nnet-training.h File Reference

`#include "nnet3/nnet-example.h"`

`#include "nnet3/nnet-computation.h"`

`#include "nnet3/nnet-compute.h"`

`#include "nnet3/nnet-optimize.h"`

`#include "nnet3/nnet-example-utils.h"`

`#include "nnet3/nnet-utils.h"`

Include dependency graph for nnet-training.h:

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

Go to the source code of this file.

## Classes | |

struct | NnetTrainerOptions |

struct | ObjectiveFunctionInfo |

class | NnetTrainer |

This class is for single-threaded training of neural nets using standard objective functions such as cross-entropy (implemented with logsoftmax nonlinearity and a linear objective function) and quadratic loss. More... | |

## Namespaces | |

kaldi | |

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

kaldi::nnet3 | |

## Functions | |

void | ComputeObjectiveFunction (const GeneralMatrix &supervision, ObjectiveType objective_type, const std::string &output_name, bool supply_deriv, NnetComputer *computer, BaseFloat *tot_weight, BaseFloat *tot_objf) |

This function computes the objective function, and if supply_deriv = true, supplies its derivative to the NnetComputation object. More... | |