Tensorflow chatbot demo by @Sirajology on Youtube
Switch branches/tags
Nothing to show
Clone or download
llSourcell Merge pull request #49 from bluetyson/master
import data_utils from seq2seq problem
Latest commit 0ab3101 Aug 23, 2017
Failed to load latest commit information.
ui first Dec 2, 2016
working_dir first Dec 2, 2016
.gitignore first Dec 2, 2016
README.md Update README.md Aug 15, 2017
__init__.py first Dec 2, 2016
data_utils.py first Dec 2, 2016
env_setup.sh first Dec 2, 2016
execute.py changes to read checkpoint model generated by training in tf 0.12-rc1 Dec 12, 2016
neuralconvo.ini first Dec 2, 2016
seq2seq.ini first Dec 2, 2016
seq2seq_model.py import data_utils from seq2seq problem Jun 30, 2017
seq2seq_serve.ini first Dec 2, 2016


Tensorflow Chatbot

Tensorflow Chatbot Demo by @Sirajology on Youtube


This is the full code for 'How to Make an Amazing Tensorflow Chatbot Easily' by @Sirajology on Youtube. In this demo code, we implement Tensorflows Sequence to Sequence model to train a chatbot on the Cornell Movie Dialogue dataset. After training for a few hours, the bot is able to hold a fun conversation.


Use pip to install any missing dependencies


To train the bot, edit the seq2seq.ini file so that mode is set to train like so

mode = train

then run the code like so

python execute.py

To test the bot during or after training, edit the seq2seq.ini file so that mode is set to test like so

mode = test

then run the code like so

python execute.py


The challenge for this video is write an entirely different script using TF Learn to generate Lord of the Ring style sentences. Check out this very similar example, it uses TF Learn to generate Shakespeare-style sentences. Train your model on Lord of the rings text to do something similar! And play around with the hyperparameters to get a more accurate result. Post your GitHub link in the video comments and I'll judge it!

Due date: December 8th

Also see this issue, some people have found this discussion helpful https://github.com/llSourcell/tensorflow_chatbot/issues/3


Credit for the vast majority of code here goes to suriyadeepan. I've merely created a wrapper to get people started.