Home

Awesome

Styles Vision Demo

A Demo application using Vision and CoreML frameworks to detect the most likely style of the given image.

<div align="center"> <img src="https://github.com/cocoa-ai/StylesVisionDemo/blob/master/Screenshot.png" alt="StylesVisionDemo" width="300" height="534" /> </div>

Model

This demo is based on the "Finetuning CaffeNet on Flickr Style" neural network classifier, which was converted from original Caffe model to CoreML model using coremltools python package.

Requirements

Installation

git clone https://github.com/cocoa-ai/StylesVisionDemo.git
cd StylesVisionDemo
pod install
open Styles.xcworkspace/

Download the CoreMl model and add the file to "Resources" folder in the project's directory.

Build the project and run it on a simulator or a device with iOS 11.

Conversion

cd Convert
./download.sh
python convert.py

Author

Vadym Markov, markov.vadym@gmail.com

Credits

Original "Finetuning CaffeNet on Flickr Style" Caffe model

References