nnet-update.h File Reference

This header provides functionality for sample-by-sample stochastic gradient descent and gradient computation with a neural net. More...

#include "nnet2/nnet-nnet.h"
#include "nnet2/nnet-example.h"
#include "util/table-types.h"

Include dependency graph for nnet-update.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes
class	NnetUpdater

Namespaces
	kaldi
	This code computes Goodness of Pronunciation (GOP) and extracts phone-level pronunciation feature for mispronunciations detection tasks, the reference:
	kaldi::nnet2

Functions
void	FormatNnetInput (const Nnet &nnet, const std::vector< NnetExample > &data, Matrix< BaseFloat > *mat)
	Takes the input to the nnet for a minibatch of examples, and formats as a single matrix. More...
double	DoBackprop (const Nnet &nnet, const std::vector< NnetExample > &examples, Nnet *nnet_to_update, double *tot_accuracy=NULL)
	This function computes the objective function and either updates the model or adds to parameter gradients. More...
double	DoBackprop (const Nnet &nnet, const std::vector< NnetExample > &examples, Matrix< BaseFloat > *examples_formatted, Nnet *nnet_to_update, double *tot_accuracy=NULL)
	This version of DoBackprop allows you to separately call FormatNnetInput and provide the result to DoBackprop; this can be useful when using GPUs because the call to FormatNnetInput can be in a separate thread from the one that uses the GPU. More...
BaseFloat	TotalNnetTrainingWeight (const std::vector< NnetExample > &egs)
	Returns the total weight summed over all the examples... More...
double	ComputeNnetObjf (const Nnet &nnet, const std::vector< NnetExample > &examples, double *tot_accuracy=NULL)
	Computes objective function over a minibatch. More...
double	ComputeNnetObjf (const Nnet &nnet, const std::vector< NnetExample > &examples, int32 minibatch_size, double *tot_accuracy=NULL)
	This version of ComputeNnetObjf breaks up the examples into multiple minibatches to do the computation. More...
double	ComputeNnetGradient (const Nnet &nnet, const std::vector< NnetExample > &examples, int32 batch_size, Nnet *gradient)
	ComputeNnetGradient is mostly used to compute gradients on validation sets; it divides the example into batches and calls DoBackprop() on each. More...

Detailed Description

This header provides functionality for sample-by-sample stochastic gradient descent and gradient computation with a neural net.

See also nnet-compute.h which is the same thing but for whole utterances.

Definition in file nnet-update.h.