I am the author of [tensorflow.rb](https://github.com/somaticio/tensorflow.rb) the Ruby API for Tensorflow.
The Ruby community has been very enthusiastic about developing a Ruby API for tensorflow (more on this [thread](https://github.com/tensorflow/tensorflow/issues/50)) and I decided to work on it.
I faced incredible challenges along the way but I do have many interesting findings that I would like to share with you guys. The tensorflow.rb gem can be found on this [link](https://github.com/somaticio/tensorflow.rb). Aside from that, I have written three blog posts where I have given a very brief summary of the work
1. [Introductory blog post](https://medium.com/@Arafat./introducing-tensorflow-ruby-api-e77a477ff16e#.mhvj9ojlj)
2. [Developers blog post](https://medium.com/@Arafat./ruby-tensorflow-for-developers-2ec56b8668c5#.97tng1qqi) (This post is for rubyists and developers of other languages.)
3. [Image Recognition Tutorial](https://medium.com/@Arafat./image-recognition-in-ruby-tensorflow-df5d5c05389b#.ty1vygtrg)
The project still needs a lot of work and contributions are very welcome. I encourage everyone to read the blog posts and then install and play with Tensorflow.rb. Any comments/suggestions would be nice and you can always post your thoughts on the [gitter channel](https://gitter.im/tensorflowrb/Lobby?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge) or comment below.