Image recognition
- Dominant language
- TypeScript
- Stars
- 14.9k
- Forks
- 1.1k
- PR merge metrics
- No merged PRs in 30d
Description

Thanks a lot guys for creating such awesome tool for neural networks for javascript community.
I have tried brain.js for creating NN for image recognition. Super-simple one - do the image contains [samoyed](https://www.google.com/search?biw=2273&bih=1216&tbm=isch&sa=1&ei=t7ZSXL-EF6XLjgTYhICQBA&q=samoyed&oq=samoyed&gs_l=img.3..0i67j0l9.13445.13445..13637...0.0..0.177.177.0j1......1....1..gws-wiz-img.483i7vNy_mM) or no.
And now I am a bit struggled. Cannot find anything about image recognition in the repo (only #176 but nothing was helpful from here)
- Does the brain.js good solution for image recognition?
- How to proceed?
- How to prepare image data?
- Why it takes so much time?
I am looking for answers and would be good if you will create some example :)
I am now doing something like [this](https://gist.github.com/dmtrKovalenko/b7bdf95c4c3b69e1873c74fc5f279aca) but it doesn't work anyway. 64x64 images processing deadly slow. For different image resolutions I am getting `error: NaN`.
Contributor guide
Assessment
This issue has not been assessed yet.