Python code to generate text using a pretrained character-based RNN

Re:Python code to generate text using a pretrained character... by minimaxir on Friday August 18, 2017 @06:01PM (#15050107)

Repo author here:

Unfortunately, a lot of the examples people give for text generation in general are cherrypicked, which leads to a selection bias toward the robustness of text generation (see my previous rant: https://news.ycombinator.com/item?id=14949220)

In terms of size vs. performance (including retraining), the 128-cell LSTM was the best balance for a repo like this. (The 3-layer 512-cell networks used in the original Karpathy examples are hundreds of MB)

I recommend looking at the examples in the /output folder for more robust examples than the ones in the README.

[ Parent | on HN ]

Re:Python code to generate text using a pretrained character... by backpropaganda on Friday August 18, 2017 @09:12PM (#15050986)

You could make the bigger model available elsewhere, and allow the user to download the bigger model if they want to.

Why don't you have a priming ability? That is, generating starting from some context text. Might be useful for a lot of applications.

[ Parent | on HN ]

Re:Python code to generate text using a pretrained character... by minimaxir on Friday August 18, 2017 @09:23PM (#15051046)

As noted in the README, supporting bigger models is an option for future development. (I still would need to train/optimize the model which does take time/money. Additionally, file hosting is not free and I am not making any revenue off of this project currently)

The generate() function does have priming with a `prefix` parameter; see the demo.

[ Parent | on HN ]