Running RNN to create short novels

Below you can find a collection of short stories and dialogues generated using an RNN, Tensorflow and GPT-2 to create short novels about relationships.

A few useful links:

Find out more about Tensorflow: An end-to-end open-source machine learning platform.

If you want to try a Multi-layer Recurrent Neural Networks (LSTM, RNN) for word-level language models in Python using TensorFlow you can use these GitHub files here  or similar packages are available in Github

The research lab OpenAI has released the full version of a text-generating AI system, see more here

Or you can try Talk to Transformer 
Built by Adam King (@AdamDanielKing) as an easier way to play with OpenAI’s new machine learning model. In February, OpenAI unveiled a language model called GPT-2 that generates coherent paragraphs of text one word at a time.

To run Tensorflow and GPT-2 from Open AI you can use Anaconda Distribution.
The open-source Anaconda Distribution is the easiest way to perform Python/R data science and machine learning on Linux, Windows, and Mac OS X.


Forget the roses

Forget the roses. Forget our failing mistakes.
I love you, a failing friend, the only rose.
The wind of Love is a ringless encourage during my hours.
I miss you.
It was a time worth to unknown led by us falling apart.
Saving me was not accidentally; neither a dream.

Can you hear it?

The deep sound of our heart beating.
The deep melancholia of our future.

When the fog of doubts comes

Don’t fall apart.
Don’t escape in a fleeting lie.
Search for the light of your strengths.

The unknown words

Don’t mute the unspoken words carved into the loneliness soul.
Don’t hide behind regrets the unknown words.
Fight back and discover the astonishing power of your knowledge.

Falling leaves

Trying to hide my shadow between the falling leaves.
I could hear your last kiss while you glance at my ego.
There is no secret; just don’t get away your Love as broken glass.
Love is a high standard, but weightless with you.

No Comments

Post A Comment