size |
Definition at line 63 of file combine-nnet-fast.h.
int32 num_lbfgs_iters |
Definition at line 53 of file combine-nnet-fast.h.
int32 num_threads |
Definition at line 54 of file combine-nnet-fast.h.
Referenced by main().
BaseFloat regularizer |
Definition at line 66 of file combine-nnet-fast.h.