wiki.ziemers.de

ziemer's informatik Wiki

Benutzer-Werkzeuge

Webseiten-Werkzeuge

Zuletzt angesehen:
wiki:software:beuthbot:rasa:training

Unterschiede

Hier werden die Unterschiede zwischen zwei Versionen angezeigt.

Link zu dieser Vergleichsansicht

Beide Seiten der vorigen Revision Vorhergehende Überarbeitung
Nächste Überarbeitung 		Vorhergehende Überarbeitung
wiki:software:beuthbot:rasa:training [22.07.2020 19:29]
Lukas Danckwerth 		wiki:software:beuthbot:rasa:training [22.07.2020 19:39] (aktuell)
Lukas Danckwerth
Zeile 27: Zeile 27:
 This guide explains how to create a new training model for Rasa. The following image gives you an overview of the files and steps to do. `*.chatito` files places in the `training/app/input/` directory are used by [Chatito](#Chatito) to create `JSON` files in the `training/app/data/` directory. These `JSON` files are used by Rasa to create the training model which will be placed in the `training/app/model/`. This guide explains how to create a new training model for Rasa. The following image gives you an overview of the files and steps to do. `*.chatito` files places in the `training/app/input/` directory are used by [Chatito](#Chatito) to create `JSON` files in the `training/app/data/` directory. These `JSON` files are used by Rasa to create the training model which will be placed in the `training/app/model/`.
  
-![alternative text](http://www.plantuml.com/plantuml/proxy?cache=no&src=https://raw.githubusercontent.com/beuthbot/rasa/database-understanding/.documentation/uml/training.txt)+<uml> 
 +@startuml 
 +package Rasa { 
 + 
 +folder training/app/input as TI { 
 +artifact FILE1.chatito 
 +artifact FILE2.chatito 
 +} 
 + 
 +card "docker-compose -f docker-compose.generate-data.yml up" as C1 
 + 
 +folder training/app/data as TD { 
 +artifact FILE1.json 
 +artifact FILE2.json 
 +} 
 + 
 +card "docker-compose -f docker-compose.train-model.yml up" as C2 
 + 
 +folder training/app/model as M { 
 +artifact "nlu-YYYYMMDD-HHMMSS.tar.gz" 
 +} 
 + 
 +TI --> C1 
 +C1 --> TD 
 +TD --> C2 
 +C2 --> M 
 + 
 +} 
 +@enduml 
 +</uml>
  
 === 1 -  Provide new input training data === === 1 -  Provide new input training data ===
  
-Modify or add  `*.chatito` files in the `training/app/input/` directory to provide a new functionality. For more information about `Chatito` have a look a the [Chatito](#Chatito) section of this document.+Modify or add  `*.chatito` files in the `training/app/input/` directory to provide a new functionality. For more information about `Chatito` have a look a the [[https://github.com/rodrigopivi/Chatito|Chatito]] section of this document.
  
 == 1.1 - Generate training datasets == == 1.1 - Generate training datasets ==
Zeile 76: Zeile 105:
 </code> </code>
  
-> For a fast convenient way to [generate training datasets](#1.1---Generate-training-datasets) and [create a model](#2---Create-model-with-Rasa) simply use the `docker-compose.yml` file in the `training` directory. +> For a fast convenient way to [[#1.1---Generate-training-datasets|generate training datasets]] and [[#2---Create-model-with-Rasa|create a model]] simply use the `docker-compose.yml` file in the `training` directory. 
-> <code> +<code> 
-> # runs both the dataset generation and train model container +# runs both the dataset generation and train model container 
-> docker-compose -f docker-compose.yml up +docker-compose -f docker-compose.yml up 
->  +  
-> # .. or simply +# .. or simply 
-> docker-compose up +docker-compose up 
-> </code>+</code>
  
 === 3 - Check generated file === === 3 - Check generated file ===
wiki/software/beuthbot/rasa/training.1595438999.txt.gz · Zuletzt geändert: 22.07.2020 19:29 von Lukas Danckwerth

Seiten-Werkzeuge