项目作者: akshatjagga

项目描述 :
A neural image contextualised caption generator based on CoreML
高级语言: Swift
项目地址: git://github.com/akshatjagga/Nosco.git
创建时间: 2018-06-09T19:33:35Z
项目社区:https://github.com/akshatjagga/Nosco

开源协议:

下载


Nosco

A neural image contextualised caption generator based on CoreML

Introduction

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

Screenshots

Requirements

1) Xcode 9.0+
2) iOS 11.0+
3) Swift 4.0+

Model

The model in its current state is not ready for production as it has only been trained with MSCOCO dataset for about 40k steps.

Contact Me!

1) Mail - akshat.jagga@yahoo.in
2) Website - http://techkindle.com/contact-us