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.
- numpy
- scipy
- six
- tensorflow (https://www.tensorflow.org/versions/r0.12/get_started/os_setup.html)
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!
Also see this issue, some people have found this discussion helpful #3
Credit for the vast majority of code here goes to suriyadeepan. I've merely created a wrapper to get people started.