A neural image contextualised caption generator based on CoreML
A neural image contextualised caption generator based on CoreML
Nosco is written in Swift 4 and uses CoreML to implement the image to text model described in -
“Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge.”
You can read the full research paper by following this link - https://ai.googleblog.com/2016/09/show-and-tell-image-captioning-open.html
1) Xcode 9.0+
2) iOS 11.0+
3) Swift 4.0+
The model in its current state is not ready for production as it has only been trained with MSCOCO dataset for about 40k steps.
1) Mail - akshat.jagga@yahoo.in
2) Website - http://techkindle.com/contact-us