Skip to content

michaellin99999/Conversational-AI-Chatbot-using-Practical-Seq2Seq

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Conversational-AI-Chatbot-using-Practical-Seq2Seq

A simple open domain generative based chatbot based on Recurrent Neural Networks

REQUIREMENTS

  • python 3.5.4
  • tensorflow 0.12.1

TRAINING YOUR OWN MODEL

Please refer to the link below to download the open source dataset. https://www.cs.cornell.edu/~cristian/Cornell_Movie-Dialogs_Corpus.html

The dataset will contain many files out of which two files are to be used by us.

  1. “movie_lines.txt”
  2. “movie_conversations.txt”

Copy both of these files into the github repository containing main.py file. These files are imported on the line 17 “#Importing the dataset”. Please let me know if you have any questions. And do give a star to my GitHub repo if it is of help to you.

USING PRETRAINED WEIGHTS

  1. For using the pretrained weights download them at https://gofile.io/?c=mV7ySi.
  2. Unzip the file and store them in a folder named "weights" inside the folder chatbot-pretrained weights.
  3. Run the "the_best_chatbot.py" file.

Source: Semeh Ben Salem

Image Source: Semeh Ben Salem https://www.linkedin.com/in/semeh-ben-salem-60b5759a/

For a better understanding please refer to my article https://medium.com/@harshpanwar9524/understanding-rnns-lstm-and-seq2seq-model-using-a-practical-implementation-of-chatbot-in-2b9ab76d1eda

About

A simple open domain generative based chatbot based on Recurrent Neural Networks

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%